Research on classification of architectural style image based on convolution neural network
Kun Guo, Ning Li · 2017 IEEE 3rd Information Technology and Mechatronics Engineering Conference (ITOEC) · 2017
Deep learning is a new field in machine learning research. Convolution neural network is the most important factor in image recognition. This paper mainly focuses on the network design and parameter optimization of convolution neural network. This paper is first based on the traditional handwritten digital classification framework LeNet-5 to improve, and implements the test on the ten and twenty-five architectural style data set, and then based on ImageNet-k model design ideas to design a deep convolution neural network structure. The experimental results show that the deeper the network level, the more comprehensive the feature of the image, the better the training effect. In this paper, we study the network design and parameters optimization of convolution neural network, and summarize some practical rules of depth classification on image classification, which is very instructive to solve practical problems.