In this study, we present an application of neural network and image processing\ntechniques for detecting the defects of an internal micro-spray nozzle. The defect regions\nwere segmented by Canny edge detection, a randomized algorithm for detecting circles and\na circle inspection (CI) algorithm. The gray level co-occurrence matrix (GLCM) was\nfurther used to evaluate the texture features of the segmented region. These texture features\n(contrast, entropy, energy), color features (mean and variance of gray level) and geometric\nfeatures (distance variance, mean diameter and diameter ratio) were used in the\nclassification procedures. A back-propagation neural network classifier was employed to\ndetect the defects of micro-spray nozzles. The methodology presented herein effectively\nworks for detecting micro-spray nozzle defects to an accuracy of 90.71%.
Loading....