Dual-Branch Multitask Fusion Network for Offline Chinese Writer Identification
Article No.: 24, Pages 1 - 22
Abstract
Chinese characters are complex and contain discriminative information, meaning that their writers have the potential to be recognized using less text. In this study, offline Chinese writer identification based on a single character was investigated. To extract comprehensive features to model Chinese characters, explicit and implicit information as well as global and local features are of interest. A dual-branch multitask fusion network is proposed that contains two branches for global and local feature extraction simultaneously, and introduces auxiliary tasks to help the main task. Content recognition, stroke number estimation, and stroke recognition are considered as three auxiliary tasks for explicit information. The main task extracts implicit information of writer identity. The experimental results validated the positive influences of auxiliary tasks on the writer identification task, with the stroke number estimation task being most helpful. In-depth research was conducted to investigate the influencing factors in Chinese writer identification, with respect to character complexity, stroke importance, and character number, which provides a systematic reference for the actual application of neural networks in Chinese writer identification.
References
[1]
Utpal Garain and Thierry Paquet. 2009. Off-line multi-script writer identification using AR coefficients. In Proceedings of the 10th ICDAR. 991–995.
[2]
Abedelkadir Asi, Alaa Abdalhaleem, Daniel Fecker, Volker Märgner, and Jihad El-Sana. 2017. On writer identification for Arabic historical manuscripts. Int. J. Doc. Anal. Recognit. 20, 3 (September 2017), 173–187.
[3]
Andrew J. Newell and Lewis D. Griffin. 2014. Writer identification using oriented basic image features and the delta encoding. Pattern Recogn. 47, 6 (June 2014), 2255–2265.
[4]
Sheng He and Lambert Schomaker. 2017. Writer identification using curvature-free features. Pattern Recogn. 63, C (March 2017), 451–464.
[5]
Vivek Venugopal and Suresh Sundaram. 2021. Modified sparse representation classification framework for online writer identification. IEEE Trans. Syst. Man Cy-S. 51, 1 (January 2021), 314–325.
[6]
Vivek Venugopal and Suresh Sundaram. 2018. Online writer identification with sparse coding-based descriptors. IEEE Trans. Inf. Forensics Secur. 13, 10 (October 2018), 2538–2552.
[7]
Bilal Hadjadji and Youcef Chibani. 2018. Two combination stages of clustered one-class classifiers for writer identification from text fragments. Pattern Recogn. 82 (2018), 147–162.
[8]
Vincent Christlein, David Bernecker, Florian Hönig, Andreas Maier, and Elli Angelopoulou. 2017. Writer identification using GMM supervectors and rxemplar-SVMs. Pattern Recogn. 63, C (March 2017), 258–267.
[9]
Wong Yee Leng and Siti Mariyam Shamsuddin. 2010. Writer identification for Chinese handwriting. Int. J. Advance. Soft Comput. Appl. 2, 2 (July 2010), 142–173.
[10]
Zhenyu He, Xinge You, and Yuan Yan Tang. 2008. Writer identification of Chinese handwriting documents using hidden Markov tree model. Pattern Recogn. 41, 4 (April 2008), 1295–1307.
[11]
Makki Maliki, Naseer Al-Jawad, and Sabah Jassim. 2017. Offline writer identification for Arabic language: Analysis and classification techniques using subwords features. In Proceedings of the 2017 1st ASAR. 145–152.
[12]
Thameur Dhieb, Houcine Boubaker, Wael Ouarda, Mounir Ben Ayed, and Adel M. Alimi. 2019. Deep bidirectional long short-term memory for online Arabic writer identification based on Beta-Elliptic model. In Proceedings of the 2019 ICDARW. 35–40.
[13]
Huwida E. S. Said, Tienniu N. Tan, and Keith D. Baker. 2000. Personal identification based on handwriting. Pattern Recogn. 33, 1 (January 2000), 149–160.
[14]
Behzad Helli and Mohsen Ebrahimi Moghaddam. 2010. A text-independent Persian writer identification based on feature relation graph (FRG). Pattern Recogn. 43, 6 (June 2010), 2199–2209.
[15]
Chawki Djeddi, Imran Siddiqi, Labiba Souici-Meslati, and Abdellatif Ennaji. 2013. Text-independent writer recognition using multi-script handwritten texts. Pattern Recogn. Lett. 34, 10 (July 2013), 1196–1202.
[16]
P. S. Hiremath, S. Shivashankar, Jagadeesh D. Pujari, and R. K. Kartik. 2010. Writer identification in a handwritten document image using texture features. In Proceedings of the ICSIP. 139–142.
[17]
Axel Brink, Marius Bulacu, and Lambert Schomaker. 2008. How much handwritten text is needed for text-independent writer verification and identification. In Proceedings of the 2008 19th ICPR. 1–4.
[18]
Sheng He and Lambert Schomaker. 2019. Deep adaptive learning for writer identification based on single handwritten word images. Pattern Recogn. 88, C (April 2019), 64–74.
[19]
Shiming Chen, Yisong Wang, Chin-Teng Lin, Weiping Ding, and Zehong Cao. 2019. Semi-supervised feature learning for improving writer identification. Inf. Sci. 482, C (May 2019), 156–170.
[20]
Sheng He and Lambert Schomaker. 2021. GR-RNN: Global-context residual recurrent neural networks for writer identification. Pattern Recogn. 117, C (September 2021), 107975.
[21]
Songxuan Lai, Yecheng Zhu, and Lianwen Jin. 2020. Encoding pathlet and SIFT features with bagged VLAD for historical writer identification. IEEE Trans. Inf. Forensics Secur. 15 (2020), 3553–3566.
[22]
Ross Girshick. 2015. Fast R-CNN. In Proceedings of the IEEE ICCV. 1440–1448.
[23]
Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2017. ImageNet classification with deep convolutional neural networks. Commun. ACM 60, 6 (June 2017), 84–90.
[24]
Sebastian Ruder. 2017. An overview of multi-task learning in deep neural networks. Retrieved from https://arxiv.org/abs/1706.05098 (2021).
[25]
Marius Bulacu and Lambert Schomaker. 2007. Text-independent writer identification and verification using textural and allographic features. IEEE Trans. Pattern Anal. Mach. Intell. 29, 4 (April 2007), 701–717.
[26]
Sheng He and Lambert Schomaker. 2017. Beyond OCR: Multi-faceted understanding of handwritten document characteristics. Pattern Recogn. 63, C (March 2017), 321–333.
[27]
Sheng He and Lambert Schomaker. 2020. FragNet: Writer identification using deep fragment networks. IEEE Trans. Inf. Forensics Secur. 15 (2020), 3013–3022.
[28]
A. A. Brink, J. Smit, M. L. Bulacu, and L. R. B. Schomaker. 2012. Writer identification using directional ink-trace width measurements. Pattern Recogn. 45, 1 (January 2012), 162–171.
[29]
Andreas Schlapbach and Horst Bunke. 2006. Off-line writer identification using Gaussian mixture models. In Proceedings of the 18th International Conference on Pattern Recognition - Volume 03 (ICPR ’06). IEEE Computer Society, 992–995.
[30]
Andreas Schlapbach and Horst Bunke. 2007. A writer identification and verification system using HMM based recognizers. Pattern Anal. Appl. 10, 1 (February 2007), 33–43.
[31]
Chawki Djeddi, Imran Siddiqi, Labiba Souici-Meslati, and Abdellatif Ennaji. 2013. Codebook for writer characterization: A vocabulary of patterns or a mere representation space? In Proceedings of the 2013 12th International Conference on Document Analysis and Recognition (ICDAR ’13). IEEE Computer Society, 423–427.
[32]
Imran Siddiqi and Nicole Vincent. 2010. Text independent writer recognition using redundant writing patterns with contour-based orientation and curvature features. Pattern Recogn. 43, 11 (November 2010), 3853–3865.
[33]
Mohamed Nidhal Abdi and Maher Khemakhem. 2015. A model-based approach to offline text-independent Arabic writer identification and verification. Pattern Recogn. 48, 5 (May 2015), 1890–1903.
[34]
Alaa Sulaiman, Khairuddin Omar, Mohammad F. Nasrudin, and Anas Arram. 2019. Length independent writer identification based on the fusion of deep and hand-crafted descriptors. IEEE Access. 7 (2019), 91772–91784.
[35]
Xiangqian Wu, Youbao Tang, and Wei Bu. 2014. Offline text-independent writer identification based on scale invariant feature transform. IEEE Trans. Inf. Forensics Secur. 9, 3 (March 2014), 526–536.
[36]
Yong Zhu, Tieniu Tan, and Yunhong Wang. 2000. Biometric personal identification based on handwriting. In Proceedings of the 15th International Conference on Pattern Recognition (ICPR 2000), 02 (2000). 797–800.
[37]
Zhenyu He, Xinge You, and Yuan Yan Tang. 2008. Writer identification using global wavelet-based features. Neurocomput. 71, 10–12 (June 2008), 1832–1841.
[38]
Yongjie Hu, Wenming Yang, and Youbin Chen. 2014. Bag of features approach for offline text-independent Chinese writer identification. In Proceedings of the 2014 IEEE International Conference on Image Processing (ICIP ’14). 2609–2613.
[39]
Linjie Xing and Yu Qiao. 2016. DeepWriter: A multi-stream deep CNN for text-independent writer identification. In Proceedings of the 15th International Conference on Frontiers in Handwriting Recognition (ICFHR ’16). 584–589.
[40]
Ping Wei, Huan Li, and Ping Hu. 2019. Inverse discriminative networks for handwritten signature verification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR ’19), 5764–5772.
[41]
S. Hwang and H. E. Kim. 2016. Self-transfer learning for fully weakly supervised object localization. Retrieved from https://arxiv.org/abs/1602.01625 (2021)
[42]
Zhanpeng Zhang, Ping Luo, Chen Change Loy, and Xiaoou Tang. 2014. Facial landmark detection by deep multi-task learning. In Proceedings of the 13th European Conference on Computer Vision (ECCV ’14), 8694 (2014). 6–12.
[43]
Cheng-Lin Liu, Fei Yin, Da-Han Wang, Qiu-Feng Wang, C.-L. Liu, F. Yin, D.-H. Wang, and Q.-F. Wang. 2011. CASIA online and offline Chinese handwriting databases. In Proceedings of the 2011 International Conference on Document Analysis and Recognition (ICDAR ’11). 37–41.
[44]
Florian Kleber, Stefan Fiel, Markus Diem, and Robert Sablatnig. 2013. CVL-DataBase: An off-line database for writer retrieval, writer identification and word spotting. In Proceedings of the 12th International Conference on Document Analysis and Recognition (ICDAR ’13). 560–564.
[45]
D. P. Kingma and J. Ba. 2014. Adam: A method for stochastic optimization. Retrieved from https://arxiv.org/abs/1412.6980 (2021).
[46]
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR ’16). 770–778.
[47]
Mingxing Tan and Le Quoc. 2019. EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the 2019 International Conference on Machine Learning (PMLR'19). 6105--6114.
[48]
Wirmanto Suteddy, Devi Aprianti Rimadhani Agustini, Anugrah Adiwilaga, and Dastin Aryo Atmanto. 2023. End-To-end evaluation of deep learning architectures for off-line handwriting writer identification: A comparative study. JOIV: Int. J. Inf. Vis. 7, 1 (2023). 178–185.
[49]
Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An image is worth 16×16 words: transformers for image recognition at scale. In Proceedings of the 2021 ICLR. 1–22.
Index Terms
- Dual-Branch Multitask Fusion Network for Offline Chinese Writer Identification
Index terms have been assigned to the content through auto-classification.
Recommendations
Writer Identification Using TF-IDF for Cursive Handwritten Word Recognition
ICDAR '11: Proceedings of the 2011 International Conference on Document Analysis and RecognitionIn this paper, we present two text-independent writer identification methods in a closed-world context. Both methods use on-line and off-line features jointly with a classifier inspired from information retrieval methods. These methods are local, ...
Binarization, character extraction, and writer identification of historical Hebrew calligraphy documents
We present our work on the paleographic analysis and recognition system intended for processing of historical Hebrew calligraphy documents. The main goal is to analyze documents of different writing styles in order to identify the locations, dates, and ...
Offline text-independent writer identification using codebook and efficient code extraction methods
In this paper, an efficient method for text-independent writer identification using a codebook method is proposed. The method uses the occurrence histogram of the shapes in a codebook to create a feature vector for each specific manuscript. For cursive ...
Comments
Information & Contributors
Information
Published In
February 2024
340 pages
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 08 February 2024
Online AM: 26 December 2023
Accepted: 14 December 2023
Revised: 22 May 2023
Received: 03 August 2022
Published in TALLIP Volume 23, Issue 2
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- National Natural Science Foundation of China
- Leading Innovation Team of Zhejiang Province
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 75Total Downloads
- Downloads (Last 12 months)75
- Downloads (Last 6 weeks)6
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in