Automatic fabric pattern recognition and design based on deep learning and portable device

With the development of e‐commerce, online shopping has become the main approach to buy clothes, in which accurately classifying clothing through images becomes more and more important. However, most of clothing classification works focus on clothing types. With the increasing volume of online clothing transactions, various platforms have accumulated a large number of unmarked clothing images that cannot be fully utilized. Meanwhile, many consumers pay more attention to the clothing style. In order to solve this problem, this paper proposes a clothing style recognition framework based on Alex Net run on a portable device. The proposed clothing style recognition is evaluated on Deepfashion dataset. The experimental results show that the proposed clothing style recognition is superior to traditional convolutional neural network (CNN), ResNet and Bilinear convolutional neural network (Bilinear‐CNN).