Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
4 results
Search Results
Item Identifying Humans Through Gait Features(Springer Science and Business Media Deutschland GmbH, 2024) Anusha, R.; Jaidhar, C.D.Achieving robust human identification in visual surveillance is an ongoing and open research challenge in biometrics. In recent years, gait has added attention for its unique benefits when matched to other biometrics. Different gait-challenging conditions hinder the performance of gait recognition systems in real-world scenarios. The only solution to solve these challenges is to develop suitable features using available information sources. Enhancing the gait recognition system’s performance is the goal of this research, with a focus on frontal, speed-invariant, and clothing-invariant recognition. The proposed approaches demonstrate their capabilities through experimental results, outperforming existing methods of gait recognition. The solutions proposed in this paper increase gait recognition performance, making it applicable in real-world scenarios. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.Item Speed-Invariant Gait Recognition Using Correlation Factor Lists for Classroom Attendance Systems(Springer Science and Business Media Deutschland GmbH, 2024) Anusha, R.; Jaidhar, C.D.The way a person walks is an important biometric used in many human detection applications, including classroom attendance systems. In such applications, speed is one of the key factors that can affect the performance of a gait detection system, as the student will enter the classroom at different speeds, depending on various factors. This study proposes an effective approach to reduce the impact of speed variations in a gait detection system. Initially, the proposed approach identifies similar regions between training and test samples. Later, the correlation factor lists are calculated using three proposed features: intensity measure, contour measure, and spatial measure. By capturing minute variations in static data, this method efficiently enhances the performance of a gait detection system. The evaluation of this approach uses CASIA C and OU-ISIR A datasets of gait. The experimental results suggest that this approach shows potential in comparison to other gait recognition methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.Item FASE Module Enabled Recognition of Individuals Using Distinct Gait Patterns(Institute of Electrical and Electronics Engineers Inc., 2024) Anusha, R.; Jaidhar, C.D.Extensive research has been conducted on gait, the walking pattern, and multiple methods have been created to utilize it as a biometric for identifying individuals. Nevertheless, there has been limited exploration of identifying individuals in running videos. A novel method is introduced in the paper that extends the feature-based approach to recognize individuals by their running patterns. The gait recognition performance is boosted in this work through the introduction of the Feature Analysis and Sample Elimination (FASE) module, which selects significant data samples using cluster formation, analysis, and elimination. Later on, the assignment of a testing sample to the training sample is achieved through the use of the proposed classification method. The experiments utilize the KTH, OU-ISIR A, and Weizmann databases. The obtained experimental results showcase the effectiveness of the proposed method. © 2024 IEEE.Item Human gait recognition based on histogram of oriented gradients and Haralick texture descriptor(Springer, 2020) Anusha, R.; Jaidhar, C.D.Gait recognition is an evolving technology in the biometric domain; it aims to recognize people through an analysis of their walking pattern. One of the significant challenges of the appearance-based gait recognition system is to augment its performance by using a distinctive low-dimensional feature vector. Therefore, this study proposes the low-dimensional features that are capable of effectively capturing the spatial, gradient, and texture information in this context. These features are obtained by the computation of histogram of oriented gradients, followed by sum variance Haralick texture descriptor from nine cells of gait gradient magnitude image. Further, the performance of the proposed method is validated on five widely used gait databases. They include CASIA A gait database, CASIA B gait database, OU-ISIR D gait database, CMU MoBo database, and KTH video database. The experimental results demonstrated that the proposed approach could choose significant discriminatory features for individual identification and consequently, outperform certain state-of-the-art methods in terms of recognition performance. © 2020, Springer Science+Business Media, LLC, part of Springer Nature.