Assessment of Intermittent Leather based on Image Score Pattern

Abstract

The process of intermittent leather inspection is being predominantly carried out with the support of human intervention based on homogenous distribution of colors. However, results of the observations between one experts to another expert may be different in opinion. Therefore, to emphasis some sort of supporting hand to the experts while taking decision, the authors have introduced to align intermitted leather images based on the Image Score Pattern algorithm. Which separates defect versus non-defect intermittent leather images from feature image datasets namely DGF, DLO, DGFLO and DLOGF consisting of 32 features generated from Gray Level Co-occurrence Matrix, Simple Linear Iterative Clustering and Minimum Spanning Tree Clustering from the training and testing datasets of about 1132 and 404 generated respectively. Gradient Boosting has implemented in finding the key feature among the Contrast, Dissimilarity, Homogeneity, Energy, Correlation and Angular Second Moment. The results of the classifier Support Vector Machine for these datasets confirms the accuracy of 84% for the proposed Image Score Pattern algorithm. The other performance measures such as Error Rate, Recall, False Positive Rate, Specificity, Precision and Prevalence  are also confirming that proposed method is performing in aligning of intermittent leather