Defect Detection in Tire X-Ray Images Using Weighted Texture Dissimilarity

Algorithm 1

The proposed detection algorithm.

Input: Inspected image

Output: Binary image with white pixels representing the defective region

(1) Extract LKR features of the inspected image by (2);

(2) for each pixel ,   do

(3)   Calculate the dissimilarity of and its neighbors , by (5);

(4)   Calculate the weight via (7);

(5)   Aggregate all , to generate the anomaly value by (4);

(6) end for

(7) Locate the defects by the thresholding function equation (11).