Fabric Defect Detection Method Based on Local Statistical Features and Global Significance Analysis
A technology of statistical features and local statistics, applied in image analysis, calculation, image data processing and other directions, can solve problems such as poor fabric image detection effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0125] In the embodiment, images of common defects in the fabric image library are used for experiments, including yarn leakage, damage, loose weft, and skipping. Knot head, etc., the size of the image is 512×512, select some images such as Figure 1a-Figure 1f shown. In the embodiment, the value of P is 8, the value of R is 3, the value of m is 16, the value of c is 4, and the value of R j The value is 0.34×0.15, K is 20, c is -0.45, and local texture features and overall saliency analysis are used to generate a visual saliency map, such as Figure 2a-Figure 2f As shown, it can be seen from the figure that Figure 2a , Figure 2b and Figure 2e The effect of generating visual saliency map is poor, and there is a certain gap between the highlighted defect area and the actual defect; the visual saliency map is generated by using grayscale statistical features and overall saliency analysis, such as Figure 3a-Figure 3f As shown, it can be seen from the figure that Figure 3...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 