Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning

• URL: http://arxiv.org/abs/2309.01083v1
• Date: Sun, 3 Sep 2023 05:33:16 GMT
• Title: Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning
• Authors: Haiyang Yu, Xiaocong Wang, Bin Li, Xiangyang Xue
• Abstract summary: We propose a two-stage framework for Chinese Text Recognition (CTR) We pre-train a CLIP-like model through aligning printed character images and Ideographic Description Sequences (IDS) This pre-training stage simulates humans recognizing Chinese characters and obtains the canonical representation of each character. The learned representations are employed to supervise the CTR model, such that traditional single-character recognition can be improved to text-line recognition.
• Score: 61.34060587461462
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scene text recognition has been studied for decades due to its broad applications. However, despite Chinese characters possessing different characteristics from Latin characters, such as complex inner structures and large categories, few methods have been proposed for Chinese Text Recognition (CTR). Particularly, the characteristic of large categories poses challenges in dealing with zero-shot and few-shot Chinese characters. In this paper, inspired by the way humans recognize Chinese texts, we propose a two-stage framework for CTR. Firstly, we pre-train a CLIP-like model through aligning printed character images and Ideographic Description Sequences (IDS). This pre-training stage simulates humans recognizing Chinese characters and obtains the canonical representation of each character. Subsequently, the learned representations are employed to supervise the CTR model, such that traditional single-character recognition can be improved to text-line recognition through image-IDS matching. To evaluate the effectiveness of the proposed method, we conduct extensive experiments on both Chinese character recognition (CCR) and CTR. The experimental results demonstrate that the proposed method performs best in CCR and outperforms previous methods in most scenarios of the CTR benchmark. It is worth noting that the proposed method can recognize zero-shot Chinese characters in text images without fine-tuning, whereas previous methods require fine-tuning when new classes appear. The code is available at https://github.com/FudanVI/FudanOCR/tree/main/image-ids-CTR.

Related papers

• Decoder Pre-Training with only Text for Scene Text Recognition [54.93037783663204]
  Scene text recognition (STR) pre-training methods have achieved remarkable progress, primarily relying on synthetic datasets. We introduce a novel method named Decoder Pre-training with only text for STR (DPTR) DPTR treats text embeddings produced by the CLIP text encoder as pseudo visual embeddings and uses them to pre-train the decoder.
  arXiv  Detail & Related papers  (2024-08-11T06:36:42Z)
• HierCode: A Lightweight Hierarchical Codebook for Zero-shot Chinese Text Recognition [47.86479271322264]
  We propose HierCode, a novel and lightweight codebook that exploits the innate hierarchical nature of Chinese characters. HierCode employs a multi-hot encoding strategy, leveraging hierarchical binary tree encoding and prototype learning to create distinctive, informative representations for each character. This approach not only facilitates zero-shot recognition of OOV characters by utilizing shared radicals and structures but also excels in line-level recognition tasks by computing similarity with visual features.
  arXiv  Detail & Related papers  (2024-03-20T17:20:48Z)
• Orientation-Independent Chinese Text Recognition in Scene Images [61.34060587461462]
  We take the first attempt to extract orientation-independent visual features by disentangling content and orientation information of text images. Specifically, we introduce a Character Image Reconstruction Network (CIRN) to recover corresponding printed character images with disentangled content and orientation information.
  arXiv  Detail & Related papers  (2023-09-03T05:30:21Z)
• Zero-shot Generation of Training Data with Denoising Diffusion Probabilistic Model for Handwritten Chinese Character Recognition [11.186226578337125]
  There are more than 80,000 character categories in Chinese but most are rarely used. To build a high performance handwritten Chinese character recognition system, many training samples need be collected for each character category. We propose a novel approach to transforming Chinese character glyph images generated from font libraries to handwritten ones.
  arXiv  Detail & Related papers  (2023-05-25T02:13:37Z)
• Stroke-Based Autoencoders: Self-Supervised Learners for Efficient Zero-Shot Chinese Character Recognition [4.64065792373245]
  We develop a stroke-based autoencoder to model the sophisticated morphology of Chinese characters. Our SAE architecture outperforms other existing methods in zero-shot recognition.
  arXiv  Detail & Related papers  (2022-07-17T14:39:10Z)
• SVTR: Scene Text Recognition with a Single Visual Model [44.26135584093631]
  We propose a Single Visual model for Scene Text recognition within the patch-wise image tokenization framework. The method, termed SVTR, firstly decomposes an image text into small patches named character components. Experimental results on both English and Chinese scene text recognition tasks demonstrate the effectiveness of SVTR.
  arXiv  Detail & Related papers  (2022-04-30T04:37:01Z)
• CRIS: CLIP-Driven Referring Image Segmentation [71.56466057776086]
  We propose an end-to-end CLIP-Driven Referring Image framework (CRIS) CRIS resorts to vision-language decoding and contrastive learning for achieving the text-to-pixel alignment. Our proposed framework significantly outperforms the state-of-the-art performance without any post-processing.
  arXiv  Detail & Related papers  (2021-11-30T07:29:08Z)
• TextScanner: Reading Characters in Order for Robust Scene Text Recognition [60.04267660533966]
  TextScanner is an alternative approach for scene text recognition. It generates pixel-wise, multi-channel segmentation maps for character class, position and order. It also adopts RNN for context modeling and performs paralleled prediction for character position and class.
  arXiv  Detail & Related papers  (2019-12-28T07:52:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.