Open AccessMulti-type web image text detection based on the improved EAST algorithm
Author(s) -
Yuanji Xiang,
Fei Luo
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1544/1/012115
Subject(s) - computer science , offset (computer science) , image (mathematics) , pixel , artificial intelligence , point (geometry) , detector , algorithm , field (mathematics) , edge detection , text detection , function (biology) , enhanced data rates for gsm evolution , computer vision , image processing , mathematics , telecommunications , geometry , evolutionary biology , pure mathematics , biology , programming language
Web image character recognition has important application value in the commercial field and text detection is the basis of extracting this text information. Among many text detection algorithms, EAST (efficient and accurate scene text detector) algorithm has a good performance in natural scenes, but it is ordinary in web pictures. Based on this, aiming at the problem that the number of channels in the QUAD output layer of EAST algorithm is redundant, which leads to the low accuracy of web image text detection, it is modified as the distance from the point marked as a positive sample to the four vertices of the text box where it is located instead of the coordinate offset to the vertices. The improvement reduces from the original 8 channels to 4 channels, which restricts the optimization direction of the model, and then by setting a new loss function in order to improve the loss value of the edge area of the text box and the pixels in the image that are difficult to detect, the model is more suitable for the text detection of the web image. The experimental results show that the improved EAST algorithm significantly improves the accuracy of text detection in web images.