TWI827030B - Method and detecting device for detecting a detected object - Google Patents

Abstract

A method for detecting a detected object by a detecting device is provided. The method includes transmitting a request for detecting the detected object; receiving the position point of the detected object; obtaining a plurality of detecting images along a plurality of detecting directions on the position point of the detected object; obtaining a detection result based on the plurality of detecting images, wherein the detection result is generated based on a comparison between the plurality of detecting images and a corresponding point of a base object corresponding to the detecting object.

Description

A method and detection device for detecting an object to be detected

The present invention relates to the field of detecting objects, and in particular, to a method and a detection device for detecting an object to be detected.

Although today's anti-counterfeiting technology is advancing rapidly, there are still many problems with anti-counterfeiting technology for art, jewelry, antiques and other items. Some identification techniques require sampling of the items to be identified, which may damage the integrity of the items to be identified. However, it is difficult to fully grasp the actual condition of the items to be identified by observing them with the naked eye alone. In addition, if identification is performed through electronic equipment, it is difficult to ensure whether the information stored in the electronic equipment has been tampered with or replaced. Therefore, if electronic instruments are to be used for identification, the security and non-tamperability of the data need to be ensured.

The present invention is completed in view of the above problems, and provides a method and a detection device for detecting an object to be detected.

In order to solve the above problems, the present invention provides a method for detecting an object to be detected by a detection device. The method includes: transmitting a request to detect the object to be detected; receiving the positioning point of the object to be detected; Obtain multiple detection images along multiple detection directions at the positioning point of the detection object; and obtain a detection result based on the multiple detection images, wherein the detection The result is generated based on a comparison of the plurality of detection images and a corresponding positioning point of a reference object corresponding to the object to be detected.

In order to solve the above problems, the present invention also provides a detection device for detecting an object to be detected. The detection device includes: an image capture unit used to obtain multiple detection images; a movement control unit, The movement control unit is used to enable the image capture unit to move when detecting the object to be detected; a processor coupled to the image capture unit and the mobile unit; a transmission unit, the transmission unit coupled to the processor; a receiving unit coupled to the processor; and a storage device coupled to the processor and storing a plurality of instructions that when executed by the processor The processor is caused to: transmit a request for detecting the object to be detected through the transmission unit; receive the positioning point of the object to be detected through the receiving unit; and cause the image capture unit to locate the object to be detected through the movement control unit. At the positioning point, the plurality of detection images are obtained along multiple detection directions; and a detection result is obtained based on the plurality of detection images, wherein the detection result is based on the multiple detection images and an image corresponding to the object to be detected. Produced by a comparison of a corresponding positioning point of the reference object.

In order to solve the above problem, the present invention also provides a method for detecting an object to be detected by a server. The method includes: receiving a request to detect the object to be detected; sending the positioning point of the object to be detected; receiving Multiple detection images obtained along multiple detection directions at the positioning point of the object to be detected; and obtaining a detection result based on the multiple detection images, wherein the detection result is based on the multiple detection images and the corresponding Produced by a comparison of the test substance to a reference substance.

Through the above method, the detection system saves the information of the reference object and thereby limits the sampling points of the reference object (that is, the corresponding positioning point). In this way, the detection device must first upload the information of the object to be detected so that the detection system can confirm the corresponding reference object before obtaining the positioning point where the image of the object to be detected needs to be captured. This method can not only safely preserve the identification information of the reference object, but also It is difficult to directly obtain the sampling point of the reference material, which also makes it more difficult for counterfeit products to pass detection. In addition, if the information of the reference object is stored in a blockchain storage device, the security and non-tamperability of the information can be further improved.

101, 102: Sampling system

10:Server

11: Internal storage device

20: Sampling device

30:Online storage device

21, 41: Mobile control unit

22, 42: Image capture unit

23, 43: Processor

24, 44: Storage

240: Sampling procedure

241, 441: Positioning module

242: Sampling module

25, 45: Transmission unit

300: Sampling method

S310-S330, S610-S640: steps

401, 402: Detection system

40:Detection device

440:Detection procedure

442:Detection module

46: Receiving unit

600:Detection method

710: First imaging range

711: Image acquisition area

7111-7116: Image acquisition block

720: Second imaging range

760: First sampled image

761: First sampling area

7611-7616: The first sampling block

770: Second sampling image

771: Second sampling area

7711-7716: Second sampling block

In order to more clearly explain the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the purpose of describing the embodiments or the prior art. For some embodiments of the application, those of ordinary skill in the art can also obtain other drawings based on these drawings without exerting creative efforts.

FIG. 1A is a block diagram of a sampling system for establishing identification data for reference objects and performing sampling according to the present invention.

FIG. 1B is a block diagram of another sampling system of the present invention for establishing identification data for reference objects and performing sampling.

Figure 2 is a block diagram of a sampling device for establishing identification data on a reference object and performing sampling according to the present invention.

Figure 3 is a flow chart of a sampling method for establishing identification data for a reference object and performing sampling according to the present invention.

Figure 4A is a block diagram of a detection system for detecting objects to be detected according to the present invention.

Figure 4B is a block diagram of another detection system for detecting objects to be detected according to the present invention.

Figure 5 is a block diagram of a detection device for detecting an object to be detected according to the present invention.

Figure 6 is a flow chart of a detection method for detecting an object to be detected according to the present invention.

FIG. 7A shows a schematic diagram of the image capturing unit capturing a sampling image in a sampling direction at the positioning point of the reference object according to an exemplary embodiment of the present invention.

FIG. 7B shows a schematic diagram of the image capturing unit capturing a sampling image in another sampling direction at the positioning point of the reference object according to an exemplary embodiment of the present invention.

8A-8E are photos of different sampling images captured on a reference object according to an exemplary embodiment of the present invention.

8F to 8J are photos of different detection images captured on the object to be detected according to an exemplary embodiment of the present invention.

9A and 9B are sampling images of different gemstones sampled with the same processing method in the same sampling direction according to an exemplary embodiment of the present invention.

Figure 10A is a photo of antique utensils with the same texture but different textures.

10B and 10C are sampling images of different antique utensils shown in FIG. 10A sampled in the same sampling direction according to an exemplary embodiment of the present invention.

The following description contains specific information related to exemplary embodiments of the present invention. The drawings in this disclosure and their accompanying detailed description are merely exemplary embodiments. However, the present invention is not limited to these exemplary embodiments. Other variations and embodiments of the invention will occur to those skilled in the art. Unless otherwise stated, the same or corresponding elements in the drawings may be designated by the same or corresponding reference numerals. Furthermore, the drawings and illustrations in this disclosure are generally not to scale and are not intended to correspond to actual relative sizes.

For purposes of consistency and ease of understanding, identical features are identified by reference numbers in the illustrative drawings (although in some examples they are not). However, features in different embodiments may differ in other respects and therefore should not be narrowly limited to those shown in the drawings.

Terms such as "at least one embodiment", "an embodiment", "multiple embodiments", "different embodiments", "some embodiments", "this embodiment", etc. may indicate the implementation of the invention so described. Modes may include specific features, structures, or characteristics, but not every possible embodiment of the invention must include a particular feature, structure, or characteristic. Furthermore, repeated use of the phrases "in one embodiment" and "in this embodiment" do not necessarily refer to the same embodiment, although they may be. Furthermore, phrases such as "embodiments" used in connection with "the present invention" do not mean that all embodiments of the invention must include a particular feature, structure or characteristic, and should be understood to mean "at least some embodiments of the invention" ” includes the specific features, structures or characteristics described. The term "coupled" is defined as a connection, whether directly or indirectly through intervening components, and is not necessarily limited to physical connections. When the term "includes" is used, it means "including but not limited to," which expressly indicates the open inclusion or relationship of stated combinations, groups, series, and equivalents.

Additionally, for purposes of explanation and not limitation, specific details such as functional entities, technologies, protocols, standards, etc. are set forth to provide an understanding of the described technologies. In other examples, detailed descriptions of well-known methods, techniques, systems, architectures, etc. are omitted to avoid obscuring the narrative with unnecessary detail.

The terms "first", "second" and "third" in the description of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than describing a specific sequence. Furthermore, the term "includes" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or modules is not limited to the listed steps or modules, but optionally also includes steps or modules that are not listed, or optionally It also includes other steps or modules that are inherent to such processes, methods, products, or devices.

Those skilled in the art will immediately recognize that any computing function or algorithm described in this invention may be implemented by hardware, software, or a combination of software and hardware. The functions described are available for The corresponding module can be software, hardware, firmware, or any combination thereof. Software implementations may include computer-executable instructions stored on computer-readable media such as memory or other types of storage. For example, one or more microprocessors or general purpose computers with communications processing capabilities may be programmed with corresponding executable instructions to design and execute the described network functions or algorithms. A processor, microprocessor or general-purpose computer may be formed by an Application Specific Integrated Circuit (ASIC), a programmable logic array, and/or use one or more Digital Signal Processors (DSP). Although several of the exemplary embodiments described in this specification are directed to software installed and executed on computer hardware, alternative exemplary embodiments in which the embodiments are implemented in firmware or hardware or a combination of hardware and software are also contemplated herein. within the scope of the invention.

The storage device can be a computer-readable medium, including but not limited to RAM (Random Access Memory), ROM (Read Only Memory), and EPROM (Erasable Programmable Memory). Read-Only Memory), electrically erasable programmable read-only memory EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, compact disc read-only memory CD ROM (Compact Disc Read-Only Memory), magnetic cartridge , magnetic tape, disk memory, or any other equivalent medium capable of storing computer-readable instructions.

The coupling between the devices of the present invention can adopt customized protocols or follow existing standards or de facto standards, including but not limited to Ethernet, IEEE 802.11 or IEEE 802.15 series, wireless USB or telecommunications standards (including but not limited to GSM (Global) System for Mobile Communications, global mobile communications system), CDMA2000 (Code Division Multiple Access, code division multiple access technology), TD-SCDMA (Time Division-Synchronization Code Division Multiple Access, time division synchronization code division multiple access technology), WiMAX (World Interoperability for Microwave Access, global microwave access Interoperability), 3GPP-LTE (Long Term Evolution, long-term evolution technology) or TD-LTE (Time Division Long Term Evolution, time division long-term evolution technology)). In addition, each apparatus of the present invention may also each include any device configured to transmit and/or store data to and receive data from a computer-readable medium. Furthermore, each device of the present invention may include a computer system interface that enables data to be stored on or received from the storage device. For example, each device of the present invention may include a chip set supporting peripheral component interconnect (Peripheral Component Interconnect, PCI) and high-speed peripheral component interconnect (Peripheral Component Interconnect Express, PCIe) bus protocols, dedicated bus protocols, and universal serial bus (Universal serial bus). Serial Bus (USB) protocol, I2C, or any other logical and physical structure that can be used to interconnect peer devices.

The present invention will be described in further detail below with reference to the embodiments of the drawings.

Please refer to FIG. 1A. FIG. 1A is a block diagram of a sampling system 101 for establishing identification data on a reference object and performing sampling according to the present invention. In one embodiment, the sampling system 101 includes a server 10 and a sampling device 20 . The server 10 may include an internal storage device 11 to store the sampling results. In one embodiment, when the sampling device 20 receives a sampling request, the sampling device 20 can be coupled with the server 10 to complete the sampling method of the present invention. After the sampling system 101 completes the sampling method, the sampling device 20 can stop coupling with the server 10 .

Please refer to FIG. 1B . FIG. 1B is a block diagram of another sampling system 102 provided by the present invention for establishing identification data on a reference object and performing sampling. In one embodiment, the sampling system 102 includes a server 10 , a sampling device 20 and an online storage device 30 . In one embodiment, when the sampling device 20 receives a sampling request, the sampling device 20 can be coupled with the server 10, and the server 10 can be further coupled with the online storage device 30 to complete the sampling according to the present invention. method. After the sampling system 102 completes the sampling method, the sampling device 20 can be disconnected from the server 10 , and the server 10 can also be disconnected from the online storage device 30 . In another embodiment, when the sampling device 20 receives a When sampling is required, the sampling device 20 can be coupled to the server 10 and the online storage device 30 to complete the sampling method of the present invention. After the sampling system 102 completes the sampling method, the sampling device 20 can be coupled to the server 10 and the online storage device 30 .

In the embodiment, the online storage device 30 may be a network data storage device or a blockchain storage device. When the online storage device 30 is a blockchain storage device, the possibility of the sampling results being tampered with or replaced can be reduced through the characteristics of the blockchain. In the embodiment, the online storage device 30 can store records of all transactions of the benchmark, inspection time and results, and updated pictures.

Please refer to FIG. 2. FIG. 2 is a block diagram of a sampling device 20 for establishing identification data on a reference object and performing sampling according to the present invention. The sampling device 20 may be a mobile phone, a tablet computer, a desktop computer, a notebook computer, a camera, a video recorder, or other electronic equipment, which is not limited here. The sampling device 20 includes a movement control unit 21, an image capture unit 22, a processor 23, a storage 24 and a transmission unit 25.

The movement control unit 21 is used to enable the sampling device 20 to move as required for the sampling process. In one embodiment, the movement control unit 21 is used to cause the image capture unit 22 to complete the movement when sampling the reference object. In one embodiment, the movement control unit 21 may be a display screen on the sampling device 20 or an automatic movement device coupled to the image capture unit 22 .

When the display screen serves as the movement control unit 21, the display screen can be used to provide a movement instruction to the user to instruct the user to move the image capture unit 22 to the sampling position. In the embodiment, the sampling position can be determined by a sampling distance and a sampling direction. For example, when a camera distance between the image capture unit 22 and a certain position on the reference object is equal to the sampling distance, and a camera direction of the image capture unit 22 at the position point on the reference object is equal to In the sampling direction, the display screen shows that the image capturing unit 22 has moved to the sampling position and can start to obtain the required sampling images. When the camera distance is not equal to the sampling distance At this time, the display screen may instruct the user to further move the image capturing unit 22 to extend or shorten the imaging distance. When the imaging direction is not equal to the sampling direction, the display screen can instruct the user to further move the image capturing unit 22 to the left, right, raise or lower the imaging direction. In another embodiment, the sampling position may be determined by the sampling direction. In the embodiment, the sampling distance can be adjusted by adjusting the focal length of the image capturing unit 22 to ensure that detailed surface information of the reference object is obtained.

When the automatic mobile device serves as the mobile control unit 21, the automatic mobile device can be a robotic arm or other device that can move the image capturing unit 22. The automatic mobile device can receive the sampling position instructed by the processor 23 to capture the sampling position. The image capturing unit 22 moves to the sampling position. In another embodiment, the sampling distance can be adjusted by adjusting the focal length of the image capturing unit 22 to ensure that detailed surface information of the reference object is obtained. Therefore, the automatic moving device can only adjust the sampling direction of the moving image capturing unit 22 to obtain the required sampling image.

The image capturing unit 22 is used to acquire multiple sample images. When the sampling device 20 wants to sample the reference object, the image capture unit 22 can move to a plurality of different sampling positions, so that the image capture unit 22 can capture images of the reference object at different sampling positions. to obtain the multiple sample images. The image capturing unit 22 may be a CCD (Charge-Coupled Device) image sensor, a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a camera. In one embodiment, the image capture unit 22 may include a high-magnification image capture lens to obtain detailed surface information of the reference object. In the embodiment, the image capturing unit 22 may include a microscope image capturing lens. In one embodiment, the plurality of sampling images captured by the image capturing unit 22 are all surface microscopic images of the reference object. In this embodiment, the surface microscopic image is a surface texture image.

The processor 23 and the storage 24 are coupled to each other. The memory 24 stores a plurality of instructions for the processor 23 to execute the sampling method of the sampling device 20 according to the plurality of instructions stored in the memory 24 . To implement the sampling method of the present invention, the memory 24 stores a sampling program 240 . In the embodiment, the sampling program 240 further includes a positioning module 241 and a sampling module 242. The positioning module 241 is used to enable the processor 23 to assist the movement control unit 21 to move the image capture unit 22 to the sampling position. The sampling module 242 is used to enable the processor 23 to assist the image capturing unit 22 to obtain the required sampling image at the sampling position.

The transmission unit 25 may utilize a custom protocol or follow existing standards or actual standards, including but not limited to Ethernet, IEEE 802.11 or IEEE 802.15 series, wireless USB or telecommunications standards (including but not limited to GSM, CDMA2000, TD-SCDMA, WiMAX , 3GPP-LTE or TD-LTE), thereby transmitting the sampling characteristics to other devices other than the sampling device 20 .

FIG. 3 is a flow chart of a sampling method 300 for establishing identification data for a reference object and performing sampling according to the present invention. Because there are many ways to perform the sampling method 300, the sampling method 300 shown in Figure 3 is only an example. The sampling method 300 may be performed using the configurations shown in FIGS. 1A, 1B, and 2, and while describing the sampling method 300, please incorporate reference to various elements in FIGS. 1A, 1B, and 2. Each step shown in FIG. 3 may represent one or more processes, methods or subroutines executed, and the order of each step may be adjusted arbitrarily without causing the essence of the sampling method 300 to deviate from the technical solution of the sampling method 300 range.

In step S310, the sampling device 20 obtains the positioning point on the reference object.

In one embodiment, the sampling device 20 can set the positioning point of the reference object by itself. In one embodiment, when the sampling device 20 receives a request to establish the identification data for the reference object, the sampling device 20 can select the positioning point on the reference object by itself. In one embodiment, the image capturing unit 22 of the sampling device 20 can obtain an overall image of the reference object, and the user can select a position on the reference object as the positioning point from the overall image. In another embodiment, the image capturing unit 22 of the sampling device 20 can obtain an overall image of the reference object, and select a position on the reference object as the anchor point randomly or through a preset selection method.

In one embodiment, the sampling device 20 may receive the positioning point for the reference object from a device other than the sampling device 20 . In the embodiment, the sampling device 20 may further include a receiving unit (not shown). The receiving unit may receive data provided to the sampling device 20 from a device other than the sampling device 20 . In one embodiment, the receiving unit can be integrated with the transmitting unit 25 to form a communication unit.

In the embodiment, when the sampling device 20 receives a request to establish the identification data for the reference object, the image capture unit 22 of the sampling device 20 can obtain an overall image of the reference object and transmit it through the transmission unit 25 The entire image is transmitted to the server 10. When the server 10 receives the request to establish the identification data for the reference object and the overall image, the server 10 can select the anchor point from the overall image based on a preset selection method and return the anchor point. to the receiving unit of the sampling device 20. In one embodiment, the server 10 can store the anchor point in the internal storage device 11 in the server 10 . In another embodiment, the server 10 can transmit the anchor point to the online storage device 30 for storage.

In step S320, the sampling device 20 acquires multiple sampling images along multiple sampling directions at the positioning point.

In one embodiment, the sampling device 20 can set the plurality of sampling directions of the positioning point by itself. In the embodiment, when the sampling device 20 starts to capture the sampling image for the positioning point, the sampling device 20 can select the plurality of sampling directions for the positioning point by itself. In one embodiment, the sampling device 20 further includes a positioning unit (not shown), which may include a positioning device such as a gyroscope. In one embodiment, the sampling device 20 can record the location of the sampled image through the positioning unit when the image capturing unit 22 captures the sampled image of the positioning point. corresponding to the sampling direction. In another embodiment, the sampling device 20 can select the plurality of sampling directions in advance based on a preset orientation method, and use the movement control unit 21 to cause the image capture unit 22 to perform the plurality of sampling images in the plurality of sampling directions. of extraction.

In one embodiment, the sampling device 20 may receive the plurality of sampling directions from a device other than the sampling device 20 . In the embodiment, after the sampling device 20 transmits the overall image to the server 10 through the transmission unit 25, the server 10 can set the plurality of sampling directions based on the preset orientation method, and return at the positioning point. When transmitted to the receiving unit of the sampling device 20, the set sampling directions are also transmitted back to the receiving unit. In one embodiment, the server 10 can store the plurality of sampling directions in the internal storage device 11 of the server 10 . In another embodiment, the server 10 can transmit the plurality of sampling directions to the online storage device 30 for storage. In yet another embodiment, the server 10 may not store the plurality of sampling directions in the internal storage device 11 and may not transmit them to the online storage device 30 . In other words, the sampling system does not store the multiple sampling directions.

In one embodiment, the image capturing unit 22 acquires the plurality of sampled images based on the plurality of sampling directions. In the embodiment, the image capture unit 22 can obtain a plurality of first sampling images based on a first sampling direction among the plurality of sampling directions, and can obtain a plurality of first sampling images based on a second sampling direction among the plurality of sampling directions. , obtain multiple second sampling images.

In step S330, the sampling device 20 transmits the sampling features created by the plurality of sampling images for storage by an online device.

In one embodiment, the network device may be the internal storage device 11 or the online storage device 30 in the server 10 . In one embodiment, the sampling device 20 can transmit the sampling features established by the plurality of sampled images to the server 10 through the transmission unit 25 . In one embodiment, the server 10 can store the sampling characteristics in the internal storage device 11 in the server 10 , or the server 10 can transmit the sampling characteristics to the online storage device 30 for storage. In another embodiment, although However, the sampling device 20 also transmits the sampling features created by the plurality of sampled images to the server 10 through the transmission unit 25. However, the server 10 obtains a verification feature through a preset image processing method and stores the verification feature in the server. The internal storage device 11 in the server 10, or the server 10 can transmit the verification characteristics to the online storage device 30 for storage. In another embodiment, the sampling device 20 can directly transmit the sampling features established by the plurality of sampling images to the online storage device 30 through the transmission unit 25 .

In one implementation, the sampling feature may be a sampling set of the plurality of sampled images. In other words, all of the multiple sampling images, the multiple sampling directions, and the sampling correspondence between them are the sampling features. In one embodiment, when the server 10 receives the plurality of sampling images, the plurality of sampling directions and the sampling correspondence, the server 10 can obtain the verification feature according to the preset image processing method and perform the verification. The verification features are stored in the internal storage device 11 or the online storage device 30 . In another embodiment, after the server 10 receives the plurality of sampling images, the plurality of sampling directions and the sampling correspondence, the server 10 directly converts the plurality of sampling images, the plurality of sampling directions and the sampling The corresponding relationship is stored in the internal storage device 11 or the online storage device 30, and the multiple sampling images, the multiple sampling directions, and the sampling corresponding relationship are directly used as subsequent verification features.

In one embodiment, the sampling feature may be the verification feature generated based on the plurality of sampling images, the plurality of sampling directions and the sampling correspondence. In other words, the processor 23 of the sampling device 20 can obtain the verification feature by itself based on the preset image processing method. In one embodiment, the sampling device 20 can transmit the verification feature to the server 10 through the transmitting unit 25 . In one embodiment, the server 10 can store the verification feature in the internal storage device 11 in the server 10, or the server 10 can transmit the verification feature to the online storage device 30 for storage. In another embodiment, the sampling device 20 can directly transmit the verification characteristics to the online storage device 30 for storage through the transmission unit 25 .

In one embodiment, if the anchor point is set by the sampling device 20, when the sampling device 20 transmits the sampling characteristics to the server 10 or the online storage device 30, the sampling device 20 can also transmit the anchor point to the server 10 or the online storage device 30. The server 10 or the online storage device 30 is used for storage.

In one embodiment, the sampling device 20 also transmits the object information of the reference object, and the object information is stored in the online storage device 30 or the internal storage device 11, so that when an object to be detected is subsequently detected, the server 10 can The object information is compared with the information of the object to be detected to determine whether the server 10 should retrieve the positioning point and the verification feature of the reference object as identification information for detecting the object to be detected.

In one embodiment, since the benchmark will change slightly over time, if a long period of time (for example: 10 or 20 years) passes, the benchmark will be tested again in the same way. During the second sampling, the secondary sampling result will be different from the sampling characteristics or the verification characteristics stored in the server 10 or the online storage device 30, causing the reference object to be identified as a fake. Therefore, the sampling device 20 can simultaneously send a change information to the server 10 when sending the sampling characteristics to the server 10 . In the implementation, the change information can be the material information or object information of the reference object, and the server 10 can search for a deterioration information of the reference object based on the material information and object information for subsequent sampling features. When used to detect an object to be detected, the possible deterioration of the reference object can also be considered. In the embodiment, the server 10 can store the degradation information in the internal storage device 11 or the online storage device 30 . In another embodiment, the server 10 can directly store the change information in the internal storage device 11 or the online storage device 30 for subsequent detection of the object to be detected, and then search for the degradation based on the material information and object information. information. In yet another embodiment, the change information may be the degradation information of the reference object. In the embodiment, the sampling device 20 can search for the deterioration information of the reference object based on the material information or the object information of the reference object, and transmit the deterioration information to the server 10 or directly to an online storage device. 30. In the described embodiment, when the server 10 receives the bad When degraded information, the server 10 can store the degraded information in the internal storage device 11 or the online storage device 30 .

The sampling method 300 of the present invention may at least include but is not limited to all the following embodiments: In a first embodiment of the sampling method 300 of the present invention, the set of the plurality of sampling images is directly stored in the internal storage as the verification feature. device 11 or online storage device 30, and the positioning point and the plurality of sampling directions are determined by the sampling device 20. In the embodiment, the sampling device 20 first sets the positioning point and the plurality of sampling directions, obtains the plurality of sampling images based on the positioning point and the plurality of sampling directions, and converts the plurality of sampling images into The set is used as a sampling feature and is then transmitted to the server 10 or directly to the online storage device 30 for storage together with the positioning point, the plurality of sampling directions, and the sampling correspondence between the plurality of sampling images and the plurality of sampling directions. In the embodiment, when the server 10 receives the plurality of sampling images, the positioning points, the plurality of sampling directions and the sampling correspondence, the server 10 can convert the plurality of sampling images, the positioning points, The multiple sampling directions and the sampling correspondence are stored in the internal storage device 11 or the online storage device 30 . In the embodiment, the data transmitted by the sampling device 20 further includes the change information, and the data stored in the internal storage device 11 or the online storage device 30 may further include the material information, the object information or the deterioration information.

In a second embodiment of the sampling method 300 of the present invention, the set of the plurality of sampling images is directly stored in the internal storage device 11 or the online storage device 30 as the verification feature, and the positioning point or the plurality of sampling directions One is determined by the sampling device 20 and the other is determined by the server 10 . In one embodiment, the plurality of sampling directions are determined by the sampling device 20 , and the positioning point is determined by the server 10 . Therefore, when the sampling device 20 receives the request to establish the identification data for the reference object, the sampling device 20 can obtain the overall image for the reference object and send it to the server 10, and the server 10 can based on the preset selection method, The positioning point is selected from the overall image and provided to the sampling device 20 . At the same time, the sampling device 20 can also select itself based on the preset orientation method. The multiple sampling directions. In another embodiment, the positioning point is determined by the sampling device 20 , and the multiple sampling directions are determined by the server 10 . Therefore, when the sampling device 20 receives the request to establish the identification data for the reference object, the sampling device 20 can obtain the overall image for the reference object, and can select the position from the overall image based on the preset selection method. point. At the same time, the sampling device 20 transmits the sampling request to the server 10, so that the server 10 selects the plurality of sampling directions based on the preset orientation method and provides them to the sampling device 20. In one embodiment, after obtaining the positioning point and the plurality of sampling directions, the sampling device 20 further obtains the plurality of sampling images, and uses the set of the plurality of sampling images as the sampling feature, together with the positioning point and the plurality of sampling directions. One of the plurality of sampling directions and the sampling correspondence are sent to the server 10 or directly to the online storage device 30 for storage. In the embodiment, when the server 10 receives the plurality of sampling images, the server 10 can store the plurality of sampling images, the positioning points, the plurality of sampling directions and the sampling correspondence in an internal storage device. 11 or online storage device 30. In the embodiment, when the online storage device 30 receives the plurality of sampling images directly from the sampling device 20, the online storage device 30 can obtain the positioning that the online storage device 30 has not received from the sampling device 20 from the server 10. point and one of the multiple sampling directions. In the embodiment, if the anchor point is determined by the server 10, the sampling device 20 does not need to additionally transmit the anchor point. If the multiple sampling directions are determined by the server 10, the sampling device 20 does not need to additionally transmit the multiple sampling directions, but only needs to transmit the sampling correspondence. In the embodiment, the data transmitted by the sampling device 20 further includes the change information, and the data stored in the internal storage device 11 or the online storage device 30 may further include the material information, the object information or the deterioration information.

In a third embodiment of the sampling method 300 of the present invention, the set of the plurality of sampling images is directly stored in the internal storage device 11 or the online storage device 30 as the verification feature, and the positioning point and the plurality of sampling directions are All are decided by the server 10. In the embodiment, when the sampling device 20 receives a request to establish the identification data for the reference object, the sampling device 20 20 The overall image can be obtained for the reference object to the server 10, and the server 10 can select the positioning point from the overall image based on the preset selection method and orientation method and additionally determine the plurality of sampling directions to provide Give sampling device 20. The sampling device 20 obtains the plurality of sampling images based on the received positioning point and the plurality of sampling directions, uses the set of the plurality of sampling images as sampling features, and then transmits the sampling correspondence to the server 10 or Directly transmitted to the online storage device 30 for storage. In the embodiment, when the server 10 receives the plurality of sampling images and the sampling correspondence, the server 10 can obtain the plurality of sampling images, the positioning points, the plurality of sampling directions and the sampling correspondence. Stored in the internal storage device 11 or the online storage device 30. In the embodiment, when the online storage device 30 receives the multiple sampling images and the sampling correspondence directly from the sampling device 20 , the online storage device 30 can obtain the positioning point and the multiple sampling directions from the server 10 . In the embodiment, the data transmitted by the sampling device 20 further includes the change information, and the data stored in the internal storage device 11 or the online storage device 30 may further include the material information, the object information or the deterioration information.

In a fourth embodiment of the sampling method 300 of the present invention, the plurality of sampled images generate the verification features through a preset image processing method and then are stored in the internal storage device 11 or the online storage device 30, and the anchor point and the Multiple sampling directions are determined by the sampling device 20 . In the embodiment, the sampling device 20 first sets the positioning point and the plurality of sampling directions by itself, and obtains the plurality of sampling images based on the positioning point and the plurality of sampling directions. In one embodiment, the sampling device 20 generates the verification feature for the anchor point through a preset image processing method based on the plurality of sampling images, the plurality of sampling directions and the sampling correspondence, and the sampling device 20 generates the verification feature. The verification feature is used as the sampling feature and is transmitted to the server 10 together with the positioning point or directly to the online storage device 30 for storage. In the embodiment, when the server 10 receives the verification feature and the anchor point, the server 10 can store the verification feature and the anchor point in the internal storage device 11 or the online storage device 30 . In another embodiment, the sampling device 20 directly The anchor point, the plurality of sampling directions, the plurality of sampling images and the sampling correspondence are sent to the server 10. The server 10 uses the preset settings based on the plurality of sampling images, the plurality of sampling directions and the sampling correspondence. The image processing method generates the verification feature for the anchor point, and stores it together with the anchor point in the internal storage device 11 or the online storage device 30 . In the embodiment, the data transmitted by the sampling device 20 further includes the change information, and the data stored in the internal storage device 11 or the online storage device 30 may further include the material information, the object information or the deterioration information.

In a fifth embodiment of the sampling method 300 of the present invention, after the plurality of sampled images generate the verification features through a preset image processing method, they are stored in the internal storage device 11 or the online storage device 30, and the anchor point or The plurality of sampling directions are determined by the sampling device 20 , and the other one is determined by the server 10 . The fifth embodiment is based on the same method as the aforementioned second embodiment. The sampling device 20 and the server 10 each generate the positioning point according to the preset selection method and the overall image of the reference object or according to the preset orientation method. the plurality of sampling directions, and obtain the plurality of sampling images accordingly. In one embodiment, the sampling device 20 generates the verification feature for the anchor point through a preset image processing method based on the plurality of sampling images, the plurality of sampling directions and the sampling correspondence, and the sampling device 20 generates the verification feature. The verification feature is used as the sampling feature and is sent to the server 10 or directly to the online storage device 30 for storage. In the embodiment, if the anchor point is determined by the server 10, the sampling device 20 does not need to additionally transmit the anchor point. If the anchor point is determined by the sampling device 20, the sampling device 20 can additionally transmit the anchor point to the server 10 or directly transmit it to the online storage device 30 for storage. In the embodiment, when the server 10 receives the verification feature, the server 10 can store the verification feature and the anchor point in the internal storage device 11 or the online storage device 30 . In another embodiment, the sampling device 20 directly transmits the plurality of sampling images and the sampling correspondence to the server 10. The server 10 based on the plurality of sampling images, the plurality of sampling directions and the sampling correspondence, through preset images The processing method generates the verification feature for the anchor point and stores it together with the anchor point in the internal storage device 11 or the online storage device 30 . In the embodiment, if the plurality of sampling directions are determined by the sampling device 20, the sampling device 20 may additionally transmit the plurality of sampling directions to the server 10. If the anchor point is determined by the sampling device 20, the sampling device 20 can additionally transmit the anchor point to the server 10 or directly transmit it to the online storage device 30 for storage. In the embodiment, the data transmitted by the sampling device 20 further includes the change information, and the data stored in the internal storage device 11 or the online storage device 30 may further include the material information, the object information or the deterioration information.

In a sixth embodiment of the sampling method 300 of the present invention, after the plurality of sampled images generate the verification features through a preset image processing method, they are stored in the internal storage device 11 or the online storage device 30, and the anchor point and The plurality of sampling directions are determined by the server 10 . The sixth embodiment is based on the same method as the aforementioned third embodiment. The server 10 generates the positioning point based on the preset selection method and the overall image of the reference object received from the sampling device 20, and based on the preset Orientation method is used to generate the plurality of sampling directions, and then the positioning point and the plurality of sampling directions are provided to the sampling device 20 . In one embodiment, the sampling device 20 generates the verification feature for the anchor point through a preset image processing method based on the plurality of sampling images, the plurality of sampling directions and the sampling correspondence, and the sampling device 20 generates the verification feature. The verification feature is used as the sampling feature and is sent to the server 10 or directly to the online storage device 30 for storage. In the embodiment, since the anchor point is determined by the server 10, the sampling device 20 does not need to additionally transmit the anchor point. In the embodiment, when the server 10 receives the verification feature, the server 10 can store the verification feature and the anchor point in the internal storage device 11 or the online storage device 30 . In another embodiment, the sampling device 20 directly transmits the plurality of sampling images and the sampling correspondence to the server 10. The server 10 based on the plurality of sampling images, the plurality of sampling directions and the sampling correspondence, The preset image processing method is used to generate the image for the anchor point. Verify the feature and store it together with the anchor point in the internal storage device 11 or the online storage device 30 . In the embodiment, the data transmitted by the sampling device 20 further includes the change information, and the data stored in the internal storage device 11 or the online storage device 30 may further include the material information, the object information or the deterioration information.

In the embodiment, the preset selection method may be a random selection method, allowing the sampling device 20 or the server 10 to arbitrarily select the anchor point from the overall image of the reference object. In the embodiment, the preset selection method may be through a surface analysis technology, allowing the sampling device 20 or the server 10 to select the anchor point from the overall image of the reference object. The surface analysis technology can be an image analysis technology such as image complexity analysis to obtain a high-complexity area in the overall image as a certain position. In the implementation, the preset selection method includes but is not limited to the above-mentioned selection method. Any method that can be used to select a specific location of the reference object can be used in the sampling method 300 described in this case.

In the embodiment, the preset orientation mode may be a random orientation mode, allowing the sampling device 20 or the server 10 to arbitrarily select the plurality of sampling directions. In the embodiment, if the sampling device 20 or the server 10 obtains the anchor point in the overall image in advance, the plurality of sampling directions can be selected based on the anchor point through a surface analysis technology. The surface analysis technology can set more sampling directions for the parts with higher color changes around the anchor point based on the gradient of the pixel value change, so as to obtain more complete sampling features around the anchor point. In the embodiment, the preset orientation includes but is not limited to the above-mentioned orientation. Any method that can be used to select multiple different sampling directions can be used in the sampling method 300 described in this case.

In the embodiment, the preset image processing method may be three-dimensional modeling processing. In the embodiment, the sampling device 20 or the server 10 can be based on the plurality of sampling images, the plurality of sampling directions, and the sampling correspondence between the plurality of sampling images and the plurality of sampling directions. relationship, using machine learning technology to generate the sampling model for the anchor point. The sampling model may be a three-dimensional sampling model.

In the embodiment, the sampling device 20 can select multiple positioning points for the reference object, and obtain multiple sampling images with multiple sampling directions for each positioning point, thereby obtaining different positioning points for the reference object. different sampling characteristics. In one embodiment, the multiple sampling directions of each positioning point may be completely different. In another embodiment, each anchor point can use the same set of sampling combinations, and the sampling combination has multiple sampling directions, so the multiple sampling directions between each anchor point are exactly the same. In yet another embodiment, the plurality of sampling directions of each positioning point may be partly the same and partly different.

Please refer to FIG. 4A. FIG. 4A is a block diagram of a detection system 401 for detecting an object to be detected according to the present invention. In one embodiment, the detection system 401 includes a server 10 and a detection device 40 . The server 10 may include an internal storage device 11 to store the sampling characteristics obtained by the sampling device 20 of FIG. 2 in advance. In one embodiment, when the detection device 40 receives a detection request, the detection device 40 can be coupled with the server 10 to complete the detection method of the present invention. After the detection system 401 completes the detection method, the detection device 40 can stop coupling with the server 10 .

Please refer to FIG. 4B. FIG. 4B is a block diagram of another detection system 402 for detecting an object to be detected according to the present invention. In one embodiment, the detection system 402 includes a server 10 , a detection device 40 and an online storage device 30 . In one embodiment, when the detection device 40 receives a detection request, the detection device 40 can be coupled to the server 10, and the server 10 can be further coupled to the online storage device 30 to complete the detection of the present invention. method. After the detection system 402 completes the detection method, the detection device 40 can be disconnected from the server 10 , and the server 10 can also be disconnected from the online storage device 30 . In another embodiment, when the detection device 40 receives a detection request, the detection device 40 can be coupled with the server 10 and the online storage device 30 to complete the process of the present invention. detection method. After the detection system 402 completes the detection method, the detection device 40 can stop coupling with the server 10 and the online storage device 30 .

In the embodiment, the online storage device 30 may be a network data storage or a blockchain storage device. When the online storage device 30 is a blockchain storage device, the possibility of the previously stored sampling characteristics being tampered with or replaced can be reduced through the characteristics of the blockchain. In the above embodiment, the online storage device 30 can store records of all transactions of the benchmark, inspection time and results, and updated pictures.

Please refer to FIG. 5 , which is a block diagram of a detection device 40 for detecting an object to be detected according to the present invention. The detection device 40 may be a mobile phone, a tablet computer, a desktop computer, a notebook computer, a camera, a video recorder or other electronic equipment, which is not limited here. The detection device 40 includes a movement control unit 41, an image capturing unit 42, a processor 43, a storage 44, a transmitting unit 45 and a receiving unit 46.

The movement control unit 41 is used to enable the detection device 40 to move as required by the detection process. In one embodiment, the movement control unit 41 is used to cause the image capture unit 42 to complete the movement when detecting the object to be detected. In one embodiment, the movement control unit 41 may be a display screen on the detection device 40 or an automatic movement device coupled to the image capture unit 42 .

When the display screen serves as the movement control unit 41, the display screen can be used to provide a movement instruction to the user to instruct the user to move the image capture unit 42 to the detection position. In the embodiment, the detection position can be determined by a detection distance and a detection direction. For example, when a camera distance between the image capture unit 42 and a certain point on the object to be detected is equal to the detection distance, and the image capture unit 42 takes a picture of the position point on the object to be detected. When the direction is equal to the detection direction, the display screen shows that the image capture unit 42 has moved to the detection position and can start to obtain the required detection images. When the imaging distance is not equal to the detection distance, the display screen can instruct the user to further move the image capturing unit 42 to zoom out or Close the camera distance. When the imaging direction is not equal to the detection direction, the display screen may instruct the user to further move the image capturing unit 42 to the left, right, raise or lower the imaging direction. In another embodiment, the detection position may be determined by the detection direction. In the embodiment, the detection distance can be adjusted by adjusting the focal length of the image capture unit 42 to ensure that detailed surface information of the object to be detected is obtained.

When the automatic mobile device serves as the mobile control unit 41, the automatic mobile device can be a robotic arm or other device that can move the image capturing unit 42. The automatic mobile device can receive the detection position instructed by the processor 43 to capture the detection position. The image capturing unit 42 moves to the detection position. In another embodiment, the detection distance can be adjusted by adjusting the focal length of the image capture unit 42 to ensure that detailed surface information of the object to be detected is obtained. Therefore, the automatic mobile device can only adjust the detection direction of the mobile image capturing unit 42 to obtain the required detection image.

The image capturing unit 42 is used to acquire multiple detection images. When the detection device 40 is to detect the object to be detected, the image capture unit 42 can move to a plurality of different detection positions, so that the image capture unit 42 can capture images of the object to be detected at different detection positions. to obtain the multiple detection images. The image capturing unit 42 may be a CCD (Charge-Coupled Device) image sensor, a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a camera. In one embodiment, the image capture unit 42 may include a high-magnification image capture lens to obtain detailed surface information of the object to be detected. In the embodiment, the image capture unit 42 may include a microscope image capture lens. In one embodiment, the plurality of detection images captured by the image capture unit 42 are all surface microscopic images of the object to be detected. In this embodiment, the surface microscopic image is a surface texture image.

The processor 43 and the storage 44 are coupled to each other. The memory 44 stores a plurality of instructions for the processor 43 to execute the detection method of the detection device 40 according to the plurality of instructions stored in the memory 44 . Law. In order to complete the detection method of the present invention, the storage 44 stores a detection program 440. In the embodiment, the detection program 440 further includes a positioning module 441 and a detection module 442. The positioning module 441 is used to enable the processor 43 to assist the movement control unit 41 to move the image capture unit 42 to the detection position. The detection module 442 is used to enable the processor 43 to assist the image capture unit 42 to obtain the required detection image at the detection position.

The transmitting unit 45 and the receiving unit 46 may utilize customized protocols or follow existing standards or actual standards, including but not limited to Ethernet, IEEE 802.11 or IEEE 802.15 series, wireless USB or telecommunications standards (including but not limited to GSM, CDMA2000, TD -SCDMA, WiMAX, 3GPP-LTE or TD-LTE), thereby transmitting the detection characteristics to other devices other than the detection device 40, and thereby receiving sampling characteristics transmitted from other devices other than the detection device 40.

Figure 6 is a flow chart of a detection method 600 for detecting an object to be detected provided by the present invention. The detection method 600 shown in Figure 3 is only an example because there are many ways to perform the detection method. The detection method 600 may be performed using the configurations shown in FIGS. 4A, 4B, and 5, and while describing the detection method 600, please refer to the various elements in FIGS. 4A, 4B, and 5. Each step shown in Figure 6 may represent one or more processes, methods or subroutines executed, and the order of each step may be adjusted arbitrarily, without causing the essence of the detection method 600 to deviate from the technical solution of the detection method 600 range.

In step S610, the detection device 40 transmits a request for detecting the positioning point of the object to be detected.

In one embodiment, before capturing the detection image, the detection device 40 needs to know which block of the object to be detected should be used to detect the image, so that it can be compared with the information stored in the online storage device 30 or the internal storage device 11 Verification characteristics are compared, so the detection device 40 can first send a request to detect the location point of the object to be detected, in order to obtain the location of the detection object in the store. site. In the embodiment, the detection device 40 may send the request to the server 10, and the request may include object information of the object to be detected. Therefore, the server 10 can use the object information of the object to be detected to confirm which reference object's corresponding positioning point and verification characteristics are to be retrieved as identification data for the object to be detected. In the embodiment, the corresponding positioning point of the reference object is the positioning point of the object to be detected.

In one embodiment, when the corresponding positioning point of the reference object corresponding to the object to be detected and the verification feature are stored in the internal storage device 11 , the server 10 transmits the corresponding positioning point of the reference object to the detection device 40 . In another embodiment, when the corresponding positioning point of the reference object corresponding to the object to be detected and the verification feature are stored in the online storage device 30, the server 10 will first send a request for the positioning point of the object to be detected. The request is sent to the online storage device 30 for the online storage device 30 to confirm which reference object's positioning point and verification characteristics are to be retrieved as the identification data required for the detection of the object to be detected, and then the online storage device 30 returns the positioning point. And the verification feature is sent to the server 10, and then the server 10 sends the positioning point to the detection device 40. In the above embodiment, the online storage device 30 will also transmit the change information of the reference object to the server 10 .

In step S620, the detection device 40 receives information having the positioning point of the object to be detected.

In one embodiment, the server 10 transmits the positioning point of the object to be detected to the detection device 40 for subsequent image capture by the detection device 40 . In one embodiment, if the verification features obtained by the server 10 are multiple sampling images of the corresponding positioning points of the reference object, the information transmitted by the server 10 will also provide samples of each of the multiple sampling images. direction, so that the detection device 40 can obtain detection images in the same detection direction.

In one embodiment, if the detection device 40 can complete the comparison of the plurality of detection images described below with the verification features by itself, the server 10 can simultaneously transmit the verification features of the reference object to the detection device 40 . In the described embodiment, the server 10 will also transmit the change of the reference object. information to the detection device 40. In another embodiment, if the comparison is completed by the server 10, the server 10 may not transmit the verification feature of the reference object to the detection device 40, but directly retain it in the server 10 for subsequent comparison. .

In step S630, the detection device 40 acquires multiple detection images along multiple detection directions at the positioning point of the object to be detected.

In one embodiment, the detection device 40 can set the plurality of detection directions of the positioning point by itself. In the embodiment, when the detection device 40 starts to capture the detection image for the positioning point, the detection device 40 can select the multiple detection directions for the positioning point by itself. In one embodiment, the detection device 40 further includes a positioning unit (not shown), which may include a positioning device such as a gyroscope. In one embodiment, the detection device 40 can record the detection direction corresponding to the detection image through the positioning unit when the image capture unit 42 captures the detection image of the positioning point. In another embodiment, the detection device 40 can select the multiple detection directions in advance based on a preset orientation method, and use the movement control unit 41 to make the image capture unit 42 reach the multiple detection directions to perform the detection image. Retrieve.

In one embodiment, the detection device 40 may receive the multiple detection directions from a device other than the detection device 40 . In the embodiment, the detection device 40 can obtain the multiple detection directions through the receiving unit 46 . In one embodiment, if the internal storage device 11 and the online storage device 30 do not store the multiple sampling directions of the corresponding positioning points of the reference object, the server 10 can select the multiple sampling directions in advance based on the preset orientation method. detect the direction and transmit it to the receiving unit 46. In another embodiment, if the internal storage device 11 or the online storage device 30 stores the plurality of sampling directions of the corresponding positioning point of the reference object, the plurality of sampling directions can be re-sent to the detection device 40 as the detection device 40 . The multiple detection directions of the positioning point of the object to be detected. In one embodiment, if the plurality of sampling directions are stored in the internal storage device 11, the server 10 can transmit the plurality of sampling directions to the receiving unit 46 as the plurality of detection directions. In another embodiment, if the When multiple sampling directions are stored in the online storage device 30, the online storage device 30 can directly transmit the multiple sampling directions to the receiving unit 46 as the multiple detection directions, or indirectly transmit the multiple sampling directions to the receiving unit 46 through the server 10. The receiving unit 46 serves as the plurality of detection directions.

In one embodiment, the image capturing unit 42 acquires the plurality of detection images based on the plurality of detection directions. In the embodiment, the image capturing unit 42 can obtain a plurality of first detection images based on a first detection direction among the plurality of detection directions, and can obtain a plurality of first detection images based on a second detection direction among the plurality of detection directions. , obtain multiple second detection images.

In step S640, the detection device 40 obtains detection results based on the plurality of detection images.

In one embodiment, the detection result is generated based on a comparison of the plurality of detection images and a reference object corresponding to the object to be detected. In one embodiment, the detection device 40 can compare the plurality of detection images with the verification features of the reference object by itself to obtain the detection result. In another embodiment, the detection device 40 can generate detection features based on the plurality of detection images, and transmit the detection features to the server 10 for the server 10 to compare the detection features with the verification features. Finally, The server 10 then transmits the detection result to the detection device 40 .

In one embodiment, when the detection result is generated by the detection device 40 itself, the detection device 40 compares the multiple detection images with the received verification feature. In one embodiment, the verification feature may be a sampling model of the corresponding positioning point of the reference object. The sampling model may be a three-dimensional sampling model. In an embodiment, the detection device 40 may generate the detection feature based on the multiple detection images, the multiple detection directions, and a detection correspondence between the multiple detection images and the multiple detection directions. In other words, the processor 43 of the detection device 40 can obtain the detection features by itself based on the preset image processing method. In the embodiment, the detection feature is a detection model of the positioning point of the object to be detected. The detection model may be a three-dimensional detection model. Therefore, the detection device 40 can directly compare the similarity between the three-dimensional sampling model and the three-dimensional detection model, so as to produce this test result. In another embodiment, the detection device 40 can compare with the three-dimensional sampling model based on the multiple detection images, the multiple detection directions and the detection correspondence. In the embodiment, the detection device 40 can infer multiple verification images through the three-dimensional sampling model through the multiple detection directions, and then compare the multiple verification images with the multiple verification images one by one based on the detection correspondence. Detect the similarity of images to produce detection results. In one embodiment, the verification feature may be the plurality of sampling images, the plurality of sampling directions and the sampling correspondence of the corresponding positioning point of the reference object. In the embodiment, the plurality of sampling directions can be exactly the same as the plurality of detection directions. Therefore, the detection device 40 can compare the plurality of sampling images with the plurality of sampling images one by one according to the sampling corresponding relationship and the detection corresponding relationship. Detect similarity of influences to produce detection results.

In one embodiment, when the detection result is generated by the server 10, the detection device 40 will transmit the detection feature to the server 10. In one embodiment, the transmitted detection feature may be the three-dimensional sampling model or a combination of the multiple detection images, the multiple detection directions, and the detection correspondence. In one embodiment, the detection device 40 may generate the three-dimensional detection model based on the multiple detection images, the multiple detection directions, and the detection correspondence. In other words, the processor 43 of the detection device 40 can obtain the three-dimensional detection model by itself based on the preset image processing method. Therefore, the detection device 40 can directly transmit the three-dimensional detection model to the server 10, and the server 10 compares the similarity between the three-dimensional sampling model and the three-dimensional detection model to provide the detection result to the detection device 40.

In another embodiment, the detection device 40 may transmit a combination of the plurality of detection images, the plurality of detection directions and the detection correspondence to the server 10 . In one embodiment, the server 10 can generate the three-dimensional detection model based on the multiple detection images, the multiple detection directions, and the detection correspondence. In other words, the server 10 can obtain the three-dimensional detection model based on a preset image processing method. In the described embodiment, the server 10 can directly compare the three-dimensional samples model and the similarity of the three-dimensional detection model to provide the detection result to the detection device 40 . In another embodiment, the server 10 can compare with the three-dimensional sampling model based on the plurality of detection images, the plurality of detection directions and the detection correspondence. In the embodiment, the server 10 can infer a plurality of verification images through the three-dimensional sampling model through the plurality of detection directions, and then compare the plurality of verification images with the plurality of verification images one by one according to the detection correspondence. The similarity of the images is detected to provide the detection result to the detection device 40 . In yet another embodiment, the verification feature may be the plurality of sampling images, the plurality of sampling directions and the sampling correspondence of the corresponding positioning point of the reference object. In the embodiment, the plurality of sampling directions can be exactly the same as the plurality of detection directions. Therefore, the server 10 can compare the plurality of sampling images with the plurality of sampling images one by one according to the sampling correspondence and the detection correspondence. The similarity of the influence is detected to provide the detection result to the detection device 40 . In the embodiment, the plurality of detection directions are the plurality of sampling directions obtained from the online storage device 30 or the internal storage device 11 .

In one embodiment, if the detection result shows that the similarity between the reference object and the object to be detected is high, the detection result obtained by the detection device 40 can determine that the object to be detected is the reference object. If the detection result shows that the similarity between the reference object and the object to be detected is low, the detection result obtained by the detection device 40 can determine that the object to be detected is different from the reference object. In another embodiment, if the detection result shows that the similarity between the reference object and the object to be detected is low and the detection result determines that the object to be detected is different from the reference object, the detection device 40 or the server 10 can The detection result is updated through the change information of the reference object. In the embodiment, the detection device 40 or the server 10 can adjust the verification feature based on the change information of the reference object, and update the detection result based on the adjustment feature and the comparison of the multiple detection images.

In one implementation, the change information may be the material information, the object information or the deterioration information of the reference object. If the change information is the material information or the object information, the detection device 40 or the server 10 can use the network or internal data based on the material information or the object information. Search the database for the degradation information of the reference object. The detection device 40 or the server 10 can estimate the possible degree of deterioration of the reference object through the degradation information and the time difference between the detection time point and the sampling time point. Therefore, the detection device 40 or the server 10 can obtain the adjustment feature based on the verification feature and the degree of degradation.

In one implementation, the degradation information may be material aging information, and the material aging information may be related to color changes (eg, fading). If the deterioration information is material aging information, the actual material aging degree can be evaluated through the material aging information and the time difference. For example, the likely degree of fading can be estimated. In another embodiment, the degradation information may be material condition information, which may be related to material decomposition or damage. If the deterioration information is the material condition information, the actual material damage degree can be evaluated through the material condition information and the time difference. For example: the possible crack size or number of cracks can be estimated.

In one embodiment, if the updated detection result shows that the similarity between the reference object and the object to be detected is high, the detection result obtained by the detection device 40 can determine that the object to be detected is the reference object. In the embodiment, the detection device 40 or the server 10 can store the detection features generated by the plurality of detection images to the internal storage device 11 or the online storage device 30 . In one implementation, the detection feature can directly replace the verification feature as the basis for subsequent detection. If the change information is relied on for a long time to predict the change of the benchmark object, as long as the actual change condition of the benchmark object is too different from the predicted change condition, it will be difficult to correctly identify the object to be detected in the future. Therefore, if the updated detection result shows that the similarity between the reference object and the object to be detected is high, it means that the detection feature can show the actual change status of the reference object as the object to be detected at the moment of detection. The detection device 40 or the server 10 can transmit and store the detection characteristics. In this way, the actual change status of the reference object can be appropriately tracked to avoid the actual change status exceeding the expected change status, and the verification characteristics can be maintained at any time or The correctness of this detection feature in subsequent inspections.

In another embodiment, if the updated detection result shows that the similarity between the reference object and the object to be detected is high, the detection device 40 or the server 10 can combine the detection features generated by the multiple detection images with The verification characteristics are stored together. In other words, the online storage device 30 or the internal storage device 11 will have the characteristic information of the reference object at two different times. Therefore, if a new substance to be detected will be compared with the detection characteristics and the verification characteristics after a period of time (for example: 1 year later), in addition to whether the new substance to be detected is similar to the detection characteristics and the verification characteristics, In addition, it can also be further detected whether the degree of deterioration of the new object to be detected relative to the verification feature is greater than the degree of deterioration of the detection feature. If the degree of deterioration of the new object to be detected is smaller than the degree of deterioration of the detection feature, even if the new object to be detected is similar to the detection feature and the verification feature, the detection system can still issue a warning for the new object to be detected. In this way, the detection accuracy can be further improved by making the degree of deterioration irreversible.

The detection method 600 of the present invention may at least include, but is not limited to, all the following embodiments: In a first embodiment of the detection method 600 of the present invention, the comparison of the plurality of detection images and the verification features is performed by the detection device 40, And the verification features include the plurality of sampling images of the corresponding positioning points of the reference object corresponding to the object to be detected, the plurality of sampling directions, and the sampling correspondence between the plurality of sampling images and the plurality of sampling directions. . In one embodiment, the detection device 40 transmits a request to detect the object to be detected. After receiving the request, the server 10 obtains the corresponding positioning point and the verification feature of the reference object corresponding to the object to be detected from the internal storage device 11 or the online storage device 30, and stores the corresponding positioning point and the verification feature. The multiple sampling directions are sent to the detection device 40 . In one embodiment, the server 10 may simultaneously send the plurality of sampling images and the sampling correspondence to the detection device 40 at this time.

In one embodiment, after receiving the corresponding positioning point and the plurality of sampling directions, the detection device 40 directly sets the corresponding positioning point and the plurality of sampling directions respectively as the positioning point and the plurality of detection objects for the object to be detected. direction, and thereby obtain the multiple detection images. implemented in a In this method, if the detection device 40 has obtained the plurality of sampling images before obtaining the plurality of detection images, the comparison can be started directly. In another embodiment, if the detection device 40 has not obtained the plurality of sampling images before obtaining the plurality of detection images, the detection device 40 can send a request to compare the reference object to the server 10 again, and the server 10 After receiving the request, the corresponding relationship between the multiple sample images and the samples is provided to the detection device 40 . The server 10 can use this method of sending the request twice to prevent the user from sending the first request at will just to defraud all the verification information. In the embodiment, the request sent again by the detection device 40 may include the multiple detection images for the server 10 to perform a preliminary verification. If the server 10 believes that the multiple detection images are obviously completely unrelated to the sampling image, the server 10 The processor 10 may refuse to provide the plurality of sampled images. If the server 10 believes that there is a slight correlation between the multiple detection images and the multiple sampling images, the server 10 can send the multiple sampling images for comparison by the detection device 40 .

In one embodiment, the detection device 40 compares the plurality of sampling images and the plurality of detection images through the sampling correspondence and the detection correspondence. If the similarity between the plurality of sampling images and the plurality of detection images is When it is high, the detection device 40 can determine that the object to be detected is the reference object, and transmit the detection result to the server 10 . If the similarity between the plurality of sampling images and the plurality of detection images is low, the detection device 40 may determine that the object to be detected is not the reference object, and transmit the detection result to the server 10 . In another embodiment, if the similarity between the plurality of sampling images and the plurality of detection images is low, the detection device 40 may send a request for the change information of the reference object to the server 10 . In the embodiment, the server 10 also performs another preliminary verification through the request for the change information (for example, requesting the complete detection images) to confirm whether the detection device 40 needs the change information. In one embodiment, the detection device 40 adjusts the plurality of sampled images according to the change information to generate a plurality of adjusted images as part of the adjustment feature, and then compares the plurality of sampled images through the sampling correspondence and the detection correspondence. A plurality of adjustment images and the plurality of detection images. If the similarity between the multiple adjustment images and the multiple detection images When the degree is low, the detection device 40 can determine that the object to be detected is not the reference object, and transmit the detection result to the server 10 . If the similarity between the plurality of adjusted images and the plurality of detection images is high, the detection device 40 can update the original detection results that are different, change the detection result to determine that the object to be detected is the reference object, and transmit the detection result. Result to server 10. In the embodiment, the detection device 40 can upload the plurality of detection images to the server 10 , so that the server 10 can store the plurality of detection images in the internal storage device 11 or the online storage device 30 . In one embodiment, the plurality of detection images and the plurality of sampling images may be simultaneously stored in the internal storage device 11 or the online storage device 30 corresponding to the reference object, so as to jointly serve as the verification feature of the reference object. In another embodiment, the plurality of detection images can directly replace the plurality of sampling images as the verification features of the reference object. In one embodiment, when receiving the multiple detection images, the server 10 can further confirm the multiple detection images again to confirm the similarity between the multiple detection images and the multiple adjustment images, so as to Avoid storing incorrect validation characteristics.

In a second embodiment of the detection method 600 of the present invention, the comparison of the plurality of detection images and the verification features is performed by the detection device 40, and the verification features include the correspondence of the reference object corresponding to the object to be detected. Sampling model for anchor points. In one embodiment, the detection device 40 transmits a request to detect the object to be detected. After receiving the request, the server 10 obtains the corresponding positioning point and the verification feature of the reference object corresponding to the object to be detected from the internal storage device 11 or the online storage device 30, and transmits the corresponding positioning point to the detection device. 40. In one embodiment, the server 10 may simultaneously send the sampling model to the detection device 40 at this time.

In one embodiment, after receiving the corresponding positioning point, the detection device 40 directly sets the corresponding positioning point as the positioning point of the object to be detected, and selects the multiple detection directions by itself, thereby obtaining the multiple detection directions. image. In one embodiment, if the detection device 40 has acquired the sampling model before acquiring the plurality of detection images, the comparison can be started directly. In another embodiment, if the detection device 40 has not acquired the sampling model before acquiring the plurality of detection images, the detection device 40 The detection device 40 can send a request for comparing the reference object to the server 10 again, and the server 10 then provides the sampling model to the detection device 40 after receiving the request. The server 10 can use this method of sending the request twice to prevent the user from sending the first request at will just to defraud all the verification information. In the embodiment, the request sent again by the detection device 40 may include the multiple detection images for the server 10 to perform a preliminary verification. If the server 10 believes that the multiple detection images are obviously completely irrelevant to the sampling model, the server 10 The processor 10 may refuse to provide the sampling model. If the server 10 believes that there is a slight correlation between the multiple detection images and the sampling model, the server 10 can send the sampling model for comparison by the detection device 40 .

In one embodiment, the detection device 40 can generate a detection model based on the multiple detection images, the multiple detection directions and the detection correspondence, and generate the detection model by comparing the similarity between the detection model and the sampling model. result. In another embodiment, the detection device 40 can infer multiple verification images based on the multiple detection directions and the sampling model, and then compare them one by one based on the detection correspondence between the multiple detection images and the multiple detection directions. The similarity between the plurality of verification images and the plurality of detection images is used to generate detection results.

In one embodiment, if the similarity between the verification images and the detection images is high or the similarity between the sampling model and the detection model is high, the detection device 40 may determine that the object to be detected is the reference object, and transmits the detection result to the server 10. If the similarity between the verification images and the detection images is low or the similarity between the sampling model and the detection model is low, the detection device 40 may determine that the object to be detected is not the reference object, and transmit the The detection results are sent to the server 10. In another embodiment, if the similarity between the verification images and the detection images is low or the similarity between the sampling model and the detection model is low, the detection device 40 may send a request for the reference object. A request for change information is sent to the server 10. In the above embodiment, the server 10 also performs another preliminary verification through the request for the change information (for example, requesting the complete detection images or detection models) to confirm whether the detection device 40 needs the change information. News. In one embodiment, the detection device 40 adjusts the sampling model according to the change information to generate an adjustment model as the adjustment feature, and then compares the adjustment model with the plurality of detection images through the detection correspondence, or directly compares The adjustment model and the detection model. If the similarity between the adjustment model and the plurality of detection images is low or the similarity between the adjustment model and the detection model is low, the detection device 40 may determine that the object to be detected is not the reference object, and transmit the The detection results are sent to the server 10. If the similarity between the adjustment model and the plurality of detection images is high or the similarity between the adjustment model and the detection model is high, the detection device 40 can update the detection results that were originally different and change the detection results to be determined to be the same. The detection object is the reference object, and the detection result is sent to the server 10 . In the embodiment, the detection device 40 can upload the multiple detection images or the detection model to the server 10 . If the detection device 40 uploads the multiple detection images to the server 10, the detection device 40 must upload the multiple detection directions and the detection correspondences together for the server 10 to generate the detection model. In the embodiment, the server 10 stores the detection model in the internal storage device 11 or the online storage device 30 . In one embodiment, the detection model and the plurality of sampling models can be simultaneously stored in the internal storage device 11 or the online storage device 30 corresponding to the reference object, so as to jointly serve as the verification feature of the reference object. In another embodiment, the detection model can directly replace the plurality of sampling models as the verification feature of the benchmark. In one embodiment, when obtaining the detection model, the server 10 may further confirm the detection model again to confirm the similarity between the detection model and the sampling model to avoid storing wrong verification features.

In a third embodiment of the detection method 600 of the present invention, the comparison between the plurality of detection images and the verification features is performed by the server 10, and the verification features include the corresponding positioning of the reference object corresponding to the object to be detected. The plurality of sampling images of the point, the plurality of sampling directions, and the sampling correspondence between the plurality of sampling images and the plurality of sampling directions. In one embodiment, the detection device 40 transmits a request to detect the object to be detected. After receiving the request, the server 10 obtains the corresponding position of the reference object corresponding to the object to be detected from the internal storage device 11 or the online storage device 30 point and the verification feature, and transmit the corresponding positioning point and the plurality of sampling directions in the verification feature to the detection device 40 . In the embodiment, the server 10 does not need to transmit the plurality of sampling images and the sampling correspondence to the detection device 40, so there is no need to worry about the plurality of sampling images and the sampling correspondence being obtained in an improper manner.

In one embodiment, after receiving the corresponding positioning point and the plurality of sampling directions, the detection device 40 directly sets the corresponding positioning point and the plurality of sampling directions respectively as the positioning point and the plurality of detection objects for the object to be detected. direction, and thereby obtain the multiple detection images. In one embodiment, the detection device 40 transmits the multiple detection images and the detection correspondence relationships between the multiple detection images and the multiple detection directions to the server 10 for the server 10 to perform a comparison with the verification feature. comparison between.

In one embodiment, the server 10 compares the plurality of sampling images and the plurality of detection images through the sampling correspondence and the detection correspondence. If the similarity between the plurality of sampling images and the plurality of detection images is When it is high, the server 10 can determine that the object to be detected is the reference object, and return the detection result to the detection device 40 . If the similarity between the plurality of sampling images and the plurality of detection images is low, the server 10 may determine that the object to be detected is not the reference object, and send the detection result to the detection device 40 . In another embodiment, if the similarity between the plurality of sampling images and the plurality of detection images is low, the server 10 can obtain the change of the reference object from the online storage device 30 or the internal storage device 11 information. In the embodiment, the server 10 does not need to send the change information to the detection device 40, so there is no need to worry about the change information being obtained in an improper manner.

In one embodiment, the server 10 adjusts the plurality of sampled images according to the change information to generate a plurality of adjusted images as part of the adjustment feature, and then compares the plurality of sampled images through the sampling correspondence and the detection correspondence. A plurality of adjustment images and the plurality of detection images. If the similarity between the plurality of adjustment images and the plurality of detection images is low, the server 10 may determine that the The object to be detected is not the reference object, and the detection result is sent to the detection device 40 . If the similarity between the plurality of adjustment images and the plurality of detection images is high, the server 10 can update the original detection results that are different, change the detection results to determine that the object to be detected is the reference object, and transmit the detection result. The result is given to the detection device 40. In the embodiment, the server 10 can store the plurality of detection images in the internal storage device 11 or the online storage device 30 . In one embodiment, the plurality of detection images and the plurality of sampling images may be simultaneously stored in the internal storage device 11 or the online storage device 30 corresponding to the reference object, so as to jointly serve as the verification feature of the reference object. In another embodiment, the plurality of detection images can directly replace the plurality of sampling images as the verification features of the reference object. In one embodiment, since the server 10 itself has done a complete comparison, there is no need to worry about storing wrong verification features.

In a fourth embodiment of the detection method 600 of the present invention, the comparison of the plurality of detection images and the verification features is performed by the server 10, and the verification features include the correspondence of the reference object corresponding to the object to be detected. Sampling model for anchor points. In one embodiment, the detection device 40 transmits a request to detect the object to be detected. After receiving the request, the server 10 obtains the corresponding positioning point and the verification feature of the reference object corresponding to the object to be detected from the internal storage device 11 or the online storage device 30, and transmits the corresponding positioning point to the detection device. 40. In the embodiment, the server 10 does not need to transmit the sampling model to the detection device 40, so there is no need to worry about the sampling model being obtained in an improper manner.

In one embodiment, after receiving the corresponding positioning point, the detection device 40 directly sets the corresponding positioning point as the positioning point of the object to be detected, and selects the multiple detection directions by itself, thereby obtaining the multiple detection directions. image. In one embodiment, the detection device 40 transmits the multiple detection images, the multiple detection directions, and the detection correspondence relationships between the multiple detection images and the multiple detection directions to the server 10 for use by the server 10 Compare with this verification feature. In another embodiment, the detection device 40 can detect based on the multiple detection images and the multiple detection directions. The detection model is automatically generated based on the detection corresponding relationship, and the detection model is sent to the server 10 for the server 10 to compare with the verification feature.

In one embodiment, the server 10 can generate the detection model based on the multiple detection images, the multiple detection directions and the detection correspondence, and generate the detection model by comparing the similarity between the detection model and the sampling model. Test results. In another embodiment, the server 10 may generate a detection result by comparing the similarity between the sampling model and the received detection model. In yet another embodiment, the server 10 can infer multiple verification images based on the multiple detection directions and the sampling model, and then compare them one by one based on the detection correspondence between the multiple detection images and the multiple detection directions. The similarity between the plurality of verification images and the plurality of detection images is used to generate detection results.

In one embodiment, if the similarity between the verification images and the detection images is high or the similarity between the sampling model and the detection model is high, the server 10 may determine that the object to be detected is the reference object, and transmits the detection result to the detection device 40. If the similarity between the multiple verification images and the multiple detection images is low or the similarity between the sampling model and the detection model is low, the server 10 may determine that the object to be detected is not the reference object, and transmit the The detection results are given to the detection device 40. In another embodiment, if the similarity between the verification images and the detection images is low or the similarity between the sampling model and the detection model is low, the server 10 can obtain the data from the online storage device. 30 or the internal storage device 11 obtains the change information of the reference object. In the embodiment, the server 10 does not need to send the change information to the detection device 40, so there is no need to worry about the change information being obtained in an improper manner.

In one embodiment, the server 10 adjusts the sampling model according to the change information to generate an adjustment model as the adjustment feature, and then compares the adjustment model with the plurality of detection images through the detection correspondence, or directly compares The adjustment model and the detection model. If the similarity between the adjustment model and the multiple detection images is low or the difference between the adjustment model and the detection model When the similarity is low, the server 10 can determine that the object to be detected is not the reference object, and send the detection result to the detection device 40 . If the similarity between the adjustment model and the plurality of detection images is high or the similarity between the adjustment model and the detection model is high, the server 10 can update the detection results that were originally different and change the detection results to be determined. The detection object is the reference object, and the detection result is sent to the detection device 40 . In the embodiment, the server 10 can store the detection model in the internal storage device 11 or the online storage device 30 . If the server 10 only has the plurality of detection images and the detection correspondence, the server 10 can generate a detection model based on the plurality of detection images, the plurality of detection directions and the detection correspondence and store it internally. in the storage device 11 or the online storage device 30. In one embodiment, the detection model and the sampling model can be simultaneously stored in the internal storage device 11 or the online storage device 30 corresponding to the reference object, so as to jointly serve as the verification feature of the reference object. In another embodiment, the detection model can directly replace the sampling model as the verification feature of the benchmark. In one embodiment, since the server 10 itself has done a complete comparison, there is no need to worry about storing wrong verification features.

7A and 7B show a schematic diagram of the image capturing unit 22 capturing sampling images in different sampling directions at the positioning point of the reference object according to an exemplary embodiment of the present invention. The image capturing unit 22 in FIG. 7A is located directly above the positioning point of the reference object, and the image capturing unit 22 in FIG. 7B has a deflection angle compared to the image capturing unit 22 in FIG. 7A .

In one embodiment, the image capturing unit 22 faces the positioning point of the reference object and captures the first sampling image 760 in a first imaging range 710. The sampling device 20 or the server 10 can capture the first sampling image 760 in the first imaging range 710. A first sampling area 761 is extracted from a sampling image 760, and the first sampling area 761 is further divided into a plurality of first sampling blocks 7611-7616. The sampling device 20 or the server 10 can calculate the plurality of first sampling blocks 7611. -7616 value. In the embodiment, the first sampling area 761 corresponds to an imaging area 711 in the first imaging range 710, and the plurality of first sampling blocks 7611-7616 correspond to the plurality of imaging blocks 7111-7116.

In one embodiment, the image capturing unit 22 faces the positioning point of the reference object at the deflection angle and captures the second sampling image 770 in a second imaging range 720. The sampling device 20 or the server 10. A second sampling area 771 can be extracted from the second sampling image 770, and the second sampling area 771 can be further divided into a plurality of second sampling blocks 7711-7716. The sampling device 20 or the server 10 can calculate a plurality of second sampling blocks 7711-7716. The values of the two sampling blocks 7711-7716. In the above embodiment, in order to make the imaging areas corresponding to the first sampling area 761 and the second sampling area 771 the same, the sampling device 20 or the server 10 makes the distance between the first sampling area 761 and the second sampling area 771 It can be the sampling results in the same area but in different directions. Therefore, the sampling device 20 or the server 10 can project the first sampling area 761 to the second sampling image 770 through the deflection angle to find the second sampling area 771 . Therefore, if the first sampling area 761 and the second sampling area 771 are projected onto the first imaging range 710 and the second imaging range 720 , the same imaging area 711 can be obtained, and multiple second sampling blocks 7711 -7716 can also correspond to multiple imaging blocks 7111-7116.

In the embodiment, the sampling device 20 or the server 10 can respectively calculate a value for each of the plurality of first sampling blocks 7611-7616 and the plurality of second sampling blocks 7711-7716. The plurality of values are used to represent the plurality of first sampling blocks 7611-7616 and a plurality of second sampling blocks 7711-7716. In one implementation, the multiple values may be the average, mode, or median of multiple pixels in each block. For example, the values of the plurality of first sampling blocks 7611-7616 may be a11, a12, a13, a14, a15 and a16 respectively, and the values of the plurality of second sampling blocks 7711-7716 may be a21, a22, a23 respectively. , a24, a25 and a26. In one implementation, the sampling device 20 or the server 10 can respectively obtain more values at other sampling angles. For example: a31, a32, a33, a34, a35, a36, ..., an1, an2, an3, an4, an5 and an6. Through this, the sampling device 20 or the server 10 can obtain the following multiple image data training sets: A1=[a11, a21, a31,...,an1]

A2=[a12,a22,a32,...,an2]

A3=[a13,a23,a33,...,an3]

A4=[a14,a24,a34,...,an4]

A5=[a15,a25,a35,...,an5]

A6=[a16, a26, a36,...,an6] In the embodiment, the sampling device 20 or the server 10 can combine these large amounts of image data training sets based on the machine learning technology. The sampling sample point data is used to generate a sampling model in the form of three-dimensional modeling. In an embodiment, the detection device 40 or the server 10 can also capture a large number of detection sample points through the multiple detection images in the same manner, and establish multiple image data training sets, and use machine learning technology to , these large amounts of detection sample point data are used to generate detection models in the form of three-dimensional modeling.

8A-8E are photos of different sampling images captured on a painting as a reference object according to an exemplary embodiment of the present invention. Please refer to FIG. 1 and FIG. 2 together. The image capturing unit 22 captures multiple sampling images on the reference object. The sampling device 20 or the server 10 can use the multiple sampling images to generate verification features. In one implementation, the verification feature can be directly the plurality of sampled images. In another embodiment, the verification feature can also be analyzed and trained by using machine learning technology to generate the verification features required for verification. In the embodiment, the verification feature may be a three-dimensionally modeled sampling model.

8F to 8J are photos of different detection images captured on a painting as an object to be detected according to an exemplary embodiment of the present invention. Please refer to FIG. 4 and FIG. 5 together. Through the image capture unit 42, multiple detection images are captured on the object to be detected. The detection device 40 or the server 10 can use the multiple detection images to compare with the verification feature. Make a comparison.

In one embodiment, if the verification feature is a plurality of sampling images, the detection device 40 or the server 10 can directly compare FIGS. 8A-8E with FIGS. 8F-8J to identify that the object to be detected is obvious. Different from the benchmark. In another implementation, if the verification feature is the sampling pattern According to Figures 8A-8E, the sampling pattern should have no obvious unevenness and a relatively steep slope. Therefore, the detection device 40 or the server 10 combines the detection images of Figures 8F-8J with the sampling model. When comparing, it can be found that there is a significant difference in the slope between the two, and it can be identified that the object to be detected is different from the reference object.

Please refer to FIGS. 9A and 9B . FIGS. 9A and 9B are sampling images of different gemstones sampled in the same processing method in the same sampling direction according to an exemplary embodiment of the present invention. From Figure 9A and Figure 9B, even if the sampling direction is exactly the same and the processing process is exactly the same, different sampling images may still be produced between different gemstones due to factors such as the color or clarity of the gemstone itself. Therefore, as long as a gemstone is used as a reference object and a sampling image is captured in advance to generate verification features, the detection device and detection method can subsequently be used to confirm whether the object to be detected is a gemstone that has been sampled previously.

Please refer to Figures 10A-10C. Figure 10A is a photo of antique utensils with the same texture but different textures. 10B and 10C are sampling images of different antique utensils shown in FIG. 10A sampled in the same sampling direction according to an exemplary embodiment of the present invention. Judging from Figure 10B and Figure 10C , even antique utensils with the same texture may still have different texture changes due to slight differences in glaze distribution during the firing process of the antique utensils. Therefore, as long as an antique utensil is used as a reference object and the sampling image is captured in advance to generate verification features, the detection device and detection method can subsequently be used to confirm whether the object to be detected is an antique utensil that has been sampled previously.

The method described in the present invention is not limited to use in works of art (including but not limited to paintings, sculptures, etc.), gemstones (including but not limited to diamonds, sapphires, jade, etc.) or antique items (including but not limited to pottery, porcelain, etc.) , as long as the verification characteristics of the reference object (including but not limited to color distribution, texture details, scratch defects, etc.) are obtained in advance, it can be used as the basis for subsequent verification of the object to be detected.

Therefore, one aspect of the present disclosure provides a method for detecting an object to be detected by a detection device. The method includes: transmitting a request to detect the object to be detected; receiving the positioning point of the object to be detected; Obtain multiple detection images along multiple detection directions at the positioning point of the object to be detected; and obtain a detection result based on the multiple detection images, wherein the detection result is based on the multiple detection images and the corresponding object to be detected It is generated by a comparison of a corresponding positioning point of a reference object.

Another aspect of the present disclosure provides a detection device for detecting an object to be detected. The detection device includes: an image capture unit used to obtain a plurality of detection images; a movement control unit, the The movement control unit is used to make the image capture unit move when detecting the object to be detected; the processor is coupled to the image capture unit and the mobile unit; the transmission unit is connected to The processor is coupled; a receiving unit coupled to the processor; and a storage device coupled to the processor and storing a plurality of instructions that when executed by the processor The processor: transmits a request to detect the object to be detected through the transmission unit; receives the positioning point of the object to be detected through the receiving unit; and causes the image capture unit to move at the position of the object to be detected through the movement control unit. At the positioning point, the multiple detection images are obtained along multiple detection directions; and a detection result is obtained based on the multiple detection images, wherein the detection result is based on the multiple detection images and a benchmark corresponding to the object to be detected. It is generated by a comparison of corresponding positioning points of objects.

In some embodiments of the detection device or the detection method of the present invention, when the detection result indicates that the reference object is different from the object to be detected, a change data of the reference object and a verification feature of the reference object are generated. Adjustment characteristics, wherein: the comparison is to compare the multiple detection images with the verification characteristics, and the change data of the reference object is from an online storage device; and based on the multiple detection images and the adjustment characteristics, update The test results.

In some embodiments of the detection device or the detection method of the present invention, when the updated detection result indicates that the reference object is the same as the object to be detected, a detection feature is transmitted to the online storage device to store the detection feature in In the online storage device, the detection feature is generated based on the plurality of detection images, and the detection feature stored in the online storage device corresponds to the reference object.

In some embodiments of the detection device or the detection method of the present invention, the detection feature replaces the verification feature of the reference object stored in the online storage device.

In some embodiments of the detection device or its detection method of the present invention, the detection results are generated by comparing the multiple detection images with a verification feature of the reference object; the verification feature is a reconstruction based on multiple sampling images. Sampling model, the plurality of sampling images are obtained along multiple sampling directions at the corresponding positioning points of the reference object, and the detection results are compared with the detection image and the sampling model based on the multiple detection directions. One degree of similarity.

In some embodiments of the detection device or its detection method of the present invention, the detection results are generated by comparing the multiple detection images with a verification feature of the reference object; the verification feature is a reconstruction based on multiple sampling images. Sampling model, the plurality of sampling images are obtained along the plurality of sampling directions at the corresponding positioning point of the reference object, the plurality of detection images reconstruct a detection model based on the plurality of detection directions, and the detection result is a comparison The similarity between the detection model and one of the sampling models.

In some embodiments of the detection device or its detection method of the present invention, the detection results are generated by comparing the plurality of detection images with a verification feature of the reference object; the verification feature is at the corresponding positioning point of the reference object A plurality of sampling images obtained along a plurality of sampling directions, the detection result is a comparison of the similarity between the plurality of detection images and one of the plurality of sampling images, and the plurality of detection directions are obtained from an online storage device. The multiple sampling directions obtained.

One aspect of the present disclosure provides a method for detecting an object to be detected by a server. The method includes: receiving a request to detect the object to be detected; sending the positioning point of the object to be detected; receiving the location point of the object to be detected; Multiple detection images obtained along multiple detection directions on the positioning point of the detection object; and obtaining a detection result based on the multiple detection images, wherein the detection result is based on the multiple detection images and the corresponding object to be detected Produced by a comparison of a benchmark.

One aspect of the present disclosure provides a server for detecting an object to be detected. The server includes: a processor; a transmitting unit coupled to the processor; and a receiving unit coupled to the processor. Coupling; and a storage device, the storage device is coupled to the processor and stores a plurality of instructions, which when executed by the processor, cause the processor to: receive a message for detecting the object to be detected through the receiving unit. Request; send the positioning point of the object to be detected through the transmission unit; receive multiple detection images obtained along multiple detection directions at the positioning point of the object to be detected through the receiving unit; and based on the multiple detections The image obtains a detection result, wherein the detection result is generated based on a comparison between the plurality of detection images and a reference object corresponding to the object to be detected.

In some embodiments of the server or the detection method of the present invention, when the detection result indicates that the reference object is different from the object to be detected, a change data of the reference object and a verification feature of the reference object are generated. Adjustment characteristics, wherein: the comparison is to compare the multiple detection images with the verification characteristics, and the change data of the reference object is from an online storage device; and based on the multiple detection images and the adjustment characteristics, update The test results.

In some embodiments of the server of the present invention or its detection method, when the updated detection result indicates that the reference object is the same as the object to be detected, a detection feature is sent to the online storage device to store the detection feature in In the online storage device, the detection feature is generated based on the plurality of detection images, and the detection feature stored in the online storage device corresponds to the reference object.

In some embodiments of the server or the detection method of the present invention, the detection feature replaces the verification feature of the reference object stored in the online storage device.

In some embodiments of the server or its detection method of the present invention, the detection results are generated by comparing the multiple detection images with a verification feature of the reference object; the verification feature is a reconstruction based on multiple sampling images. Sampling model, the plurality of sampling images are obtained along multiple sampling directions at the corresponding positioning points of the reference object, and the detection results are compared with the detection image and the sampling model based on the multiple detection directions. One degree of similarity.

In some embodiments of the server or its detection method of the present invention, the detection results are generated by comparing the multiple detection images with a verification feature of the reference object; the verification feature is a reconstruction based on multiple sampling images. Sampling model, the plurality of sampling images are obtained along the plurality of sampling directions at the corresponding positioning point of the reference object, the plurality of detection images reconstruct a detection model based on the plurality of detection directions, and the detection result is a comparison The similarity between the detection model and one of the sampling models.

In some embodiments of the server or its detection method of the present invention, the detection results are generated by comparing the plurality of detection images with a verification feature of the reference object; the verification feature is at the corresponding positioning point of the reference object A plurality of sampling images obtained along a plurality of sampling directions, the detection result is a comparison of the similarity between the plurality of detection images and one of the plurality of sampling images, and the plurality of detection directions are obtained from an online storage device. The multiple sampling directions obtained.

One aspect of the present disclosure provides a sampling method for establishing identification data on a benchmark object using a sampling device. The method includes: obtaining a certain position on the benchmark object; and sampling along a plurality of sampling directions on the position point on the benchmark object. Obtain multiple sampling images; generate sampling features of the positioning point of the reference object based on the multiple sampling images and the multiple sampling directions; and transmit the sampling features for storage by a network device.

One aspect of the present disclosure provides a sampling device for sampling a reference object to establish identification data. The sampling device includes: an image capturing unit used to acquire a plurality of sampling images; a movement control unit, The movement control unit is used to enable the image capture unit to move when sampling the reference object; a processor coupled to the image capture unit and the mobile unit; a transmission unit coupled to The processor is coupled; and a storage device, the storage device is coupled to the processor and stores a plurality of instructions that, when executed by the processor, cause the processor to: obtain a certain position on the reference object ; Use the movement control unit to cause the image capture unit to acquire multiple sampling images along multiple sampling directions at the positioning point of the benchmark object; generate the benchmark based on the multiple sampling images and the multiple sampling directions. sampling characteristics of the positioning point of the object; and transmitting the sampling characteristics through the transmission unit for storage by a network device.

In some embodiments of the sampling device or the sampling method of the present invention, the positioning point set for the reference object is received from a server, wherein: when the server is a network device, the server stores the positioning point point, and when the server is an online storage device, the server sends the anchor point to the online storage device.

In some embodiments of the sampling device or the sampling method of the present invention, when the positioning point is set by the sampling device, the positioning point is transmitted to the network device.

This disclosure claims the benefit and priority of U.S. Provisional Patent Application Serial No. 63/183643, filed on May 4, 2021, entitled "Surface Micro Feature Recognition Using Blockchain" (hereinafter referred to as the "'643 Provisional"). The disclosures of the '643 Provisional Case are hereby fully incorporated by reference into this disclosure.

As mentioned above, the above embodiments are only used to illustrate the technical solution of the present invention, but not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the foregoing. The technical solutions described in each embodiment are modified Modifications, or equivalent substitutions are made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to depart from the scope of the technical solutions of the embodiments of the present invention.

To sum up, this invention meets the requirements for an invention patent and a patent application should be filed in accordance with the law. However, the above are only preferred embodiments of the present invention. Any equivalent modifications or changes made by those familiar with the art of this application in accordance with the creative spirit of this application should be included in the scope of the following patent application.

600:Method

S610-S640: Steps

Claims (9)

A method for detecting an object to be detected by a detection device. The method includes: transmitting a request to detect the object to be detected; receiving a positioning point of the object to be detected; and detecting an object at the positioning point of the object to be detected. Obtain multiple detection images in multiple detection directions; obtain a detection result based on the multiple detection images, wherein the detection result is based on a corresponding positioning point of the multiple detection images and a reference object corresponding to the object to be detected Generated by a comparison; when the test result indicates that the reference object is different from the object to be detected, an adjustment feature is generated based on a change data of the reference object and a verification feature of the reference object, wherein: the comparison is The plurality of detection images are compared with the verification feature. The change data of the reference object is from an online storage device. The adjustment feature is generated by the change data and a time difference, and the time difference is a value of the reference object. The difference between the sampling time point and a detection time point of the object to be detected; and updating the detection result based on the multiple detection images and the adjustment characteristics. The method of claim 1, further comprising: when the updated detection result indicates that the reference object is the same as the object to be detected, transmitting a detection feature to the online storage device to store the detection feature on the online Storage device, wherein: the detection feature is generated based on the plurality of detection images, and the detection feature stored in the online storage device corresponds to the reference object. The method of claim 2, wherein the detection feature replaces the verification feature of the reference object stored in the online storage device. A method as described in request item 1, wherein: The verification feature is a sampling model reconstructed based on a plurality of sampling images obtained along a plurality of sampling directions at the corresponding positioning points of the reference object, and the detection result is based on the plurality of sampling images. The detection direction is used to compare the similarity between the detection image and one of the sampling models. The method of claim 1, wherein: the verification feature is a sampling model reconstructed based on multiple sampling images, and the multiple sampling images are obtained along multiple sampling directions on the corresponding positioning points of the benchmark object. Obtaining, the plurality of detection images reconstructs a detection model based on the plurality of detection directions, and the detection result is a similarity between the detection model and the sampling model. The method of claim 1, wherein: the verification feature is a plurality of sampling images obtained along a plurality of sampling directions at the corresponding positioning point of the reference object, and the detection result is a comparison of the plurality of detection images Similarity to one of the plurality of sampling images, and the plurality of detection directions are the plurality of sampling directions obtained from an online storage device. A detection device for detecting an object to be detected, the detection device includes: an image capture unit, the image capture unit is used to obtain a plurality of detection images; a movement control unit, the movement control unit is used to make the image The capturing unit moves when detecting the object to be detected; a processor coupled to the image capturing unit and the movement control unit; a transmitting unit coupled to the processor; receiving unit, the receiving unit is coupled to the processor; and A storage device that is coupled to the processor and stores a plurality of instructions that, when executed by the processor, cause the processor to: transmit a request to detect the object to be detected through the transmission unit; The receiving unit receives the positioning point of the object to be detected; through the movement control unit, the image capturing unit acquires the multiple detection images along multiple detection directions at the positioning point of the object to be detected; based on the multiple detection images The detection image obtains a detection result, wherein the detection result is generated based on a comparison of the plurality of detection images and a corresponding positioning point of a reference object corresponding to the object to be detected; when the detection result indicates that the reference object and When the objects to be detected are different, an adjustment feature is generated based on a change data of the reference object and a verification feature of the reference object, wherein: the comparison is to compare the multiple detection images with the verification feature, and the reference The change data of the object comes from an online storage device, the adjustment feature is generated by the change data and a time difference, and the time difference is the difference between a sampling time point of the reference object and a detection time point of the object to be detected ; and update the detection results based on the multiple detection images and the adjustment features. The detection device as claimed in claim 7, wherein the plurality of instructions, when executed by the processor, further causes the processor to: when the updated detection result indicates that the reference object is the same as the object to be detected, send a The detection feature is provided to the online storage device to store the detection feature in the online storage device, wherein: the detection feature is generated based on the plurality of detection images, and the detection feature stored in the online storage device corresponds to the benchmark things. A method for detecting an object to be detected by a server. The method includes: receiving a request to detect the object to be detected; sending the positioning point of the object to be detected; receiving an edge on the positioning point of the object to be detected. Multiple detection images obtained in multiple detection directions; and obtaining a detection result based on the multiple detection images, wherein the detection result is based on a comparison between the multiple detection images and a reference object corresponding to the object to be detected Generated; when the test result indicates that the reference object is different from the object to be detected, an adjustment feature is generated based on a change data of the reference object and a verification feature of the reference object, wherein: the comparison is to compare the multiple A detection image is compared with the verification feature, the adjustment feature is generated by the change data and a time difference, and the time difference is the difference between a sampling time point of the reference object and a detection time point of the object to be detected; and based on The multiple detection images and the adjustment features update the detection results.

Images