SMT product character recognition based on BP neural network

In this paper, we present an approach to recognizing characters in surface mount technology (SMT) product. The recognition rate of SMT product character is not very good, because of unexpected noise in SMT the product character image. An improved SMT product character recognition method is proposed which can improve the recognition rate. At first, the character image is changed into a gray image. Some appropriate image processing algorithms are used to eliminate the noise. Then, single character image is obtained after character segmentation and character normalization. Finally, a three-layer back propagation (BP) neural network module is constructed. In order to improve the convergence rate of the network and avoid oscillation and divergence, the BP algorithm with momentum item is used. As a result, the SMT product character recognition system is developed, and its implementation method and steps are introduced with practical examples. Experimental results indicate that the proposed character recognition can obtain satisfactory character-recognition rate and the recognition rate reached over by 98.6%.