Image detection method and device, equipment and storage medium
By using multiple grayscale feature values and statistical index information in image detection, the problem of indistinguishability from background in periodic images is solved, and more accurate defect detection and reduction of error detection rate is achieved.
CN119648608APending Publication Date: 2025-03-18SKYVERSE TECH CO LTD
0 Cites 0 Cited by
Patent Information
- Application Number
- CN202311204893.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-09-18
- Publication Date
- 2025-03-18
AI Technical Summary
Technical Problem
In periodic images, defects and background mixing are difficult to distinguish, resulting in more false detections in traditional image detection methods.
Method used
By obtaining a number of grayscale characteristic values based on the grayscale value of each pixel in the image to be tested and the grayscale value of the neighboring pixels, the pixel distribution information is counted, and statistical index information is obtained, and abnormal points are determined according to preset conditions to identify defect areas.
Benefits of technology
The accuracy of image detection is improved, the error detection rate is reduced, and defect areas in periodic images can be more effectively identified.
✦ Generated by Eureka AI based on patent content.
Abstract
The invention discloses an image detection method and device, equipment and a storage medium, and the method comprises the steps: obtaining a plurality of gray feature values of pixels according to the gray values of the pixels and neighborhoods of the pixels in a to-be-detected image; counting gray feature values of pixels in the to-be-detected image, and obtaining pixel distribution information indicating the number of pixels of different numerical value types in the to-be-detected image; the pixels with different numerical value types refer to at least one pixel with different gray feature values; processing the pixel distribution information to obtain statistical index information containing statistical indexes of each type of pixels of the to-be-detected image; and according to the statistical index information, determining the pixel with the corresponding statistical index meeting a preset condition as an abnormal point, and further identifying a defect area where the abnormal point is located. According to the scheme, the abnormal points are screened based on whether the statistical indexes of the pixels of different numerical value types in the to-be-detected image meet the preset conditions or not, the number characteristics of the non-abnormal points and the abnormal points in the periodic image are met, and the accuracy is high when the defects of the periodic image are detected.
Need to check novelty before this filing date? Find Prior Art