Fisheye lens stain detection method

Abstract

According to the fish-eye lens stain detection method, a detection device, a fish-eye lens fixing device and a shooting module are included; the detection device comprises a picture reading module, the picture reading module is in data connection with a binarization processing module, the binarization processing module is in data connection with a circle center and radius calculation module, and the circle center and radius calculation module is in data connection with an image preprocessing module. According to the fish-eye lens stain detection method, a binarization threshold value is set, a dark boundary is extracted, a circle is fitted through boundary coordinate points, an area in the circle is identified and detected, a center area and a frontier detection area are divided with the circle center as the center and the radius as the edge (judgment standards are different, such as contrast, etc. And detecting in the pair area to judge whether stains exist or not.

Description

Technical Field

[0001] The present invention relates to the technical field of fisheye lens detection methods, and in particular to a fisheye lens stain detection method. Background Art

[0002] Due to the particularity of the fisheye lens, if the entire screen is detected, misjudgment may occur. If the position is fixed, the deviation of each camera will cause different dark corners. Therefore, the present invention proposes a fisheye lens stain detection method that can quickly solve the problem. Summary of the invention

[0003] The purpose of the present invention is to overcome the deficiencies in the prior art and provide a fisheye lens stain detection method.

[0004] The objective of the present invention is achieved through the following technical solutions:

[0005] A fisheye lens stain detection method comprises: a detection device, a fisheye lens fixing device and a shooting module; the detection device comprises a picture reading module, the picture reading module is data-connected with a binarization processing module, the binarization processing module is data-connected with a circle center and radius calculation module, the circle center and radius calculation module is data-connected with an image preprocessing module, the image preprocessing module is data-connected with a row and column mean enumeration module, the row and column mean enumeration module is data-connected with a comparison enumeration module; the comparison enumeration module is data-connected with a region recognition and threshold extraction module, the region recognition and threshold extraction module is data-connected with a judgment module, the judgment module is data-connected with a contrast threshold judgment module, the contrast threshold judgment module is data-connected with an output result module and a bad point connected area recognition module respectively, the output result module is data-connected with an end program module, the bad point connected area recognition module is data-connected with the output result module, the bad point connected area recognition module is data-connected with a test result NG module, the test result NG module is data-connected with the end program module; the shooting module is data-connected with the detection device.

[0006] In one of the embodiments, the binarization processing module extracts the dark boundary by setting a binarization threshold, and the center and radius calculation module fits a circle according to the edge of the image and obtains the center and radius.

[0007] In one of the embodiments, the image preprocessing module performs shading calibration on the received image, and the row and column mean enumeration module uses the row and column mean method to quickly calculate the contrast between each pixel and its background.

[0008] In one embodiment, the comparison and listing module will compare the data listed by the column mean listing module with a certain threshold, and list the contrast greater than the threshold, while the region identification and threshold extraction module will perform 8-connected region identification on all target points and list the data greater than the threshold.

[0009] In one embodiment, the judgment module judges whether the average contrast of a whole stain is greater than a threshold, and judges whether the number of stains in a whole group is greater than a threshold, and the contrast threshold judgment module judges whether the contrast of the whole group is greater than a threshold.

[0010] In one embodiment, if the judgment result of the contrast threshold judgment module is no, the module directly enters the output result module, and the output result module automatically triggers the program end module after outputting the result, thereby directly ending the program.

[0011] In one of the embodiments, when the judgment result of the contrast threshold judgment module is yes, it will enter the bad pixel connected area identification module, and the bad pixel connected area identification module will perform 8 connected area identification on all bad pixels. If the identified result is greater than a certain threshold, it will enter the test result NG module.

[0012] In one of the embodiments, the test result NG module displays on the detection device that the detection does not meet expectations, and directly enters the end program module to end the program.

[0013] In one embodiment, if the result determined by the bad pixel connected area identification module is smaller than the modulus threshold, the module directly enters the result output module and outputs the obtained data on the detection device.

[0014] In one of the embodiments, the fisheye lens fixing device can fix the fisheye lens that needs to be inspected.

[0015] Compared with the prior art, the present invention has at least the following advantages:

[0016] The fisheye lens stain detection method of the present invention extracts the dark boundary by setting a binary threshold, fits a circle through the boundary coordinate points, identifies and detects the area within the circle, divides the central area and the border inspection area (the judgment criteria are different, such as contrast, etc.) with the center of the circle as the center and the radius as the edge, and detects in the area to determine whether there is a stain. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 The figure is a schematic diagram of the detection process of the fisheye lens stain detection method of the present invention. DETAILED DESCRIPTION

[0019] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. The preferred embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thoroughly understood.

[0020] In the description of the present application, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0021] Unless otherwise clearly stipulated and limited, terms such as "installed", "connected", "connected", "fixed", etc. should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integrated connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium; it can be the internal connection of two elements or the interaction relationship between two elements.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0023] like Figure 1As shown, a fisheye lens stain detection method includes: a detection device, a fisheye lens fixing device and a shooting module; the detection device includes a picture reading module, the picture reading module is data-connected with a binarization processing module, the binarization processing module is data-connected with a circle center and radius calculation module, the circle center and radius calculation module is data-connected with an image preprocessing module, the image preprocessing module is data-connected with a row and column mean enumeration module, the row and column mean enumeration module is data-connected with a comparison enumeration module; the comparison enumeration module is data-connected with a region recognition and threshold extraction module, the region recognition and threshold extraction module is data-connected with a judgment module, the judgment module is data-connected with a contrast threshold judgment module, the contrast threshold judgment module is data-connected with an output result module and a bad point connected area recognition module, the output result module is data-connected with an end program module, the bad point connected area recognition module is data-connected with the output result module, the bad point connected area recognition module is data-connected with a test result NG module, and the test result NG module is data-connected with the end program module; the shooting module is data-connected with the detection device.

[0024] In one of the embodiments, the binarization processing module extracts the dark boundary by setting a binarization threshold, and the center and radius calculation module fits a circle according to the edge of the image and obtains the center and radius.

[0025] In one of the embodiments, the image preprocessing module performs shading calibration on the received image, and the row and column mean enumeration module uses the row and column mean method to quickly calculate the contrast between each pixel and its background.

[0026] In one embodiment, the comparison and listing module compares the data listed by the column mean listing module with a certain threshold, and lists the contrast greater than the threshold, while the region recognition and threshold extraction module performs 8-connected region recognition on all target points and lists the data greater than the threshold.

[0027] In one embodiment, the judgment module judges whether the average contrast of a whole block of stains is greater than a certain threshold, and judges whether the number of stains in a whole group is greater than a certain threshold, and the contrast threshold judgment module judges whether the contrast of the whole group is greater than a certain threshold.

[0028] In one embodiment, if the judgment result of the contrast threshold judgment module is no, the module directly enters the output result module, and after the output result module outputs the result, it automatically triggers the program end module, thereby directly ending the program.

[0029] In one embodiment, when the judgment result of the contrast threshold judgment module is yes, it will enter the bad pixel connected area identification module, and the bad pixel connected area identification module will perform 8 connected area identification on all bad pixels. If the identified result is greater than a certain threshold, it will enter the test result NG module.

[0030] In one of the embodiments, the test result NG module displays on the detection device that the detection does not meet expectations, and directly enters the end program module to end the program.

[0031] In one embodiment, if the result determined by the bad pixel connected area identification module is smaller than the modulus threshold, the module directly enters the result output module and outputs the obtained data on the detection device.

[0032] In one of the embodiments, the fisheye lens fixing device can fix the fisheye lens that needs to be inspected.

[0033] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A fisheye lens stain detection method, characterized in that: include: Detection device, fisheye lens fixing device and shooting module; The detection device comprises a picture reading module, the picture reading module is data-connected to a binarization processing module, the binarization processing module is data-connected to a circle center and radius calculation module, the circle center and radius calculation module is data-connected to an image preprocessing module, the image preprocessing module is data-connected to a row and column mean enumeration module, and the row and column mean enumeration module is data-connected to a comparison enumeration module; The comparison enumeration module is data-connected with a region identification and threshold extraction module, the region identification and threshold extraction module is data-connected with a judgment module, the judgment module is data-connected with a contrast threshold judgment module, the contrast threshold judgment module is data-connected with an output result module and a bad pixel connected region identification module, the output result module is data-connected with an end program module, the bad pixel connected region identification module is data-connected with the output result module, the bad pixel connected region identification module is data-connected with a test result NG module, and the test result NG module is data-connected with the end program module; The shooting module is data connected to the detection device.

2. A fisheye lens stain detection method according to claim 1, characterized in that: The binarization processing module extracts the dark boundary by setting a binarization threshold, and the center and radius calculation module fits a circle according to the edge of the image and obtains the center and radius.

3. A fisheye lens stain detection method according to claim 1, characterized in that: The image preprocessing module will perform shading calibration on the received image, and the row and column mean enumeration module will use the row and column mean method to quickly calculate the contrast between each pixel and its background.

4. The method for detecting stains in a fisheye lens according to claim 1, characterized in that: The comparison enumeration module will compare the data enumerated by the column mean enumeration module with a certain threshold, and enumerate the contrast values ​​greater than a certain threshold, while the region recognition and threshold extraction module will perform 8-connected region recognition on all target points and enumerate the data greater than a certain threshold.

5. The method for detecting stains in a fisheye lens according to claim 1, characterized in that: The judgment module judges whether the average contrast of a whole block of stains is greater than a certain threshold, and judges whether the number of stains in a whole group is greater than a certain threshold, and the contrast threshold judgment module judges whether the contrast of the whole group is greater than a certain threshold.

6. The method for detecting stains in a fisheye lens according to claim 1, characterized in that: If the judgment result of the contrast threshold judgment module is no, the output result module is directly entered. After the output result module outputs the result, it will automatically trigger the end program module, thereby directly ending the program.

7. The method for detecting stains in a fisheye lens according to claim 1, characterized in that: When the judgment result of the contrast threshold judgment module is yes, it will enter the bad pixel connected area identification module, and the bad pixel connected area identification module will perform 8 connected area identification on all bad pixels. If the identified result is greater than a certain threshold, it will enter the test result NG module.

8. The method for detecting stains in a fisheye lens according to claim 1, characterized in that: The test result NG module displays on the detection device that the detection does not meet expectations, and directly enters the end program module to end the program.

9. The method for detecting stains in a fisheye lens according to claim 1, characterized in that: If the result determined by the bad pixel connected area identification module is less than the modulus threshold, the module directly enters the output result module and outputs the obtained data on the detection device.

10. The method for detecting stains in a fisheye lens according to claim 1, characterized in that: The fisheye lens fixing device can fix the fisheye lens that needs to be tested.

Images