Sign Language Video Segmentation with Level Sets Fusing Color, Texture, Boundary and Shape Features

This paper presents a new and improved concept for segmenting gestures of sign language. The algorithmpresented extracts signs from video sequences under various non static backgrounds. The signs are segmented which are normally hands and head of the signing person by minimizing the energy function ofthe level set fused by various image characteristics such as colour, texture, boundary and shape information. From RGB color video three color planes are extracted and one color plane is used based on the contrasting environments presented by the video background. Texture edge map provides spatial information which makes the color features more distinctive for video segmentation. The boundary features are extracted by forming image edge map form the existing color and texture features. The shape of the sign is calculated dynamically and is made adaptive to each video frame for segmentation of occlude objects. The energy minimization is achieved using level sets. Experiments show that our approach provides excellent segmentation on signer videos for different signs under robust environments such asdiverse backgrounds, sundry illumination and different signers.