TWM591198U - Object recognition system - Google Patents

Abstract

This creation discloses an object recognition system, which includes an image analysis device and a smart electronic device; wherein the image analysis device includes an image capture module and an image calculation module, and the image capture module captures an object to be measured to generate an image Message, the image computing module is connected to the image capture module and computes the image information to generate object recognition information; the smart electronic device is connected to the image computing module and receives the object recognition information, and the smart electronic device includes a plurality of object presets Information, the intelligent electronic device compares the preset information of each object with the object identification information. When the object identification information matches the preset information of one of the objects, the intelligent electronic device generates corresponding first identification result information, when the object identification information does not match One of the objects presets information, and the intelligent electronic device correspondingly generates the second identification result information.

Description

Object recognition system

This creation is about an identification system, especially about an object identification system that can identify objects based on their characteristics.

At present, some conventional recognition systems with the function of recognizing objects usually use the image capturing device to capture the image of the recognition target. After obtaining the image information, the overall image is used for calculation and analysis, and the image analysis result is preset with Cross-comparing the comparison information. When the image analysis result is consistent with the comparison information, it can determine what kind of object the target to be identified is; however, when the system can only analyze the overall image characteristics, it is easy to calculate the size of some of the features of the target Operational errors occur inconsistently, and when the operation target is slightly swayed and cannot perform detailed operations on the details of the overall image, operation errors may also occur and affect the recognition results.

In addition, the current conventional technology that can perform the function of object recognition does not effectively integrate the message encryption function, so the recognition result information generated after the recognition system recognizes the object is only intended to provide some specific people, or the recognition result information may affect individuals Or the privacy of the company's line number, the information security of the identification result information cannot be effectively guaranteed.

In view of the above problems, the inventor of the present invention has improved the object recognition system that cannot effectively analyze the captured images and ensure the security of the recognition result information, in order to solve the problems of the conventional object recognition system.

In view of the above-mentioned conventional problems, the purpose of this creation is to provide an object recognition system, which includes an image analysis device and a smart electronic device; wherein the image analysis device includes an image acquisition module and an image operation module, and the image The capture module captures the object to be tested to generate image information. The image calculation module connects the image capture module and calculates the image information to generate object identification information; the smart electronic device connects the image calculation module and receives the object identification information , The intelligent electronic device includes a plurality of object preset information, the intelligent electronic device compares the object preset information with the object identification information, and when the object identification information matches one of the object preset information, the intelligent electronic device is generated correspondingly For the first recognition result information, when the object recognition information does not match one of the object preset information, the smart electronic device correspondingly generates the second recognition result information.

Preferably, the image calculation module can calculate image messages to generate a plurality of image sub-messages, the plurality of image sub-messages are arranged in a matrix form, and the image calculation module calculates each image sub-message to generate corresponding analysis messages, and The image computing module integrates various analysis information to generate object recognition information.

Preferably, the object recognition information system may include image shape information, image color information, and image specific orientation feature information. The plurality of object default information systems include preset shape information, preset color information, and preset specific orientation feature information, respectively. Moreover, the preset information of a plurality of objects is different from each other; when the object identification information, the image shape information, image color information, and image specific orientation feature information correspond to the preset shape information and preset color information of one of the object preset information, respectively And preset specific orientation feature information, that is, the object identification information matches the preset information of one of the objects, and the intelligent electronic device correspondingly generates the first identification result information.

Preferably, the image computing module may include a remote transmission unit, which transmits object identification information to a remote smart electronic device.

Preferably, the smart electronic device generates the first password message and the second password message according to the ellipse encryption algorithm, the first password message and the second password message correspond to each other, and the smart electronic device sends the first password message to the image Computing module, the image computing module encrypts the object identification information according to the first cryptographic message, the object identification information is an encryption type, the image computing module transmits the object identification information to the smart electronic device, and the smart electronic device is based on the first Two password messages are used to decrypt the object identification information, the encryption type of the object identification information is released, and the smart electronic device compares the preset information of each object with the object identification information.

The intelligent electronic device generates the first password message and the second password message according to the RSA encryption algorithm. The first password message and the second password message correspond to each other, and the intelligent electronic device sends the first password message to the image computing module. The image computing module encrypts the object identification information according to the first cryptographic message. The object identification information is an encryption type. The image computing module transmits the object identification information to the smart electronic device. The smart electronic device uses the second cryptographic message to The object identification information is decrypted, the encryption type of the object identification information is released, and the intelligent electronic device compares the preset information of each object with the object identification information.

In summary, the object recognition system of this creation has the following advantages:

(1) Compared with the conventional recognition system, the image recognition module of the created object recognition system can compute image information to generate a plurality of image sub-messages, and the plurality of image sub-messages are arranged It is a matrix type, and the image computing module calculates each image sub-message to generate corresponding analysis information, and can further integrate each analysis information to generate object identification information; therefore, the image information module is disassembled into The plurality of image sub-messages arranged in a matrix form is helpful for the image calculation module to perform detailed analysis and calculation on each image sub-message, so it is more accurate to analyze the minute features of the object to be measured, or when the object to be measured Produce If some of the characteristics of the image message are less clear due to shaking or interference by external factors, the technical means to increase the subsequent calculation procedures by disassembling the image message can avoid the calculation of the image message containing slightly unclear features. The situation that affects the overall recognition result, that is, it has the function of effectively eliminating the operation error to further obtain accurate recognition results.

(2) The intelligent electronic device of the created object recognition system can generate the corresponding first password message and second password message according to the ellipse encryption algorithm or RSA encryption algorithm. When the intelligent electronic device sends the first password message to Image computing module. The image computing module can encrypt the object identification information according to the first cryptographic message and send it to the smart electronic device. At this time, the smart electronic device can decrypt the object identification information according to the second cryptographic message to make the smart electronic The device can compare the object identification information and the preset information of each object; by this system configuration, the image calculation module cannot release the encrypted type of object identification information by calculating the first password message, so it can effectively protect the object identification The privacy and information security of the personal or company line number corresponding to the object.

In order to make the above-mentioned objectives, technical features and gains after actual implementation more obvious and understandable, in the following, the preferred embodiments will be supplemented with corresponding drawings to explain in more detail.

10‧‧‧Object recognition system

20‧‧‧Image analysis device

30‧‧‧Image capture module

40‧‧‧Image operation module

50‧‧‧Object recognition information

60‧‧‧Object to be measured

70‧‧‧ video message

80‧‧‧Video sub-message

90‧‧‧smart electronic device

101‧‧‧ First recognition result information

102‧‧‧Second recognition result information

110‧‧‧ remote transmission unit

121‧‧‧The first password message

122‧‧‧Second password message

S1, S2, S3, S4 ‧‧‧ steps

Figure 1 is a system configuration diagram of the object recognition system based on this creation.

Figure 2 is a schematic diagram of the image sub-information of the object recognition system based on this creation.

Figure 3 is a flow chart of the application of the object recognition system based on this creation.

In the description of this creation, it should be noted that the terms "first" and "second" are used for description purposes only, and cannot be understood as indicating or implying relative importance.

In the description of this creation, it should be noted that the terms "link", "analysis", "calculation", "reception", "comparison", "recognition" and "transmission" unless otherwise clearly specified and limited , "Encryption" and "Decryption" should be broadly understood. For those of ordinary knowledge in the technical field to which they belong, they can understand the specific meaning of the above terms in this creation in specific circumstances.

In the following, embodiments of the object recognition system created according to the present invention will be described with reference to related drawings. For ease of understanding, the same elements in the following embodiments are denoted by the same symbols.

Please refer to Figure 1 and Figure 2. Figure 1 is the system configuration diagram of the object recognition system created, and Figure 2 is the image sub-message diagram of the object recognition system created. As shown in the figure, the purpose of this creation is to provide an object recognition system 10, which includes an image analysis device 20 and a smart electronic device 90; wherein the image analysis device 20 includes an image capture module 30 and an image operation Module 40, the image capture module 30 captures the object 60 to be measured to generate image information 70, and the image calculation module 40 is connected to the image capture module 30 and calculates the image information 70 to generate object identification information 50; intelligent electronics The device 90 is connected to the image computing module 40 and receives object identification information 50. The intelligent electronic device 90 includes a plurality of object preset information. The intelligent electronic device 90 compares the object preset information with the object identification information 50.

When the intelligent electronic device 90 compares the object identification information 50 with the preset information of each object in sequence, when the object identification information 50 matches one of the object preset information, the intelligent electronic device 90 generates the first recognition result information correspondingly 101, the object to be measured 60 corresponding to the object identification information 50 is the object represented by the object preset information; and when the object identification information 50 does not meet the preset information of one of the objects, the smart electronic device 90 generates the corresponding 2. The recognition result information 102, which represents that the object to be measured 60 corresponding to the object recognition information 50 is not the object represented by the object preset information, and at this time, the intelligent electronic device 90 drives the object recognition information 50 to compare with the preset information of another object .

The image operation module 40 operates the image message 70 to generate a plurality of image sub-messages 80, the plurality of image sub-messages 80 are arranged in a matrix form, and the image operation module 40 operates each image sub-message 80 to generate a corresponding analysis message. And the image computing module 40 integrates the analysis information to generate the object identification information 50; FIG. 2 is a schematic illustration of the object to be measured 60 captured by Apple as the image capture device. After the image information 70 is formed, it can be By disassembling the image message 70 into a plurality of image sub-messages 80 arranged in a matrix form by the image computing module 40, it is advantageous to disassemble the image message 70 into a plurality of image sub-messages 80 in a grid shape The image calculation module 40 performs detailed calculation and analysis on each image sub-message 80. In addition, by disassembling the image message 70 to increase the technical means of local calculation, the accuracy of object recognition information 50 due to calculation errors can be effectively avoided. Situation; the above is just an example and not limited to this.

The object identification information 50 includes image shape information, image color information, and image specific orientation feature information. The plurality of object preset information includes preset shape information, preset color information, and preset specific orientation feature information, respectively, and a plurality of objects The preset information is different from each other; when the image shape information, the image color information, and the image specific orientation feature information of the object identification information 50 correspond to the preset shape information, the preset color information, and the preset information of one of the object preset information, respectively The specific orientation characteristic information, that is, the object identification information 50 matches the preset information of one of the objects, and the intelligent electronic device 90 generates the first identification result information 101 accordingly.

The image computing module 40 includes a remote transmission unit 110 that transmits the object identification information 50 to the remote smart electronic device 90; wherein the remote transmission unit 110 can execute the object via Bluetooth or wireless network The transmission function of the identification information 50.

The intelligent electronic device 90 generates the first password message 121 and the second password message 122, the first password message 121 and the second password according to the ellipse encryption algorithm or the RSA encryption algorithm The code messages 122 correspond to each other, and the smart electronic device 90 transmits the first password message 121 to the image computing module 40. The image computing module 40 encrypts the object identification information 50 according to the first password message 121. The object identification information 50 is For the encryption type, the image computing module 40 transmits the object identification information 50 to the smart electronic device 90. The smart electronic device 90 decrypts the object identification information 50 according to the second cryptographic message 122. The encryption type of the object identification information 50 After the system is released, the intelligent electronic device 90 compares the preset information of each object with the object identification information 50.

Among them, the elliptic encryption algorithm (Elliptic Curve Cryptography, ECC) or RSA encryption algorithm are both asymmetric encryption algorithms; the asymmetric encryption algorithm uses different public and private keys corresponding to each other, that is, using the public key to encrypt The message can only be decrypted by the corresponding private key, but cannot be decrypted by further analysis and calculation of the public key. Among them, the first cryptographic message 121 created is set as the public in the asymmetric encryption algorithm Key, the second cryptographic message 122 is set as the private key in the asymmetric encryption algorithm, and the image computing module 40 encrypts the object identification information 50 according to the first cryptographic message 121 and transmits the smart electronic device 90, the smart electronic device 90 can decrypt the object identification information 50 according to the second cryptographic message 122. In addition, the image calculation module 40 cannot decrypt the object identification information 50 that is already in the encrypted mode by analyzing the first cryptographic message 121.

Please refer to Figure 3, which is an application flowchart of the object recognition system created for this. As shown in the figure, the object recognition system 10 of the present creation includes the following application steps:

In step S1: the image information 70 is generated by the image capturing module 30 photographing the object 60 to be measured.

In step S2: The object information 50 is generated by the image computing module 40 computing the image information 70.

In step S3: the intelligent electronic device 90 compares the preset information of each object with the object identification information 50.

In step S4: when the object identification information 50 matches one of the object preset information, the smart electronic device 90 generates the first identification result information 101 correspondingly, and when the object identification information 50 does not match one of the object preset information, the smart electronic The device 90 generates the second recognition result information 102 correspondingly.

Compared with the conventional recognition system, the object recognition system 10 of the present creation has an image operation module 40 that can calculate the image information 70 to generate a plurality of image sub-messages 80 and a plurality of image sub-messages. The 80 series is arranged in a matrix type, and the image calculation module 40 calculates each image sub-message 80 to generate corresponding analysis information, and can further integrate each analysis message to generate object identification information 50; therefore, the image calculation module 40. Disassembling the image message 70 into a plurality of image sub-messages 80 arranged in a matrix form is advantageous for the image calculation module 40 to perform detailed analysis and calculation on each image sub-message 80, so it is more accurate to analyze the test The small features of the object 60, or when the object 60 to be measured shakes or is interfered by external factors to make some of the features of the image message 70 less clear, by disassembling the image message 70, the subsequent calculation procedures increase the technical means, It can avoid the situation that the image information 70 containing slightly unclear features affects the overall recognition result, that is, it can effectively eliminate the operation error and further obtain accurate recognition results.

The intelligent electronic device 90 of the object recognition system 10 of the present invention can generate the first password message 121 and the second password message 122 corresponding to each other according to the ellipse encryption algorithm or the RSA encryption algorithm. When the intelligent electronic device 90 transmits the first password The message 121 is sent to the image computing module 40. The image computing module 40 can encrypt the object identification information 50 according to the first password message 121 and send it to the smart electronic device 90. At this time, the smart electronic device 90 can use the second password message 122 Decrypt the object identification information The smart electronic device 90 can compare the object identification information 50 and the preset information of each object; with this system configuration, the image calculation module 40 cannot release the encrypted object identification information 50 by calculating the first password message 121 Therefore, it can effectively protect the privacy and information security of the individual or company line number corresponding to the object to be identified.

The above is only exemplary, and not restrictive. Any modifications or changes made to the school without departing from the spirit and scope of this creation shall be included in the scope of the attached patent application.

10‧‧‧Object recognition system

20‧‧‧Image analysis device

30‧‧‧Image capture module

40‧‧‧Image operation module

50‧‧‧Object recognition information

70‧‧‧ video message

90‧‧‧smart electronic device

101‧‧‧ First recognition result information

102‧‧‧Second recognition result information

110‧‧‧ remote transmission unit

121‧‧‧The first password message

122‧‧‧Second password message

Claims (6)

An object recognition system includes: an image analysis device, including: an image capture module that captures an object on the side to generate an image message; an image calculation module that connects the image capture module and Computing the image information to generate an object identification information; and a smart electronic device connected to the image operation module and receiving the object identification information, the smart electronic device includes a plurality of object preset information, the smart electronic The device compares the object identification information with the object preset information. When the object identification information matches one of the object preset information, the smart electronic device correspondingly generates a first identification result information, when the object identification information If one of the object preset information is not met, the intelligent electronic device correspondingly generates a second identification result information. An object recognition system as described in item 1 of the patent application scope, wherein the image computing module computes the image message to generate a plurality of image sub-messages, the plurality of image sub-messages are arranged in a matrix type, and the image computing module Each image sub-message is calculated to generate a corresponding analysis message, and the image calculation module integrates each analysis message to generate the object identification information. An object recognition system as described in item 1 of the patent application scope, wherein the object recognition information includes an image shape information, an image color information, and an image specific orientation feature information, and the plurality of object preset information includes a pre Set shape information, a preset color information and a preset specific orientation feature information, and the preset information of the plurality of objects are different from each other; when the object identification information is the image shape information, the image color information and the image specific The azimuth feature information corresponds to The preset shape information, the preset color information, and the preset specific orientation feature information of one of the object preset information, that is, the object identification information matches one of the object preset information, and the smart electronic device is generated correspondingly The first recognition result information. An object recognition system as described in item 1 of the patent application range, wherein the image computing module includes a remote transmission unit that transmits the object recognition information to the remote intelligent electronic device. The object identification system as described in item 1 of the patent application scope, wherein the intelligent electronic device generates a first password message and a second password message according to an ellipse encryption algorithm, the first password message and the second password message are Correspond to each other, and the smart electronic device sends the first password message to the image computing module, the image computing module encrypts the object identification information according to the first password message, and the object identification information is an encryption type , The image computing module sends the object identification information to the smart electronic device, the smart electronic device decrypts the object identification information according to the second cryptographic message, the encryption type of the object identification information is released, the The intelligent electronic device compares the preset information of each object with the object identification information. The object identification system as described in item 1 of the patent application scope, wherein the intelligent electronic device generates a first password message and a second password message according to the RSA encryption algorithm, the first password message and the second password message are Correspond to each other, and the smart electronic device sends the first password message to the image computing module, the image computing module encrypts the object identification information according to the first password message, and the object identification information is an encryption type , The image computing module transmits the object identification information to the smart electronic device, the smart electronic device decrypts the object identification information according to the second password message, and the encryption type of the object identification information It is released, and the intelligent electronic device compares the preset information of each object with the object identification information.

Images