Frontiers in Handwriting Recognition

1. Front Matter

   Pages i-xiv

   PDF

2. Historical Document Processing

   1. Front Matter

      Pages 1-1

      PDF

   2. A Few Shot Multi-representation Approach for N-Gram Spotting in Historical Manuscripts

      • Giuseppe De Gregorio, Sanket Biswas, Mohamed Ali Souibgui, Asma Bensalah, Josep Lladós, Alicia Fornés et al.

      Pages 3-17

   3. Text Edges Guided Network for Historical Document Super Resolution

      • Boraq Madi, Reem Alaasam, Jihad El-Sana

      Pages 18-33

   4. CurT: End-to-End Text Line Detection in Historical Documents with Transformers

      • Benjamin Kiessling

      Pages 34-48

   5. Date Recognition in Historical Parish Records

      • Laura Cabello Piqueras, Constanza Fierro, Jonas F. Lotz, Phillip Rust, Joen Rommedahl, Jeppe Klok Due et al.

      Pages 49-64

   6. Improving Isolated Glyph Classification Task for Palm Leaf Manuscripts

      • Nimol Thuon, Jun Du, Jianshu Zhang

      Pages 65-79

3. Signature Verification and Writer Identification

   1. Front Matter

      Pages 81-81

      PDF

   2. Impact of Type of Convolution Operation on Performance of Convolutional Neural Networks for Online Signature Verification

      • Chandra Sekhar Vorugunti, Balasubramanian Subramanian, Avinash Gautam, Viswanath Pulabaigari

      Pages 83-97

   3. COMPOSV++: Light Weight Online Signature Verification Framework Through Compound Feature Extraction and Few-Shot Learning

      • Chandra Sekhar Vorugunti, Balasubramanian Subramanian, Prerana Mukherjee, Avinash Gautam

      Pages 98-111

   4. Finger-Touch Direction Feature Using a Frequency Distribution in the Writer Verification Base on Finger-Writing of a Simple Symbol

      • Isao Nakanishi, Masaya Yamazaki, Takahiro Horiuchi

      Pages 112-121

   5. Self-supervised Vision Transformers with Data Augmentation Strategies Using Morphological Operations for Writer Retrieval

      • Marco Peer, Florian Kleber, Robert Sablatnig

      Pages 122-136

   6. EAU-Net: A New Edge-Attention Based U-Net for Nationality Identification

      • Aritro Pal Choudhury, Palaiahnakote Shivakumara, Umapada Pal, Cheng-Lin Liu

      Pages 137-152

   7. Progressive Multitask Learning Network for Online Chinese Signature Segmentation and Recognition

      • Xunhui Qin, Hanyue Zhang, Xiao Ke, Zhonghao Shen, Songmao Qi, Ke Liu

      Pages 153-167

4. Symbol and Graphics Recognition

   1. Front Matter

      Pages 169-169

      PDF

   2. Musigraph: Optical Music Recognition Through Object Detection and Graph Neural Network

      • Arnau Baró, Pau Riba, Alicia Fornés

      Pages 171-184

   3. Combining CNN and Transformer as Encoder to Improve End-to-End Handwritten Mathematical Expression Recognition Accuracy

      • Zhang Zhang, Yibo Zhang

      Pages 185-197

   4. A Vision Transformer Based Scene Text Recognizer with Multi-grained Encoding and Decoding

      • Zhi Qiao, Zhilong Ji, Ye Yuan, Jinfeng Bai

      Pages 198-212

   5. Spatial Attention and Syntax Rule Enhanced Tree Decoder for Offline Handwritten Mathematical Expression Recognition

      • Zihao Lin, Jinrong Li, Fan Yang, Shuangping Huang, Xu Yang, Jianmin Lin et al.

      Pages 213-227

5. Handwriting Recognition and Understanding

   1. Front Matter

      Pages 229-229

      PDF

This book constitutes the refereed proceedings of the 18th International Conference on Frontiers in Handwriting Recognition, ICFHR 2022, which took place in Hyderabad, India, during December 4-7, 2022.

The 36 full papers and 1 short paper presented in this volume were carefully reviewed and selected from 61 submissions. The contributions were organized in topical sections as follows: Historical Document Processing; Signature Verification and Writer Identification; Symbol and Graphics Recognition; Handwriting Recognition and Understanding; Handwriting Datasets and Synthetic Handwriting Generation; Document Analysis and Processing.

• Bank-Check Processing
• Document Image Analysis and Recognition
• Electronic Ink and Pen-Based Systems
• Forensic Studies and Security Issues
• Form Processing
• Handwriting Recognition
• Handwritten Databases and Digital Libraries
• Handwritten Document Processing and Understanding
• Historical Document Processing
• Information Extraction and Retrieval
• Language Models in Handwriting Recognition
• Layout Analysis
• Natural Language Processing (NLP)
• Online Handwriting Recognition
• pattern recognition
• Signature and Writer Recognition and Verification
• Symbol, Equation, Sketch, Music and Drawing Recognition
• Word Spotting
• Writing in the Air

• Walmart Inc., Hoboken, USA

  Utkarsh Porwal

• Universitat Autònoma de Barcelona, Barcelona, Spain

  Alicia Fornés

• National University of Sciences and Technology (NUST), Islamabad, Pakistan

  Faisal Shafait

Policies and ethics