Clothing Image Recognition and Classification Based on Deep Learning

Abstract

With the development of the Internet of Things, big data, artificial intelligence, the rapid economic growth and the improvement of human living standards, in the field of intelligent image recognition, the application research based on clothing recognition and classification has received more and more attention. The purpose of this paper is to study clothing image recognition and classification based on deep learning. The convolutional neural network and residual network are introduced, and the clothing image dataset used in this paper is introduced and explained in detail. Three different convolutional neural networks based on single-task learning are designed for the obtained clothing dataset, these networks are: conventional convolutional neural network, convolutional neural network including Inception module, Inception module and residual module Convolutional Neural Networks. The experimental results show that the performance of the third convolutional neural network model is better, and the training time is only 21 h, and it can achieve better classification results.