The Research and Application of Image Recognition Based on Improved BP Algorithm

Abstract

Neural network has self-learning and adaptive ability, and has strong fault tolerance and robustness, so it has a broad applications in the pattern recognition. In this paper, we adopt an improved BP algorithm - Flexible BP algorithm (RPROP) in the image recogntion, and we used it to simulate the image recognition in this field of pattern recognition application . The results of the expriments show that this method can better overcome the shortcoming that use the BP algorithm trained the network, which may fall into the local minimum values, and the method has better improvement in the convergence precision and identification speed.