Chinese Text Spotter Exploiting Spatial Semantic Information in Scene Text Images
Authors:
- 15 September 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 204-208
Abstract
Chinese scene text spotting plays a significant role in computer vision applications as it involves extracting and interpreting Chinese information from scene images. However, existing methods often lack specialized designs for complex spatial semantic information in Chinese text images, leading to various degrees of false detections in Chinese scene text images. In this paper, we present SSTS, a novel Spatial Semantic Text Spotter for Chinese text image detection and recognition. SSTS utilizes a concise Transformer encoder and decoder architecture to effectively model spatial semantic information and predict the spatial orientation of Chinese text, reducing the likelihood of false detections caused by different combinations of Chinese characters in various orientations. Experimental results on Chinese scene public datasets demonstrate the superiority of our proposed method. In particular, SSTS achieves a new record of 78.5% in the 1-NED metric on the ReCTS dataset.Keywords
Funding Information
- National Natural Science Foundation of China
This publication has 34 references indexed in Scilit:
- ICDAR 2019 Competition on Large-Scale Street View Text with Partial Labeling - RRC-LSVT2019
- ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard2019
- ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text - RRC-ArT2019
- Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary ShapesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
- Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes2018
- FOTS: Fast Oriented Text Spotting with a Unified Network2018
- Towards End-to-End Text Spotting with Convolutional Recurrent Neural Networks2017
- An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Principal warps: thin-plate splines and the decomposition of deformationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1989
- The Hungarian method for the assignment problemNaval Research Logistics Quarterly, 1955