Orientation-Independent Chinese Text Recognition in Scene Images
This addresses a domain-specific problem for scene text recognition in Chinese, offering a novel solution for handling orientation variations, but it is incremental as it builds on existing STR methods.
The paper tackles the problem of recognizing vertical Chinese text in scene images, which is difficult for existing methods focused on Latin text, by introducing a Character Image Reconstruction Network (CIRN) to disentangle content and orientation information, achieving a 45.63% improvement on a new Vertical Chinese Text Recognition dataset.
Scene text recognition (STR) has attracted much attention due to its broad applications. The previous works pay more attention to dealing with the recognition of Latin text images with complex backgrounds by introducing language models or other auxiliary networks. Different from Latin texts, many vertical Chinese texts exist in natural scenes, which brings difficulties to current state-of-the-art STR methods. In this paper, we take the first attempt to extract orientation-independent visual features by disentangling content and orientation information of text images, thus recognizing both horizontal and vertical texts robustly in natural scenes. Specifically, we introduce a Character Image Reconstruction Network (CIRN) to recover corresponding printed character images with disentangled content and orientation information. We conduct experiments on a scene dataset for benchmarking Chinese text recognition, and the results demonstrate that the proposed method can indeed improve performance through disentangling content and orientation information. To further validate the effectiveness of our method, we additionally collect a Vertical Chinese Text Recognition (VCTR) dataset. The experimental results show that the proposed method achieves 45.63% improvement on VCTR when introducing CIRN to the baseline model.