Open-set Text Recognition via Character-Context Decoupling
This addresses the challenge of recognizing novel characters in text recognition, which is important for applications like OCR in diverse languages, but it appears incremental as it builds on existing methods by decoupling information.
The paper tackles the problem of open-set text recognition, where models must recognize novel characters, by proposing a Character-Context Decoupling framework to separate contextual and visual information, achieving promising performance on open-set, zero-shot, and close-set datasets.
The open-set text recognition task is an emerging challenge that requires an extra capability to cognize novel characters during evaluation. We argue that a major cause of the limited performance for current methods is the confounding effect of contextual information over the visual information of individual characters. Under open-set scenarios, the intractable bias in contextual information can be passed down to visual information, consequently impairing the classification performance. In this paper, a Character-Context Decoupling framework is proposed to alleviate this problem by separating contextual information and character-visual information. Contextual information can be decomposed into temporal information and linguistic information. Here, temporal information that models character order and word length is isolated with a detached temporal attention module. Linguistic information that models n-gram and other linguistic statistics is separated with a decoupled context anchor mechanism. A variety of quantitative and qualitative experiments show that our method achieves promising performance on open-set, zero-shot, and close-set text recognition datasets.