A Deep Learning Method for Printing Defect Detection

Abstract

In the actual printing process, the quality of printed products is often affected by many factors such as printing technology, equipment and environment. In some cases, it may cause printing defects in printed product. Product with printing defect need to be removed to ensure product quality. This paper proposes a deep learning method for printing defect detection. This method can classify printing defects into five categories. The experimental results show that the accuracy, precision and recall rate of the proposed printing defect detection method are all above 96%.