Exploring Anchor-Free Approach for Reading Chinese Characters
Open Access
- 29 October 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 23-28
Abstract
Scene text spotting has achieved an impressive performance over recent years. Currently, most text localization methods are designed with the text line instance. We argue that building a character-level spotting network is more suited to recognize the Chinese of text and Chinese is also common in scene text images. In this paper, we explore an anchor-free spotting framework that treats a character as a single point. To better capture Chinese character features, we first use the Canny edge detectors and superimpose the obtained edge information onto the RGB image channel. After that, a feed-forward network is set up and the inference can be processed in a single network forward-pass, without complex post-processing steps. Experiments are performed on the Chinese text dataset and the quantitative comparisons demonstrate the effectiveness of the anchor-free approach.Keywords
This publication has 29 references indexed in Scilit:
- Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes2018
- Arbitrary-Oriented Scene Text Detection via Rotation ProposalsIEEE Transactions on Multimedia, 2018
- Mask R-CNN2017
- YOLO9000: Better, Faster, Stronger2017
- EAST: An Efficient and Accurate Scene Text Detector2017
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- 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
- SSD: Single Shot MultiBox Detector2016
- Fully convolutional networks for semantic segmentation2015
- On the Canny edge detectorPattern Recognition, 2001