Simulation of early vision mechanisms and application to object shape recognition

摘要

In early stages of vision, the images are processed to generate "maps" or point-by point distributions of values of various quantities including the edge elements, fields of local motion, depth maps and color constancy, etc. These features are then refined and processed in visual cortex. The next stage is recognition which also leads to simple control of behaviors such as steering and obstacle avoidance, etc. In this paper we present a system for object shape recognition that utilizes the features extracted by use of human vision model. The first block of the system performs processing analogous to that in retina for edge feature extraction. The second block represents the processing in visual cortex, where features are refined and combined to form a stimulus to be presented to the recognition model. We use the normalized distances of the edge pixels from the mean to form a feature vector. The next block that accomplishes the task of recognition consists of a counterpropagation neural network model. We use gray scale images of 3D objects to train and test the performance of the system. The experiments show that the system can recognize the objects with some variations in rotation, scaling and translation.