Fabric defect detection based on improved local adaptive contrast method

In order to improve the fabric defect detection accuracy and detection effect, a background estimation method based on the most similar neighborhood patch was used to improve the detection rate. Firstly, the image was preprocessed by homomorphic filtering. Then, each pixel of the filtered image was taken as center point and window size of 11 pixel×39 pixel was taken as the central region. By calculation the similarity between the central region and the surrounding neighborhood to find out the neighborhood which was most similar to central region. So then, the purpose of background estimation was achieved. The background-difference principle was used to obtain the target image and the method of threshold segmentation and morphological was used in the image. Finally, the defection results were obtained. The experiment results show that the method is superior to the traditional detection method, not only can detection the defect image in complex background, but also has good detection results for fabric defect images under influence of external factors and different fabric weaves, the detection rate can reach 98%, and with high recognition rate, applicability and a certain degree of anti-interference. Copyright No content may be reproduced or abridged without authorization.