Affiliation:
1. Dept of Computational Sciences, Maharaja Ranjit Singh Punjab Technical University, Bathinda, Punjab, India
Abstract
Forensic Science is a branch of science that deals with the discovery, examination, and analysis of strong elements or evidence involved in the criminal justice system. It involves the use of scientific methods to investigate crimes. The Gender Classification System is closely linked to forensic studies, specifically investigating individuals through their handwriting, known as Behavioral Biometrics. Biometric systems rely on behavioral and physiological traits such as brain-prints, fingerprints, handwritten text, speech, facial attributes, gait information, palm vein patterns, hand geometry, ECG, and more. Gender classification is an intriguing and important aspect within the field of pattern recognition and machine learning. It involves a binary problem of classifying individuals as either male or female. Analyzing the differences in femininity and masculinity behaviors can contribute to the evaluation of biometric-based identification systems. Gender classification has numerous forensic applications, including crime identification, demographic research, forgery detection, security, and surveillance. The main objective of this paper is to present the latest survey findings on the gender classification system based on handwritten text, specifically the behavioral biometric modality. It includes an overview of the state-of-the-art work, the general framework, approaches, biometric modalities, and critical analysis. The manuscript concludes with a critical analysis, discussion of open issues, concluding remarks, and future perspectives.
Publisher
Association for Computing Machinery (ACM)
Reference65 articles.
1. Improving handwriting based gender classification using ensemble classifiers
2. Wavelet-based gender detection on off-line handwritten documents using probabilistic finite state automata
3. Ashiquzzaman A and Tushar AK ( 2017 ) Handwritten Arabic Numeral Recognition using Deep Learning Neural Networks . Proceedings of IEEE International Conference on Imaging, Vision & Pattern Recognition, 1-4. Ashiquzzaman A and Tushar AK (2017) Handwritten Arabic Numeral Recognition using Deep Learning Neural Networks. Proceedings of IEEE International Conference on Imaging, Vision & Pattern Recognition, 1-4.
4. Bartle A and Zheng J ( 2015 ) Gender classification with Deep Learning. Stanfordcs, 224d Course Project Report, 1-7 . Bartle A and Zheng J (2015) Gender classification with Deep Learning. Stanfordcs, 224d Course Project Report, 1-7.
5. A Multi-Feature Selection Approach for Gender Identification of Handwriting based on Kernel Mutual Information;Bi N;Pattern Recognition Letters,2018