Steel defect detection is used to detect defects on the surface of the steel and to improve the quality of the steel surface. However, traditional image detection algorithms cannot meet the detection requirements because of small defect features and low contrast between background and features about steel surface defect datasets. A novel recognition algorithm for steel surface defects based on improved deep learning network models using feature visualization and quality evaluation is proposed in this paper. Firstly, the VGG19 is used to pre-train the steel surface defect classification task and the corresponding DVGG19 is established to extract the feature images in different layers from defects weight model. Secondly, the SSIM and decision tree are used to evaluate the feature image quality and adjust the parameters and structure of VGG19. On this basis, a new VSD network is obtained and used for the classification of steel surface defects. Comparing with ResNet and VGG19 methods, experiment results show that the proposed method markedly can improve the average accuracy of classification, and the model is able to converge quickly, which can be good for steel surface defect recognition using VSD network model of feature visualization and quality evaluation.
In order to explore the accurate image segmentation of fabric defects, we will introduce the visual attention mechanism of the wavelet domain to the dynamic detection of fabric defects. First of all, feature maps are formed by extracting simple features from a collection image. Secondly, feature maps by multi-layer wavelet decomposition are decomposed into a lot of feature sub-maps of the wavelet domain. On this basis, the center-surround operator among feature sub-maps of the wavelet domain is adopted to build the feature difference sub-maps, which are fused into feature saliency maps through fuse strategy. Finally, the defect interest areas are segmented based on the maximum between-cluster variance method in saliency maps, and the fabric defects through the region growing method are detected in the defect interest areas. Comparing with the wavelet transform algorithm, experimental results show that the proposed method is able to segment the defect information completely, and it has a strong ability to resist noise interference, which can improve the accuracy of defect detection.
A novel detection algorithm for strip steel defect image based on saliency map construction using Gaussian Pyramid decomposition is proposed in this paper. Firstly, the acquired gray image of strip steel is decomposed into strips steel sub-images with different resolution by Gaussian Pyramid. Secondly, the saliency map is constructed by the central-surround differences operation of strips steel sub-images and image fusion of difference sub-images. Finally, we respectively calculated mean values of maximum value in image rows and columns, in which small mean is chosen as the optimal threshold segmentation of strip image, and then to segment surface defects of steel strip. Experiment results show that the proposed method is valid for inhibition of the image background and can be realized complete segmentation and accurate detection for strip steel defect.
In this paper, we introduce visual attention mechanism from the human vision system to detect fabric defects, and propose the integrated computational model of top-down and bottom-up visual attention. Firstly, utilizing data driven of bottom-up visual attention generates the overall saliency map to pop out fabric defects. Secondly, using target feature driven (task driven) of top-down visual attention forms region of interest (ROI) of fabric defects. Finally, the fabric defects are segmented from ROI using the threshold. Experimental results show that compared with the traditional detection methods, the proposed algorithm can segment accurately common defects from fabric images and enhance detection rate, and it has strong universality for different fabric texture, which can provide the possibility for the realization of automatic fabric defect detection.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.