Natural scene text detection based on multiscale connectionist text proposal network

Abstract

The technique of recognising text in natural scene pictures is widely used in social production. For the existing identification methods, it is difficult to accurately identify in complex environments. The accuracy of the detection determines the efficiency of the identification. A text detection method based on Multiscale Connectionist Text Proposal Network is proposed. The Multiscale‐Region Proposal Network regresses and classifies the extracted region to obtain the final candidate region. Taking a large number of commodity image samples as a dataset, the multi‐scale joint text proposal network is used to detect and locate the text content area in the image. The experimental results show that the proposed algorithm improves the detection accuracy in complex environments.