Probabilistic modelbased object recognition using local zernike moments

Object recognition is one of the most important, yet the least understood, aspect of visual perception. The difficulties originate from the variations of objects such as view position, illumination changes, background clutter, occlusion and etc. In this paper, we present an object recognition paradigm robust to these variations using modified local Zernike moments and the probabilistic voting method. We propose a feature which is robust to scale, rotation, illumination change and background clutter. A probabilistic voting scheme maximizes the conditional probability defined by the features in correspondence to recognize an object of interest. Results from the experiments show the robustness of the proposed system.