关键词: LeNet-5网络, 跨连连接, Inception V1模块, 图像分类

Abstract: Although the LeNet-5 Convolutional Neural Network（CNN） achieves good classification results in handwritten digit recognition, the classification accuracy is not high on datasets with complex texture features. In order to improve the accuracy of network class-ification on complex texture feature images, an improved LeNet-5 network structure is proposed. The idea of cross-connection is introduced to make full use of the low-level features of network extraction. The Inception V1 module is embedded in the LeNet-5 convolutional neural network to extract multi-scale features of the image. The output layer uses the softmax function to classify the image. Experimental results on the Cifar-10 and Fashion MNIST dataset show that the improved convolutional neural network has good classification ability on complex texture feature datasets.

Key words: LeNet-5 network, cross-connection, Inception V1 module, image classification