HTR-JAND: Handwritten Text Recognition with Joint Attention Network and Knowledge Distillation

• URL: http://arxiv.org/abs/2412.18524v1
• Date: Tue, 24 Dec 2024 16:08:24 GMT
• Title: HTR-JAND: Handwritten Text Recognition with Joint Attention Network and Knowledge Distillation
• Authors: Mohammed Hamdan, Abderrahmane Rahiche, Mohamed Cheriet,
• Abstract summary: Current Handwritten Text Recognition (HTR) systems struggle with the inherent complexity of historical documents. This paper introduces HTR-JAND, an efficient HTR framework that combines advanced feature extraction with knowledge distillation. We enhance recognition accuracy through context-aware T5 post-processing, particularly effective for historical documents.
• Score: 21.25786478579275
• License:
• Abstract: Despite significant advances in deep learning, current Handwritten Text Recognition (HTR) systems struggle with the inherent complexity of historical documents, including diverse writing styles, degraded text quality, and computational efficiency requirements across multiple languages and time periods. This paper introduces HTR-JAND (HTR-JAND: Handwritten Text Recognition with Joint Attention Network and Knowledge Distillation), an efficient HTR framework that combines advanced feature extraction with knowledge distillation. Our architecture incorporates three key components: (1) a CNN architecture integrating FullGatedConv2d layers with Squeeze-and-Excitation blocks for adaptive feature extraction, (2) a Combined Attention mechanism fusing Multi-Head Self-Attention with Proxima Attention for robust sequence modeling, and (3) a Knowledge Distillation framework enabling efficient model compression while preserving accuracy through curriculum-based training. The HTR-JAND framework implements a multi-stage training approach combining curriculum learning, synthetic data generation, and multi-task learning for cross-dataset knowledge transfer. We enhance recognition accuracy through context-aware T5 post-processing, particularly effective for historical documents. Comprehensive evaluations demonstrate HTR-JAND's effectiveness, achieving state-of-the-art Character Error Rates (CER) of 1.23\%, 1.02\%, and 2.02\% on IAM, RIMES, and Bentham datasets respectively. Our Student model achieves a 48\% parameter reduction (0.75M versus 1.5M parameters) while maintaining competitive performance through efficient knowledge transfer. Source code and pre-trained models are available at \href{https://github.com/DocumentRecognitionModels/HTR-JAND}{Github}.

Related papers

• HAND: Hierarchical Attention Network for Multi-Scale Handwritten Document Recognition and Layout Analysis [21.25786478579275]
  Handwritten document recognition is one of the most challenging tasks in computer vision. Traditionally, this problem has been approached as two separate tasks, handwritten text recognition and layout analysis. This paper introduces HAND, a novel end-to-end and segmentation-free architecture for simultaneous text recognition and layout analysis tasks.
  arXiv  Detail & Related papers  (2024-12-25T20:36:29Z)
• VEGA: Learning Interleaved Image-Text Comprehension in Vision-Language Large Models [76.94378391979228]
  We introduce a new, more demanding task known as Interleaved Image-Text (IITC) This task challenges models to discern and disregard superfluous elements in both images and text to accurately answer questions. In support of this task, we further craft a new VEGA dataset, tailored for the IITC task on scientific content, and devised a subtask, Image-Text Association (ITA)
  arXiv  Detail & Related papers  (2024-06-14T17:59:40Z)
• CELA: Cost-Efficient Language Model Alignment for CTR Prediction [70.65910069412944]
  Click-Through Rate (CTR) prediction holds a paramount position in recommender systems. Recent efforts have sought to mitigate these challenges by integrating Pre-trained Language Models (PLMs) We propose textbfCost-textbfEfficient textbfLanguage Model textbfAlignment (textbfCELA) for CTR prediction.
  arXiv  Detail & Related papers  (2024-05-17T07:43:25Z)
• Best Practices for a Handwritten Text Recognition System [8.334691351242753]
  Handwritten text recognition has been developed rapidly in the recent years. Non-trivial deviation in performance can be detected even when small pre-processing elements are changed. This work highlights simple yet effective empirical practices that can further help training and provide well-performing handwritten text recognition systems.
  arXiv  Detail & Related papers  (2024-04-17T13:00:05Z)
• Automated Few-shot Classification with Instruction-Finetuned Language Models [76.69064714392165]
  We show that AuT-Few outperforms state-of-the-art few-shot learning methods. We also show that AuT-Few is the best ranking method across datasets on the RAFT few-shot benchmark.
  arXiv  Detail & Related papers  (2023-05-21T21:50:27Z)
• Uncovering the Handwritten Text in the Margins: End-to-end Handwritten Text Detection and Recognition [0.840835093659811]
  This work presents an end-to-end framework for automatic detection and recognition of handwritten marginalia. It uses data augmentation and transfer learning to overcome training data scarcity. The effectiveness of the proposed framework has been empirically evaluated on the data from early book collections found in the Uppsala University Library in Sweden.
  arXiv  Detail & Related papers  (2023-03-10T14:00:53Z)
• Boosting Modern and Historical Handwritten Text Recognition with Deformable Convolutions [52.250269529057014]
  Handwritten Text Recognition (HTR) in free-volution pages is a challenging image understanding task. We propose to adopt deformable convolutions, which can deform depending on the input at hand and better adapt to the geometric variations of the text.
  arXiv  Detail & Related papers  (2022-08-17T06:55:54Z)
• One-shot Key Information Extraction from Document with Deep Partial Graph Matching [60.48651298832829]
  Key Information Extraction (KIE) from documents improves efficiency, productivity, and security in many industrial scenarios. Existing supervised learning methods for the KIE task need to feed a large number of labeled samples and learn separate models for different types of documents. We propose a deep end-to-end trainable network for one-shot KIE using partial graph matching.
  arXiv  Detail & Related papers  (2021-09-26T07:45:53Z)
• StackMix and Blot Augmentations for Handwritten Text Recognition [0.0]
  The paper describes the architecture of the neural net-work and two ways of increasing the volume of train-ing data. StackMix can also be applied to the standalone task of gen-erating handwritten text based on printed text.
  arXiv  Detail & Related papers  (2021-08-26T09:28:22Z)
• EASTER: Efficient and Scalable Text Recognizer [0.0]
  We present an Efficient And Scalable TExt Recognizer (EASTER) to perform optical character recognition on both machine printed and handwritten text. Our model utilise 1-D convolutional layers without any recurrence which enables parallel training with considerably less volume of data. We also showcase improvements over the current best results on offline handwritten text recognition task.
  arXiv  Detail & Related papers  (2020-08-18T10:26:03Z)
• Efficient Crowd Counting via Structured Knowledge Transfer [122.30417437707759]
  Crowd counting is an application-oriented task and its inference efficiency is crucial for real-world applications. We propose a novel Structured Knowledge Transfer framework to generate a lightweight but still highly effective student network. Our models obtain at least 6.5$times$ speed-up on an Nvidia 1080 GPU and even achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-03-23T08:05:41Z)

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.