An Improved Offline Text-independent Chinese Writer Identification Scheme based on Two-tier Image Retrieval Mechanism

Gloria Jennis Tan; Ling Ling Ung; Chi Wee Tan; Zeti Darleena Binti Eri; Norlina Mohd Sabri; Hoshang Kolivand; Ghazali Sulong

doi:10.15575/join.v11i1.1666

Authors

Gloria Jennis Tan Universiti Teknologi MARA (UiTM) Shah Alam, Selangor, Malaysia
Ling Ling Ung Universiti Teknologi MARA (UiTM) Sabah Branch, Kota Kinabalu Campus, Malaysia
Chi Wee Tan Tunku Abdul Rahman University of Management and Technology (TAR UMT), Kuala Lumpur, Malaysia
Zeti Darleena Binti Eri Universiti Teknologi MARA (UiTM) Terengganu Branch, Kuala Terengganu Campus, Malaysia
Norlina Mohd Sabri Universiti Teknologi MARA (UiTM) Terengganu Branch, Kuala Terengganu Campus, Malaysia
Hoshang Kolivand Liverpool John Moores University (LJMU), L3 3AF and Staffordshire University, United Kingdom
Ghazali Sulong Management and Science University (MSU), Malaysia, Malaysia

DOI:

https://doi.org/10.15575/join.v11i1.1666

Keywords:

Chinese Handwriting Analysis, Image Retrieval, Writer Identification, Writer Retrieval

Abstract

Research in writer identification has received significant interest in recent years due to its forensic applicability. Undoubtedly, many achievements have been carried out on the traditional method which is without retrieval and only focused on inconsistent and lead ambiguous identification performance. A major problem with this kind of traditional method is searching and retrieval of a document from large image repositories is currently a big issue. In this paper, the focus aim is to determine the effectiveness and reliability of integrating retrieval mechanisms compared to the best and up-to-date techniques for writer identification without retrieval mechanism in offline text-independent Chinese writer identification. Experiments were conducted on an open HIT-MW database which is widely used for performance evaluation and employed the same standard dataset for benchmarking. The proposed method incorporates a combination of selected features—Statistical Local Ternary Local Binary Pattern (SLT-LBP), Histogram of Contour (HC), and Gray Level Difference Method (GLDM)—integrated with a Euclidean distance-based classification framework. Experimental evaluations conducted on the publicly available HIT-MW dataset demonstrate that the proposed approach achieves an identification accuracy of 96.68%. These results indicate the potential of the proposed method to perform competitively with existing state-of-the-art techniques, while also offering improvements in scalability and interpretability for writer identification tasks. Integration method with two-tier image retrieval for reducing search space in interpretability of results by forensic experts when large databases are involved and improving identification rates, yet remarkable accuracy. This area, however, still has a large room for research which can be taken by upcoming researchers.

References

[1] G. J. Tan, G. Sulong, and M. S. Mohd Rahim, “Offline Text-Independent Chinese writer identification using GLDM features,” J. Telecommun. Electron. Comput. Eng., vol. 9, no. 3-3 Special Issue, 2017.

[2] R. Plamondon and G. Lorette, “Automatic signature verification and writer identification—the state of the art,” Pattern Recognit., vol. 22, no. 2, pp. 107–131, 1989.

[3] F. Leclerc and R. Plamondon, “Automatic Signature Verification: The State of the Art --1989-1993,” Int. J. Pattern Recognit. Artif. Intell., vol. 08, no. 03, pp. 643–660, 1994.

[4] L. Schomaker, “Advances in writer identification and verification,” Proc. Int. Conf. Doc. Anal. Recog-nition, ICDAR, vol. 2, pp. 1268–1273, 2007.

[5] M. Sreeraj and S. M. Idicula, “A Survey on Writer Identification Schemes,” Int. J. Comput. Appl., vol. 26, no. 2, pp. 23–33, 2011.

[6] G. J. Tan, G. Sulong, and M. S. Mohd Rahim, “Off-line text-independent writer recognition for chinese handwriting: A review,” J. Teknol., vol. 75, no. 2, 2015.

[7] G. J. Tan, G. Sulong, and M. S. M. Rahim, “Writer identification: A comparative study across three world major languages,” Forensic Sci. Int., vol. 279, 2017.

[8] S. Al-Ma’adeed, E. Mohammed, D. Al Kassis, and F. Al-Muslih, “Writer identification using edge-based directional probability distribution features for Arabic words,” AICCSA 08 - 6th IEEE/ACS Int. Conf. Comput. Syst. Appl., pp. 582–590, 2008.

[9] U.-V. Marti, R. Messerli, and H. Bunke, “Writer identification using text line based features,” in Pro-ceedings of Sixth International Conference on Document Analysis and Recognition, 2001, pp. 101–105.

[10] K. Franke, O. Biinnemeyer, and T. Sy, “Ink Texture Analysis for Writer Identification,” vol. 00, pp. 268–273, 2002.

[11] H. E. S. Said, T. N. Tan, and K. D. Baker, “Personal identification based on handwriting,” Pattern Recognit., vol. 33, pp. 149–160, 2000.

[12] R. Jain and D. Doermann, “Combining Local Features for Offline Writer Identification,” Proc. Int. Conf. Front. Handwrit. Recognition, ICFHR, vol. 2014-Decem, pp. 583–588, 2014.

[13] L. Schomaker, K. Franke, and M. Bulacu, “Using codebooks of fragmented connected-component con-tours in forensic and historic writer identification,” Pattern Recognit. Lett., vol. 28, no. 6, pp. 719–727, 2007.

[14] Y. Tang, W. Bu, and X. Wu, “Text-Independent Writer Identification Using Improved Structural Fea-tures,” pp. 404–411, 2014.

[15] R. Kumar, B. Chanda, and J. D. Sharma, “A novel sparse model based forensic writer identification,” Pattern Recognit. Lett., vol. 35, no. 1, pp. 105–112, 2014.

[16] Ezugwu, A.E., Shukla, A.K., Agbaje, M.B., Oyelade, O.N., Jose-Garcia, A. and Agushaka, J.O., 2021. Au-tomatic clustering algorithms: a systematic review and bibliometric analysis of relevant litera-ture. Neural Computing and Applications, 33(11), pp.6247-6306.

[17] V. Christlein, D. Bernecker, A. Maier, and E. Angelopoulou, “Offline writer identification using convolutional neural network activation features,” Journal Name, vol. XX, no. XX, pp. XX–XX, 2024.

[18] H. Wang, Y. Mao, Q. Miao, Q. Xiao, and Y. Zhang, “Dual branch multitask fusion network for offline Chinese writer identification,” ACM Trans. Asian Low Resour. Lang. Inf. Process., vol. 23, no. 2, Art. 24, 2024.

[19] G. J. Tan, G. Sulong, and M. S. M. Rahim, “Offline text independent writer recognition for Chinese handwriting: A review,” J. Teknol., vol. 75, no. 2, pp. 39–50, 2024.

[20] J. Zhang, Z. Xia, and X. Liu, “Offline text independent writer identification using a codebook with structural features,” Int. J. Pattern Recognit. Artif. Intell., vol. 38, no. 5, Art. 2450001, 2024.

[21] Su T., T. Zhang and D. Guan, “HIT-MW Dataset for Offline Chinese Handwritten Text Recognition,” In Proceedings of the 10th International Workshop on Frontiers in Handwriting Recognition. La Baule, France. October 23-26, 2006.

[22] S. Gupta, “Automatic Person Identification and Verification using Online Handwriting,” Online, 2008.

[23] J. Wen, B. Fang, J. Chen, Y. Tang, and H. Chen, “Fragmented edge structure coding for Chinese writer identification,” Neurocomputing, vol. 86, pp. 45–51, Jun. 2012.

[24] Wu X, Tang Y, Bu W, “Offline text-independent writer identification based on scale invariant feature-transform,” IEEE Transactions on Information Forensics and Security 526–536, 2014

[25] Zhu Y, Wang Y, “An offline text-independent writer identification system with sae feature extraction,” In: Progress in Informatics and Computing (PIC), 2016 International Conference on, pp. 432–436. IEEE, 2016