• Soumya Jain
• Prof. Deepa Gianchandani

A person’s gait carries information about the individual along multiple dimensions. In addition to indicating biologically intrinsic properties, like gender and identity, the gait of a person changes dynamically based on their emotional state and state of health. If a computer can recognize gender, it will be very helpful in many applications. This paper presents self-reproducing machine learning technique on arbitrary walking directions for gender recognition from gait sequences. Most current approaches make the unrealistic assumption that persons walk along a fixed direction or a pre-defined path. MATLAB software is used to simulate the proposed research work and simulated results optimized the overall accuracy i.e achieved 96% with less number of iteration. The program is executed in less time and generates fewer frames then some existing approaches.

Accuracy, iteration, Time, Gender, Gait, Recognition, Frames, Cluster

"Self-Reproducing Machine Learning Technique on Arbitrary Walking Directions for Gender Recognition from Gait Sequences", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 10, page no.c376-c381, October-2021, Available :http://www.jetir.org/papers/JETIR2110249.pdf

"Self-Reproducing Machine Learning Technique on Arbitrary Walking Directions for Gender Recognition from Gait Sequences", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 10, page no. ppc376-c381, October-2021, Available at : http://www.jetir.org/papers/JETIR2110249.pdf