Research on Image Classification Algorithm Based on Convolutional Neural Network-TensorFlow

Abstract

Image Classification is one of the important processing methods in the field of image processing. Traditional Classification algorithms, such as KNN (K-NearestNeighbor), have been unable to meet the accuracy standards of image Classification. And convolutional neural networks (CNN) are increasingly used to solve the problem of image classification. This paper briefly ces the convolutional neural network, which is constructed using the TensorFlow deep learning framework, and conducts experiments on 2000 pieces of custom data set of 10 classification obtained by crawler technology. At the same time, a comparative experiment is conducted on the traditional image classification KNN algorithm. Experimental results show that the application of convintroduolutional neural network in image classification has relatively large advantages, and the accuracy has been greatly improved.