AUTHOR=Wu Shilin , Wang Yan , Yang Huayu , Wang Pingfeng 

TITLE=Improved Faster R-CNN for the Detection Method of Industrial Control Logic Graph Recognition

JOURNAL=Frontiers in Bioengineering and Biotechnology

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2022.944944

DOI=10.3389/fbioe.2022.944944

ISSN=2296-4185

ABSTRACT=In the process of industrial control SAMA logic diagram commonly used in industrial process control system, there are some problems that the size of logic diagram elements is small, the shape is various, similar element recognition is easily confused and the detection accuracy is low. In this paper, the Faster R-CNN network has been improved. The original VGG16 network has been replaced by ResNet101 network and the residual value module was introduced to ensure the detailed features of the deep network. Then the industrial control logic diagram data set was analyzed to improve the anchors size ratio through K-Means clustering algorithm. The candidate box screening problem was optimized by improved the non-maximum suppression algorithm. The elements were distinguished via the combination of the candidate box location and the inherent text, which improved the recognition accuracy of similar elements. An experimental platform was build using Tensorflow framework based on Windows system and the improved method was compared with the original one by the control variable. The results showed that the performance of similar element recognition has been greatly enhanced through improved Faster R-CNN network.