Reconfigurable Hardware Architecture of a Shape Recognition System Based on Specialized Tiny Neural Networks With Online Training

Neural networks are widely used in pattern recognition, security applications, and robot control. We propose a hardware architecture system using tiny neural networks (TNNs) specialized in image recognition. The generic TNN architecture allows for expandability by means of mapping several basic units (layers) and dynamic reconfiguration, depending on the application specific demands. One of the most important features of TNNs is their learning ability. Weight modification and architecture reconfiguration can be carried out at run-time. Our system performs objects identification by the interpretation of characteristics elements of their shapes. This is achieved by interconnecting several specialized TNNs. The results of several tests in different conditions are reported in this paper. The system accurately detects a test shape in most of the experiments performed. This paper also contains a detailed description of the system architecture and the processing steps. In order to validate the research, the system has been implemented and configured as a perceptron network with back-propagation learning, choosing as reference application the recognition of shapes. Simulation results show that this architecture has significant performance benefits.

I. Introduction

One of the major problems in computer vision is to build systems with the ability to identify shapes in real world scenarios [1]–[7]. The target application of this paper is the correct identification of road traffic signs in images taken by a car-mounted camera [8], [9]. The basic technique used for this in most applications, known as pattern matching, is to compare each portion of an image with a set of known models. The approach taken in this paper is to use specialized tiny neural networks (TNNs), which are explained in Section III, making it possible to use a massively parallel architecture efficiently. One of the most important features of artificial neural networks (ANNs) is their learning ability. Size and real-time considerations show that on-chip learning is necessary for a large range of applications [3].