Surface Defect Inspection in Images Using Statistical Patches Fusion and Deeply Learned Features

Yan Tao Eugene Chian,Jing Tian

doi:10.3390/ai2010002

Abstract

Defect detection in images is a challenging task due to the existence of tiny and noisy patterns on surface images. To tackle this challenge, a defect detection approach is proposed in this paper using statistical data fusion. First, the proposed approach breaks a large image that contains multiple separate defects into smaller overlapping patches to detect the existence of defects in each patch, using the conventional convolutional neural network approach. Then, a statistical data fusion approach is proposed to maintain the spatial coherence of cracks in the image and aggregate the information extracted from overlapping patches to enhance the overall performance and robustness of the system. The proposed approach is evaluated using three benchmark datasets to demonstrate its superior performance in terms of both individual patch inspection and the whole image inspection.

Highlights

The gist of the proposed approach is to break a large image that contains multiple separate defects into small overlapping patches to detect the existence of defect in each patch using the convolutional neural network classifier, and re-combines the patches back to form the final defect decision using a statistical data fusion approach
The proposed patch classifier is trained on 1405 Defect patches and 5445 Non-Defect patches, and is validated on 624 unseen Defect patches and 2312 unseen Non-Defect patches
The proposed patch classifier has achieved an accuracy of 0.923 and an area under Receiver operating characteristic (ROC) curve of 0.826, which is higher than the benchmark reference [23]

Summary

Introduction

Using Statistical Patches Fusion and Deeply Learned Features. Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Defect inspection using computer vision technology is an important task in various industries [1,2,3,4], including railroad defects on steel surfaces [5], concrete cracks [6], tunnel inspection [7]

Results

Discussion

Conclusion