Clothing Key Points Detection Algorithm Based on Cascade Convolutional Neural Network

With the development of deep learning, key points detection using deep convolutional neural networks(CNN) has attracted extensive attention. Although key points detection for human body posture and face recognition has developed rapidly, the application of this technology to clothing faces great challenges because of the variability of the background and posture in clothing pictures. Technology for clothing key points detection has great value for e-commerce and fashion collocation. To apply an algorithm for key point detection to fashion, in this paper, we propose an algorithm for clothing key points detection based on a cascade CNN. This algorithm first detects the key points of clothing and then adjusts difficult key points using a two-level cascade CNN. The first stage of the algorithm detects preliminary key points using ResNet to extract features, and then, to retain more detailed image information, uses dilated convolution to solve the problem of high receptive fields but low spatial resolution in the high-level feature map of a pyramid structure. Using the results from the first stage as a preliminary structure of key points, the accuracy is then improved in the second stage by adjusting the difficult key points by combining them with multi-scale features extracted by an hourglass network. We used the 2018 FashionAI clothing landmark dataset for training and testing in the experiment. The normalized error was reduced to 3.56% in the clothing landmark detection task, which verifies the effectiveness of the network. Compared with the existing algorithm for key points, the algorithm proposed in this paper achieves the best result in the task of clothing key points detection, especially in the detection of difficult key points. © 2020, Editorial Board of Journal of Tianjin University(Science and Technology). All right reserved.