Gait-Based Gender Classification Using Kinect Sensor

• Published in: Association for Engineering Education - Engineering Library Division Papers p. 26.808.1
• Main Authors: Eltaher, Mohammed, Yang, Yawei, Lee, Jeongkyu
• Format: Conference Proceeding
• Language: English
• Published: Atlanta American Society for Engineering Education-ASEE 14.06.2015
• Subjects: Classification; Datasets; Feature extraction; Gait; Gender; Representations; Sensors; Training; Walking
• DOI: 10.18260/p.24145

Gait-Based Gender Classification Using Kinect Sensor Abstract. Gender classification plays an important role in many applications such assurveillance systems and medical applications. Most of approaches for genderclassification are based on features of human face, voice and gait. Among theseapproaches, gait-based approaches are becoming more and more popular since the waythat they collect human gait information is non-contact and non-invasive. In this paper,we propose a novel method to classify human gender using their gaits. For the gait-basegender classification, we collect silhouettes of human walking pattern from MicrosoftKinect sensor, and extract two main gait features, i.e., Gait Energy Image (GEI) andDenoised Energy Image (DEI) from a sequence of an entire cycle of walking silhouetteimages. GEI is an appearance-based gait representation while DEI is used to removethe noises from GEI. For the gait features, we use a low dimensional feature vector torepresent the gait features. The extracted feature dataset are divided into two parts, i.e.,training and testing datasets. The training data set are used for training a SupportVector Machine (SVM) classifier while the testing dataset are used for the evaluation.Figure 1 shows overall procedure of proposed gait-based gender classification systemusing Microsoft Kinect sensor. Despite of the limitation of the dataset, i.e., differentraces and thickness of clothes which weaken the distinct differences between males andfemales, the average accuracy of the proposed approach reaches up to 87% under 10-folds validation. According to the experimental results, we know that GEI is anapplicable feature for human gait representation.Figure 1 General design of the system.