VLIW Processor Architecture Exploration for Facial-Feature and Component Extraction

The methods for face-detection and facial-feature and component extraction exist in the literature are different in their complexity, performance, type, and nature of the images and the targeted application. The facial features and components are used in medical diagnoses, security applications, robotics, and assistance for the disabled. We use these components and feature to determine the state of alertness and fatigue for medical diagnoses. In this work we use plain color background images whose color is different from the skin. The image contains a single face. We are interested in the VLIW processor architecture dedicated for this application. This dedicated architecture must meet two constraints, which are the execution time and the VLIW processor functional unit resources. We have selected and associated a face detection algorithm based on the skin detection (using the RGB space) with a facial-feature extraction algorithm based on tracking the gradient and applying the geometric model.