Contour Object Generation Method for Object Recognition Using FPGA

Abstract

The article presents a method for obtaining the contour of an object in real time from non-binarized images for recognition purpose. The contour information is integrated into a descriptive vector named BOF used by a FuzzyARTMAP Artificial Neural Network (ANN) model to learn the object and then recognize it later. In this way, it is possible to obtain a learning process regarding the location and recognition of parts; to communicate to a robot arm the position and orientation information of an object for assembly purposes. Other method to obtain contour using binarized images, is compared with the described method in this paper in order to implement and test both in a Field Programmable Gate Array (FPGA) architecture. Since an ANN can be implemented more efficiently in a parallel structure such as FPGA architecture can supply, it is desirable to implement an efficient algorithm for obtaining the object contour in the same way.