Recognition of Gender using Gait Energy Image Projections Based on Random Forest Classifier
M. Hema1, K Babulu2, N Balaji3

1M. Hema, Assistant Professor, Dept. of ECE, JNTUK University College of Engineering, Vizianagaram, India.
2K Babulu, Professor, Dept. of ECE, JNTUK University College of Engineering, Kakinada, India.
3N Balaji, Professor, Dept. of ECE, JNTUK University College of Engineering, Narsaraopeta, India.

Manuscript received on September 15, 2019. | Revised Manuscript received on 23 September, 2019. | Manuscript published on October 10, 2019. | PP: 1518-1523 | Volume-8 Issue-12, October 2019. | Retrieval Number: L31041081219/2019©BEIESP | DOI: 10.35940/ijitee.L3104.1081219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Identification of gender is a very fascinating criterion in the present day scenario. Especially, in the surveillance applications, gender recognition is very beneficial. With the use of face, speech, voice and gait, the gender of a person can be determined. Non-contact, non-invasive and easily acquired at distance, gait analysis has attracted the interest of many researchers in the classification of gender. For the identification of gender, 2 stages of the methodology are used in our proposed work. A new descriptor called Gait energy image projection model(GPM) is proposed which highlights all the gender-related parameters. In the second stage of methodology, proposed descriptor GPM is fused with already existing descriptors like GEI and FED for enhanced performance. For classifying the gender, an Ensemble classifier called Random Forests is applied to the individual and fused descriptors and the results are evaluated. Two datasets are used for experimentation namely CASIA B and OU-ISIR datasets which are standard datasets for person identification and different performance metrics such as accuracy, precision, recall and error rate are evaluated.
Keywords: Image Recognition, Gait Energy Image, CASIA B dataset, Random Forest Classifier
Scope of the Article: Pattern Recognition