(A) study on corner-based recognition method for occluded objects using fuzzy logic

Abstract

A robust object recognition algorithm which can be used in production line is developed. Gray level corner is selected as a local feature, and a real-time gray level corner detector is developed. The gray level corner detection problem is formulated as a pattern classification problem to determine whether a pixel belongs to the class of corners or not. The probability density function is estimated by means of fuzzy logic. For the purpose of localizing gray level corners, a one-pass local maximum point detector is developed. Also, hardware implementation of the developed algorithm is studied to detect the corners in real time. An efficient corner matching algorithm is developed to minimize the amount of calculation. To reduce the amount of calculation, all available information from the gray level corner detector is used to make model. This information has uncertainties due to discretization noise and geometric distortion, and this is represented by fuzzy rule base which can represent and handle the uncertainties. From fuzzy inference procedure, a matched segment list is extracted, and resulted segment list is used to calculate the transformation between object of model and scene. In order to reduce the fuzzy rule set, an overlapping cost to minimize the matched segment list is introduced. To reduce the false hypotheses, a vote and re-vote method is developed. Also an auto tuning scheme of the fuzzy rule base is developed to find out the uncertainties of features from recognized results automatically. Overall design is focused on the development of corner-based recognition algorithm which can be used in production line. To show the effectiveness of the developed algorithm, simulations and experiments are conducted for synthetic images and images of real electronic components.