Recognition of partially occluded target objects

This paper presents a new method of consistent object representation which can be used for partially occluded target object recognition. We proposed a boundary smoothing method for curvature estimation using a constrained regularization technique. Even though the method is effective in detecting corners due to the use of corner sharpness to increase the robustness of the proposed algorithm, it does not preserve corners well. We propose another approach to boundary smoothing for curvature estimation using a mean field annealing technique to improve the capability of detecting corners. It removes the noise while preserving corners very well. In addition, we show some matching results in an occlusion environment based on the corners detected by corner sharpness with the mean field annealing approach using a hybrid Hopfield (1985) neural network.