TWI707308B - Object detection method and system based on monochromatic light - Google Patents

Abstract

The invention provides an object detection method and system based on monochromatic light. The system includes a transmission unit, a camera, a light source, a light dividing unit and a computer device. The method includes: dispersing an incident light of a light source into monochromatic light of different colors through the dividing unit; collecting a picture of an object to be tested every preset time by the camera when the object getting through the monochromatic light, and obtaining a number of pictures of the object; acquiring a number of pictures of the object by the computer device and extracting the pictures of the object under the same color light from the extracted pictures, and integrating the extracted pictures under the same color light by the computer device; and outputting the integrated picture for object detection by the computer device.

Description

Object detection method and detection system based on monochromatic light

The invention relates to the field of object detection, in particular to an object detection method based on monochromatic light and an object detection system based on monochromatic light.

In the current assembly line production process, it is often necessary to inspect the surface of the product or obtain the image of the surface of the object to be tested. The traditional inspection method is to use multiple colors of light sources according to the physical characteristics of the object to be inspected, and light the camera sequentially. , Check the physical characteristics of the surface of the object to be inspected by the nature of the reflected light. The traditional method is to use a single light source, and it often happens that the target image disappears. Different colors of light are needed to highlight the target image, and this process takes a lot of time, especially on the assembly line, due to the replacement of the light source To cause the target image to disappear, the conveyor belt of the assembly line needs to be paused, and the camera unit can only continue to rotate after the camera unit has acquired the reflected light.

In view of the above, it is necessary to propose an object detection method based on monochromatic light and an object detection system based on monochromatic light, so that the object detection based on monochromatic light can quickly and easily complete the detection of the object to be measured without changing the light source. .

The first aspect of the present application provides an object detection method based on monochromatic light, the method comprising: decomposing incident light from a light source into monochromatic light of different colors by a light splitting unit; When the object to be measured moves with the transmission unit and the area is illuminated by the monochromatic light of different colors, the camera unit collects pictures of the object to be measured every predetermined time to obtain multiple pictures of the object to be measured; the computer device obtains The multiple pictures of the object to be measured extract the pictures of the object under the same color light from the multiple pictures; the computer device integrates the pictures of the object to be measured extracted from the multiple pictures under the same color light; The computer device outputs the integrated picture for object detection.

Preferably, the light splitting unit is a triangular prism.

Preferably, the preset time is the time when the preset point on the object to be measured starts to enter a monochromatic light irradiation area and the preset point leaves the monochromatic light when the object to be measured moves with the transmission unit. The time difference between the time of light irradiation area.

Preferably, the step of acquiring the pictures of the plurality of objects to be measured, and extracting the pictures of the objects to be measured under the same color light from the plurality of pictures includes: acquiring the first monochromatic light when the camera unit enters the object to be measured The multiple pictures of the surface of the object to be measured are collected from the irradiation area to the time the last monochromatic light irradiation area is left; the multiple pictures are divided according to the irradiation area of different colors to obtain the object to be measured under the irradiation of each color light The segmented picture; extracting the picture information in the illuminated area of each color light.

Preferably, the step of dividing the plurality of pictures according to irradiation areas of different colors includes: acquiring any picture, using an image recognition method to identify areas irradiated by different colors of light in the picture; and dividing the pictures according to the irradiation areas of color light.

Preferably, the step of integrating the pictures of the object to be measured under the same color light, which are extracted from multiple pictures, includes: obtaining segmented pictures of the object to be measured under the same color light from the multiple pictures; using the images in the segmented pictures The image recognition method recognizes the content of the segmented pictures and labels them according to preset rules; Integrate the divided pictures according to the labels.

Preferably, the step further includes: performing sharpening processing on the integrated segmented image to enhance the characteristic information of the image.

The second aspect of the present application provides an object detection system based on monochromatic light. The system includes: a light source for emitting polychromatic light; and a light splitting unit for decomposing the polychromatic light emitted by the light source into monochromatic light. The unit decomposes the incident light of the light source into monochromatic light of different colors; the camera unit is used to collect pictures of the object to be measured. When the object to be measured moves with the transmission unit, the area is illuminated by the monochromatic light of different colors. The camera unit collects pictures of the object to be measured every preset time to obtain multiple pictures of the object to be measured; the processor is used to execute computer program instructions; the memory is used to store computer program instructions, the computer program instructions are The processor runs and executes the following steps: obtain the pictures of the multiple objects to be measured, extract the pictures of the objects to be measured under the same color light from the multiple pictures; integrate the images to be measured extracted from the multiple pictures The picture of the object illuminated by the same color light; output the integrated picture for object detection.

The object detection method of the present invention is based on monochromatic light. The beam splitting unit acquires monochromatic light of different colors. The imaging unit collects the image formed by the reflected light of the monochromatic light irradiated on the object to be measured. The images are sorted, and finally the image of the object to be measured under monochromatic light is output. By using the method, the pictures of the object to be measured under different monochromatic lights can be obtained conveniently and quickly, and the pictures can be used for object detection.

1: Transmission unit

2: light source

3: Spectroscopic unit

4: camera unit

5: Object to be measured

6: Computer device

10: Pipeline system

20: memory

30: processor

40: computer program

FIG. 1 is a schematic diagram of the application environment architecture of the monochromatic light detection method provided by Embodiment 1 of the present invention.

Fig. 2 is a schematic diagram of a preferred embodiment of the computer device of the present invention.

Fig. 3 is a schematic diagram of the surface illumination of the object to be measured according to the second embodiment of the present invention.

Fig. 4 is a flow chart of the monochromatic light detection method provided by the second embodiment of the present invention.

In order to be able to understand the above-mentioned objectives, features and advantages of the present invention more clearly, the present invention will be described in detail below with reference to the drawings and specific embodiments. It should be noted that the embodiments of the application and the features in the embodiments can be combined with each other if there is no conflict.

In the following description, many specific details are explained in order to fully understand the present invention. The described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the technical field of the present invention. The terms used in the description of the present invention herein are only for the purpose of describing specific embodiments, and are not intended to limit the present invention.

Example one

Referring to FIG. 1, it is a schematic diagram of the application environment architecture of the monochromatic light detection method provided by Embodiment 1 of the present invention.

In this embodiment, the monochromatic light detection method is applied to the pipeline system 10. The pipeline system includes a transmission unit 1, a light source 2, a light splitting unit 3, and a camera unit 4. As shown in the figure, the transmission unit 1 has an object 5 to be measured, and the camera unit 4 is located above the pipeline. The shooting angle of view is based on the area where the object 5 to be tested can be fully photographed in the irradiation area of different monochromatic light, the light source 2 is The light splitting unit 3 is above the object 5 to be measured. The light splitting unit 3 is located below the light source 2 and above the object 5 to be measured. The camera unit 4 and the computer device 6 establish a communication connection through the network. The network can be a wired network or a wireless network, such as radio, wireless fidelity (WIFI), cellular, satellite, broadcast, etc.

The light source 2 includes, but is not limited to, incandescent lamps, LED lamps and the like.

The light splitting unit 3 may include a prism, a light splitter, and the like. The light splitting unit 3 receives the incident light from the light source and splits the incident light into monochromatic light of different colors.

In one embodiment of the present invention, the light splitting unit is a triangular prism, the light source is an LED lamp, and the triangular prism receives the light from the LED lamp and splits the light into red, orange, yellow, green, cyan, blue, and purple. Seven monochromatic lights.

The camera unit 4 may be a camera with a shooting function, including but not limited to a camera, a camera, and the like. When the object to be measured moves with the transmission unit and the area is illuminated by the monochromatic light of different colors, the camera unit collects pictures of the object to be measured every predetermined time to obtain multiple pictures of the object to be measured.

The preset time is the time elapsed from the beginning of the irradiation of a single monochromatic light to the complete irradiation of the object to be measured as the object to be measured moves on the conveying unit.

For example, Figure 3 is a schematic diagram of the surface illumination of the object to be tested provided in the second embodiment of the present invention. The monochromatic light irradiation area that the object to be tested 5 passes through is purple, and the time when the object 5 to be tested is ready to enter the purple light irradiation area Is t ₀ , and the irradiated area of the violet light is t ₁ , then the preset time is: T = t ₁ - t ₀

And the different color light irradiation ranges are equal, the camera unit obtains pictures of the object to be measured every time T, and pictures of the object to be measured under different monochromatic light can be obtained.

In yet another embodiment of the present invention, the position of the beam splitting unit can be adjusted. By adjusting the distance between the beam splitting unit and the light source, a high-resolution image of the object to be measured under different monochromatic light can be obtained. sheet.

The computer device 6 may be an electronic device installed with software based on monochromatic light detection. As shown in FIG. 2, the computer device 6 includes a memory 20, a processor 30, and is stored in the memory 20 and can be stored in The computer program 40 running on the processor 30. The computer program is used to perform the functions described below.

Obtain the multiple pictures of the object to be measured, and extract the pictures of the object to be measured under the same color light from the multiple pictures.

In one embodiment of the present invention, the step of acquiring the pictures of the multiple objects to be measured, and extracting the pictures of the objects to be measured under the same color light from the multiple pictures may include: acquiring the camera unit when the object to be measured enters The multiple pictures of the surface of the object to be measured are collected from the first monochromatic light irradiation area to the time from the last monochromatic light irradiation area; the multiple pictures are divided according to the irradiation area of different colors to obtain each color The segmented picture of the object to be measured under light irradiation; extracting picture information in the area irradiated by each color light.

The step of dividing the plurality of pictures according to the irradiation area of different colors may include: obtaining any picture, using an image recognition method to identify the area irradiated by the different colors of light in the picture; dividing the picture according to the irradiation area of the color light.

The image recognition method includes, but is not limited to, an image recognition method based on neural network, an image recognition method based on wavelet moments, etc. The image recognition method is an existing technology and will not be repeated here.

For example, in conjunction with Figures 1 and 3, the camera unit 4 collects 8 pictures of the object to be measured from entering the monochromatic light irradiation area to completely located in the monochromatic light irradiation area, and the camera unit 4 will collect them. 8 pictures are sent to the computer device 6, the computer device 6 obtains the picture, and uses the neural network-based image recognition method to recognize the picture, and recognize the red light area in the picture Domain, the area illuminated by orange light, the area illuminated by yellow light, the area illuminated by green light, the area illuminated by cyan light, the area illuminated by blue light, and the area illuminated by purple light. By using the image recognition method to recognize multiple pictures, it is possible to obtain segmented pictures of the object to be measured that are segmented according to the illumination conditions of different colors of light.

Integrate the pictures of the object to be tested extracted from multiple pictures under the same color light.

In one embodiment of the present invention, the step of integrating the pictures of the object to be tested extracted from multiple pictures under the same color light may include: obtaining segmented pictures of the object to be tested under the same color light from the multiple pictures; In the segmented pictures, an image recognition method is used to identify the content of the segmented pictures and label them according to a preset rule; the segmented pictures are integrated according to the label.

The preset rule may be to divide the picture of the object to be measured according to the width of the light splitting area, and then according to the divided area, the object to be measured is from left to right, from right to left, from top to bottom, and from bottom to top. Numbering.

In another embodiment of the present invention, the step further includes: performing sharpening processing on the integrated segmented image to enhance the characteristic information of the image.

For example, the computer device 6 obtains a segmented image of the object to be measured under the same color light, recognizes the segmented image using an image recognition method based on neural network, and recognizes that the image is located on the object to be measured. The identified parts of the object to be measured are labeled in the order of the object to be measured from left to right, and the segmented images are integrated according to the label to obtain pictures of the object to be measured under different color lights. The image is sharpened using an image enhancement method to remove redundant information in the image, and to enhance the state information of the object under test in the image under different colors. The image enhancement method includes Laplacian operation Meta image enhancement method, bar graph equalization enhancement method.

Output the integrated picture for object detection.

In an embodiment of the present invention, the acquired image of the object 5 under different colors Like output by the computer device 6.

In other embodiments of the present invention, the image of the object 5 under different colors can also be transmitted via the network to other user terminals for output. The user terminals include but are not limited to smart phones, tablet computers, Laptops, etc.

The computer device 6 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. Those skilled in the art can understand that the schematic diagram is only an example of the computer device 6 and does not constitute a limitation on the computer device 6. It may include more or less components than those shown in the figure, or a combination of certain components, or different ones. Components, for example, the computer device 6 may also include input and output devices, network access devices, buses, and so on.

The so-called processor 30 may be a central processing unit (Central Processing Unit, CPU), other general-purpose processors, digital signal processors (Digital Signal Processors, DSP), and dedicated integrated circuits (Application Specific Integrated Circuits, ASICs). , Ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor 30 can also be any conventional processor, etc. The processor 30 is the control center of the computer device 6, which uses various interfaces and lines to connect the entire computer device 6 Various parts.

The memory 20 can be used to store the computer programs 40 and/or modules/units, and the processor 30 runs or executes the computer programs and/or modules/units stored in the memory 20, And call the data stored in the memory 20 to realize various functions of the computer device 6. The memory 20 may mainly include a storage program area and a storage data area, where the storage program area can store an operating system, an application program (such as a sound playback function, an image playback function, etc.) required by at least one function, etc.; The area can store data (such as audio data, phone book, etc.) created based on the use of the computer device 6. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, and a Smart Media Card (SMC), Secure Digital (SD) card, flash memory card (Flash Card), at least one magnetic disk memory device, flash memory device, or other volatile solid-state memory device.

If the integrated module/unit of the computer device 6 is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiments and methods, and can also be completed by computer programs instructing related hardware, and the computer programs can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of each method embodiment described above. Wherein, the computer program includes computer program code, and the computer program code may be in the form of original program code, object code, executable file, or some intermediate forms. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read- Only Memory), Random Access Memory (RAM, Random Access Memory), electric carrier signal, telecommunications signal, and software distribution media. It should be noted that the content contained in the computer-readable medium can be appropriately added or deleted according to the requirements of the legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to the legislation and patent practice, the computer-readable medium Does not include electrical carrier signals and telecommunication signals.

Example two

Please refer to FIG. 4, which is a flowchart of the monochromatic light detection method according to the second embodiment of the present invention. According to different needs, the order of the steps in the flowchart can be changed, and some steps can be omitted.

Step S1: Decompose the incident light of the light source into monochromatic light of different colors by the light splitting unit.

In one embodiment of the present invention, the light splitting unit is a triangular prism, the light source is an LED lamp, and the triangular prism receives the light from the LED lamp and splits the light into red, orange, yellow, green, cyan, blue, and purple. Seven monochromatic lights.

Step S2. When the object to be measured moves with the transmission unit, using the single When the color light illuminates the area, the camera unit collects pictures of the object to be measured every preset time to obtain multiple pictures of the object to be measured.

The preset time is the time elapsed from the beginning of the irradiation of a single monochromatic light to the complete irradiation of the object to be measured as the object to be measured moves on the conveying unit.

For example, Figure 3 is a schematic diagram of the surface illumination of the object to be tested provided in the second embodiment of the present invention. The monochromatic light irradiation area that the object to be tested 5 passes through is purple, and the time when the object 5 to be tested is ready to enter the purple light irradiation area Is t ₀ , and the irradiated area of the violet light is t ₁ , then the preset time is: T = t ₁ - t ₀

And the different color light irradiation ranges are equal, the camera unit obtains pictures of the object to be measured every time T, and pictures of the object to be measured under different monochromatic light can be obtained.

In another embodiment of the present invention, the position of the light splitting unit can be adjusted. By adjusting the distance between the light splitting unit and the light source, images of the object to be measured with different definitions under different monochromatic lights can be obtained.

Step S3: The computer device obtains the multiple pictures of the object to be measured, and extracts the pictures of the object to be measured under the same color light from the multiple pictures.

In an embodiment of the present invention, acquiring multiple pictures of the object to be measured, and extracting the state of the object to be measured under the same color light from the multiple pictures may include: acquiring the object to be measured from entering the first order The multiple pictures of the surface of the object to be measured collected by the camera unit during the time from the color light irradiation area to the time when it leaves the last monochromatic light irradiation area; the multiple pictures are divided according to the irradiation area of different colors to obtain the same color light irradiation to be measured The segmented picture of the object; extract the picture information in the same color light irradiation area.

The step of dividing the multiple pictures according to the irradiation areas of different colors may include: Obtain any picture, use the image recognition method to identify the picture, and identify the difference in the picture The area illuminated by the colored light; the picture is divided according to the area illuminated by the same colored light.

The image recognition method includes, but is not limited to, an image recognition method based on neural network, an image recognition method based on wavelet moments, etc. The image recognition method is an existing technology and will not be repeated here.

For example, FIG. 3 is a schematic diagram of the surface illumination of the object to be measured provided in the second embodiment of the present invention. The camera unit 4 collects multiple pictures from the object to be measured from entering the monochromatic light irradiation area to completely located in the monochromatic light irradiation area. The camera unit 4 sends the collected pictures to the computer device 6, and the computer device 6 obtains them. Go to the picture, use the neural network-based image recognition method to identify the picture, and identify the area illuminated by red light, the area illuminated by orange light, the area illuminated by yellow light, and the area illuminated by green light. Area, the area illuminated by cyan light, the area illuminated by blue light, and the area illuminated by purple light. Use the image recognition method to identify multiple images, and you can get segmented images of the object to be measured according to the illumination of different colors .

Step S4: The computer device integrates the pictures of the object to be measured extracted from the multiple pictures under the same color light.

In one embodiment of the present invention, the step of integrating the pictures of the object to be measured under the same color light, which are extracted from multiple pictures, may include: obtaining segmented pictures of the object to be measured under the same color light; in the segmented pictures Using an image recognition method to identify the content of the segmented pictures and label them according to preset rules; and integrate the segmented pictures according to the label.

The preset rule may be to divide the picture of the object to be measured according to the width of the light splitting area, and then according to the divided area, the object to be measured is from left to right, from right to left, from top to bottom, and from bottom to top. Numbering.

In yet another embodiment of the present invention, the step further includes: comparing the integrated segmentation map The image is sharpened to enhance the characteristic information of the image.

For example, the computer device 6 obtains a segmented image of the object to be measured under the same color light, recognizes the segmented image using an image recognition method based on neural network, and recognizes that the image is located on the object to be measured. The identified parts of the object to be measured are labeled in the order of the object to be measured from left to right, and the segmented images are integrated according to the label to obtain pictures of the object to be measured under different color lights. The image is sharpened using an image enhancement method to remove redundant information in the image, and to enhance the state information of the object under test in the image under different colors. The image enhancement method includes Laplacian operation Meta image enhancement method, bar graph equalization enhancement method.

Step S5: The computer device outputs the integrated picture for object detection.

In an embodiment of the present invention, the acquired images of the object 5 under different colors of light are output by the computer device 6.

In other embodiments of the present invention, the image of the object 5 under different colors can also be transmitted via the network to other user terminals for output. The user terminals include but are not limited to smart phones, tablet computers, Laptops, etc.

The above-mentioned Figure 2 describes in detail the monochromatic light detection method of the present invention. In conjunction with Figure 4, the functional modules of the software device for realizing the monochromatic light detection method and the hardware device for realizing the monochromatic light detection method The architecture is introduced.

It should be understood that the described embodiments are for illustrative purposes only, and are not limited by this structure in the scope of the patent application.

For those skilled in the art, it is obvious that the present invention is not limited to the details of the foregoing exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description, and therefore it is intended to fall within the claims. All changes within the meaning and scope of the equivalent elements are included in the present invention. Any reference signs in the claims should not be regarded as limiting the involved claims. In addition, it is obvious that the word "including" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or electronic devices stated in the claims can also be implemented by the same unit or electronic device by software or hardware. The first and second words are used to indicate names, but do not indicate any specific order.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be Modifications or equivalent replacements are made without departing from the spirit and scope of the technical solution of the present invention.

Claims (8)

An object detection method based on monochromatic light. The method includes: splitting the incident light of the light source into monochromatic light of different colors by a light splitting unit; when the object to be measured moves with the transmission unit, by the single When the color light is irradiated in the area, the camera unit collects pictures of the object to be tested every preset time to obtain multiple pictures of the object to be tested; the computer device captures the camera unit when the object to be tested enters the first monochromatic light irradiation area until it leaves Multiple pictures of the surface of the object to be measured collected within the last single-color light irradiation area; the computer device divides the multiple pictures according to the irradiation area of different colors of light to obtain a segmented picture of the object to be measured under each color light ; The computer device extracts the picture information in each color light irradiation area; the computer device integrates the pictures of the object to be tested extracted from multiple pictures under the same color light, and sharpens the integrated pictures to remove the pictures The redundant information in the image enhancement method is used to enhance the state information of the object under test in the integrated picture; the computer device outputs the integrated picture for object detection. The object detection method based on monochromatic light according to claim 1, wherein the light splitting unit is a triangular prism. The method for detecting an object based on monochromatic light according to claim 1, wherein the preset time is when the object to be measured moves with the conveying unit, a predetermined point on the object to be measured starts to enter a monochromatic light The time difference between the time of the irradiation area and the time when the predetermined point leaves the monochromatic light irradiation area. The object detection method based on monochromatic light according to claim 1, wherein the step of dividing the plurality of pictures according to the irradiation area of different color lights includes: obtaining any picture, and using an image recognition method to identify the The area illuminated by different colors in the picture; The picture is divided according to the color light irradiation area. The object detection method based on monochromatic light according to claim 1, wherein the step of integrating the pictures of the object to be measured extracted from multiple pictures under the same color light includes: obtaining the same color light from the multiple pictures Illuminate the segmented picture of the object to be measured; use an image recognition method in the segmented picture to identify the content of the segmented picture and label it according to a preset rule; integrate the segmented picture according to the label. The object detection method based on monochromatic light according to claim 5, wherein the step further includes: sharpening the integrated segmented image to enhance the feature information of the image. An object detection system based on monochromatic light. The system includes: a light source for emitting polychromatic light; a light splitting unit for decomposing the polychromatic light emitted by the light source into monochromatic light, and the light splitting unit decomposes the incident light of the light source Monochromatic light of different colors; camera unit, used to collect pictures of the object to be measured, when the object to be measured moves with the transmission unit, and the area is illuminated by the monochromatic light of different colors, the camera unit presets every other Time collection of pictures of the object to be measured to obtain multiple pictures of the object to be measured; processor for executing computer program instructions; memory for storing computer program instructions, which are run and executed by the processor The steps are as follows: Obtain multiple pictures of the surface of the object to be measured collected from the time the object to be measured enters the first monochromatic light irradiation area to when it leaves the last monochromatic light irradiation area; according to the irradiation area of different colors Dividing the multiple pictures to obtain a divided picture of the object to be measured illuminated by each color light; extracting the picture information in the area illuminated by each color light; Integrate the pictures of the object to be tested extracted from multiple pictures under the same color light, and sharpen the integrated picture to remove redundant information in the picture, and use image enhancement methods to enhance the integrated picture The status information of the object to be measured under the color light; output the integrated picture for object detection. The object detection system based on monochromatic light according to claim 7, wherein the step of integrating the pictures of the object to be measured extracted from multiple pictures under the same color light includes: obtaining the same color light from the multiple pictures Segmentation pictures of the object to be measured; using image recognition methods in the segmentation pictures to identify the content of the segmentation pictures and label them according to preset rules; and integrate the segmentation pictures according to the label.

Images