Feature Engineering Techniques to Improve Identification Accuracy for Offline Signature Case-Bases

Shisna Sanyal, Anindta Desarkar, Uttam Kumar Das, Chitrita Chaudhuri

Source Title: International Journal of Rough Sets and Data Analysis (IJRSDA)7(1)

ISSN: 2334-4598|EISSN: 2334-4601|EISBN13: 9781799808275|DOI: 10.4018/IJRSDA.20210101.oa1

MLA

Sanyal, Shisna, et al. "Feature Engineering Techniques to Improve Identification Accuracy for Offline Signature Case-Bases." IJRSDA vol.7, no.1 2021: pp.1-19. http://doi.org/10.4018/IJRSDA.20210101.oa1

APA

Sanyal, S., Desarkar, A., Das, U. K., & Chaudhuri, C. (2021). Feature Engineering Techniques to Improve Identification Accuracy for Offline Signature Case-Bases. International Journal of Rough Sets and Data Analysis (IJRSDA), 7(1), 1-19. http://doi.org/10.4018/IJRSDA.20210101.oa1

Chicago

Sanyal, Shisna, et al. "Feature Engineering Techniques to Improve Identification Accuracy for Offline Signature Case-Bases," International Journal of Rough Sets and Data Analysis (IJRSDA) 7, no.1: 1-19. http://doi.org/10.4018/IJRSDA.20210101.oa1

Export Reference

Favorite Full-Issue Download

View Full Text HTML

View Full Text PDF

Abstract

Handwritten signatures have been widely acclaimed for personal identification viability in educated human society. But, the astronomical growth of population in recent years warrant developing mechanized systems to remove the tedium and bias associated with manual checking. Here the proposed system, performing identification with Nearest Neighbor matching between offline signature images collected temporally. The raw images and their extracted features are preserved using Case Based Reasoning and Feature Engineering principles. Image patterns are captured through standard global and local features, along with some profitable indigenously developed features. Outlier feature values, on detection, are automatically replaced by their nearest statistically determined limit values. Search space reduction possibilities within the case base are probed on a few selected key features, applying Hierarchical clustering and Dendogram representation. Signature identification accuracy is found promising when compared with other machine learning techniques and a few existing well known approaches.