Human Gait Based Gender Classification Using Various Transformation Techniques

Abstract

Gender classification such as classifying human face is only challenging for computer, but even hard for human in some cases. In our work a new novel approach is proposed to recognize gender from the face image. Continuous Wavelet Transforms, Discrete Wavelet Transforms, Radon Transforms are used for features selections for each face images of male and female. These selected features will be used to classify the face images of each Gender using Support Vector Machine with Linear Kernel. Our work use ORL database contain 100 images include both Male and Female Gender .The experimental result shows that the proposed approach (Continuous wavelet Transform and Support Vector Machine). Proposed work achieves higher performance than some other methods, and is even more accurate than human observers. We also present a numerical analysis of the contributions of different human components, which shows that head, hair and back are more discriminative than other components. All the above prove that gaitbased gender classification is feasible in controlled environments. We use both static and dynamic data sets ( images & video) for the gender classification process through SVM classifier.

Authors and Affiliations

Muthumari Paluchamy, D. Suganya, S. Ellammal

Keywords

Related Articles

Implementation of Wireless Sensor Hub to Support Protocols Interoperability

This Paper presents a wireless sensor hub which supports protocols interoperability such as MiWi and WiFi protocol. The wireless sensor network/hub (WSN) is a combination of sensing, computation, and communication in...

Scattered Access Control with Seclusion Support in Wireless Sensor Networks by SecureQ Protocol

A wireless sensor Network consists of spatially dispersed self-directed sensors to monitor the environment conditions. This work supports in-network top-k query process over uncertain data in a distributed wireless...

An Approach to Identify Node Clones in Wireless Sensor Networks

Sensor nodes that are deployed in hostile environments are susceptible to capture and compromise. An adversary may gain private information from these sensors, clone and logically deploy them in the network to launch...

Load balancing and a Gossip protocol for dynamic resource allocation in cloud Environment

The new emerging cloud computing technology is providing various services to users and organizations. Now we are focusing on Infrastructure as a service which allows customers to use resource multiplexing through vir...

Effect Self Loop Avoidance Weighted NDFA Method Using Fuzzy Cache Counter Classifier Algorithm for Efficient and Fastest Reachable Path in Travelling Networks

Now a days in computer path networks or travelling networks, the routing of vehicles or moving objects is mainly based on the best path. This will help in minimize the costs of paths in a place, city or any specified...

Download PDF file
  • EP ID EP27752
  • DOI -
  • Views 290
  • Downloads 2

How To Cite

Muthumari Paluchamy, D. Suganya, S. Ellammal (2013). Human Gait Based Gender Classification Using Various Transformation Techniques. International Journal of Research in Computer and Communication Technology, 2(11), -. https://europub.co.uk/articles/-A-27752