An Implementation of Human Body Extraction Mechanism Based on Multi-Level Image Segmentation and Spline Regression From Single Images

Abstract

Imaging of human body segments is demanding task which supports many applications such as understanding of scenes and recognition of activities. A bottom-up technology for extracting human bodies automatically from a single image, in case of almost upright position, is the available technique in cluttered environments. The dimension, position and face color are used for localizing human body, model construction of upper and lower body as per anthropometric constraints and skin color calculation. A highest level pose can be extracted by combining different levels of segmentation granularity. Jointly estimating the foreground and background during the body part search phase gives rise to the segments of the human body, that alleviates the need for shape matching exactly.A novel approach for extraction of standing human bodies has proposed in this paper where the highly dimensional pose space, scene density, and various human appearances are handled in a better way compared to conventional state of art methods. The proposed approach is classified into five different steps (a) face detection, (b) multi level segmentation, (c) skin detection, (d) upper body segmentation and (e) lower body segmentation respectively. Finally the simulation results have achieved better performance and high efficiency over traditional state of art methods.