Hand segmentation becomes a challenging task due to uncontrolled environmental conditions, lighting, rapid motion of the hand and skin colour detection. This paper’s objective is to propose a saliency-based colour model algorithm for hand segmentation under constrained and non-constrained environments. We already have colour models for hand segmentation algorithms, but in this work, we are proposing a new model for the segmentation process. Researchers are actively engaged in hand segmentation to attain natural interaction with a machine. A secondary objective of this paper is to excel in the region of skin color detection for human-like interaction between the end user and the computer. Human-computer interaction is achieved by hand gestures. To make hand gesture identification accurate, we may need to segment the hand from the background. The proposed work in this paper leads to solving the first problem in human-computer interaction. © BEIESP.