From 1970, object identification technologies have matured to a point at which many applications are becoming possible for visual substitution. Human vision is one of the very essential part and it plays the most important role in free movement of blind peoples in surrounding environment. Hence, over thousands of techniques have been founded on these subjects that propose a variety of object recognition products and services by developing new electronic devices for the blind. Visually impaired peoples need is to perform most navigational tasks, so visually impaired people are at disadvantage because necessary information about the surrounding environment is not available. The system aims to introduce a proposed system that restores a central function of the visual system which is the identification of surrounding objects. The object detection method is based on the local grayscale conversion concept. The simulation results using feature extraction algorithm and key-points matching showed good accuracy for recognizing objects. Thus, the contribution is to present the idea of a visual substitution system based on gray-scale conversation, features extractions and matching to recognize and provide audio output of objects in images.