Title: The clothing image classification algorithm based on the improved Xception model

Authors: Zhuoyi Tan; Yuping Hu; Dongjun Luo; Man Hu; Kaihang Liu

Addresses: Information Institute, Guangdong University of Finance and Economics Guangzhou, No. 21, Luntou Road, Haizhu District, Guangzhou, 510320, Guangdong, China ' Information Institute, Guangdong University of Finance and Economics Guangzhou, No. 21, Luntou Road, Haizhu District, Guangzhou, 510320, Guangdong, China ' Information Institute, Guangdong University of Finance and Economics Guangzhou, No. 21, Luntou Road, Haizhu District, Guangzhou, 510320, Guangdong, China ' Information Institute, Guangdong University of Finance and Economics Guangzhou, No. 21, Luntou Road, Haizhu District, Guangzhou, 510320, Guangdong, China ' Information Institute, Guangdong University of Finance and Economics Guangzhou, No. 21, Luntou Road, Haizhu District, Guangzhou, 510320, Guangdong, China

Abstract: In recent years, the clothing industry develops rapidly under the great influence of internet. A large number of clothing images have been produced and how to accurately make a classification of such a wide range of clothing has become a research focus. In this paper, we propose a clothing image classification algorithm based on the improved Xception model. Firstly, the last fully connected layer of the original network is replaced with another fully connected layer to recognise eight classes instead of 1,000 classes. Secondly, the activation function we employ in our network adopts both exponential linear unit (ELU) and rectified linear unit (ReLU), which can improve the nonlinear and learning characteristics of the networks. Thirdly, in order to enhance the anti-disturbance capability of the network we employ a L2 regularisation method. Fourthly, we perform data augmentation on the training images to reduce over-fitting. Finally, the learning rate is set to zero in the layers of the first two modules of our network and we fine-tune the network. The experimental results show that the top-1 accuracy by the algorithm proposed in this paper is 92.19%, which is better than the state-of-the-art models of Inception-v3, Inception-ResNet-v2 and Xception.

Keywords: clothing image classification; transfer learning; deep convolutional neural network; Xception.

DOI: 10.1504/IJCSE.2020.111426

International Journal of Computational Science and Engineering, 2020 Vol.23 No.3, pp.214 - 223

Received: 28 Nov 2019
Accepted: 10 Jan 2020

Published online: 24 Nov 2020 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article