Application analysis of improved LeNet5 model in library management

Abstract

Nowadays, libraries have been able to achieve intelligent book positioning and borrowing. However, the book disorder affects user experience and increase management burden. A book disorder recognition system based on LeNet5 optimization model is proposed to address this issue. Firstly, the overall recognition system is designed, including a wireless radio frequency identification module, a pre-processing module, an image recognition module, and a post-processing module. The image recognition module is the key to the model. The first two modules are the foundation of this module. Therefore, the Canny operator is used to design basic modules. Subsequently, in the TensorFlow deep learning framework, a recognition system based on the LeNet5 model is designed. The whitening is used to further improve model performance. In the experimental analysis, the results showed that the recognition accuracy of the model reached 97.97 %, with an average time of 182 s. Therefore, the character recognition system based on optimized LeNet5 network proposed in the study can help libraries achieve intelligent book shelving management.