CharFormer: A Glyph Fusion based Attentive Framework for High-precision Character Image Denoising
This addresses the issue of degraded character images that lead to poor recognition results, though it appears incremental as it builds on existing denoising methods with a focus on glyph preservation.
The paper tackles the problem of character image denoising by proposing CharFormer, a framework that uses glyph fusion and attention mechanisms to preserve character glyphs during denoising, resulting in improved denoising performance compared to state-of-the-art methods on multiple datasets.
Degraded images commonly exist in the general sources of character images, leading to unsatisfactory character recognition results. Existing methods have dedicated efforts to restoring degraded character images. However, the denoising results obtained by these methods do not appear to improve character recognition performance. This is mainly because current methods only focus on pixel-level information and ignore critical features of a character, such as its glyph, resulting in character-glyph damage during the denoising process. In this paper, we introduce a novel generic framework based on glyph fusion and attention mechanisms, i.e., CharFormer, for precisely recovering character images without changing their inherent glyphs. Unlike existing frameworks, CharFormer introduces a parallel target task for capturing additional information and injecting it into the image denoising backbone, which will maintain the consistency of character glyphs during character image denoising. Moreover, we utilize attention-based networks for global-local feature interaction, which will help to deal with blind denoising and enhance denoising performance. We compare CharFormer with state-of-the-art methods on multiple datasets. The experimental results show the superiority of CharFormer quantitatively and qualitatively.