Defect detection in flat surface products using log-Gabor filters
International Journal of Hybrid Intelligent Systems
Fabric defect detection based on computer vision
AICI'11 Proceedings of the Third international conference on Artificial intelligence and computational intelligence - Volume Part III
Review: Pulse coupled neural networks and its applications
Expert Systems with Applications: An International Journal
An Iterative Thresholding Segmentation Model Using a Modified Pulse Coupled Neural Network
Neural Processing Letters
Hi-index | 0.00 |
This paper describes an adaptive image-segmentation method based on a simplified pulse-coupled neural network (PCNN) for detecting fabric defects. Defect segmentation has been a focal point in fabric inspection research, and it remains challenging because it detects delicate features of defects complicated by variations in weave textures and changes in environmental factors (e.g., illumination, noise). A new parameter called the deviation of the contrast (DOC) was introduced to describe the contrast difference in row and column between the analyzed image and a defect-free image of the same fabric. The DOC essentially weakens the influence of the weave texture and the illumination. The simplification of PCNN reduces the number of the network’s parameters by utilizing the local and global DOC information for the parameter selections. The validation tests on the developed algorithms were performed with fabric images captured by a line-scan camera on an inspection machine, and with images from TILDA’s Textile Texture Database (http://lmb.informatik.uni-freiburg.de/research/dfg-texture/tilda) as well.