Browsing by Author "Zeng, Xianyi"

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item
    Construction of a prediction model for body dimensions used in garment pattern making based on anthropometric data learning
    (The Journal of The Textile Institute, 2017) Liu, Kaixuan; Wang, Jianping; Kamalha, Edwin; Li, Victoria; Zeng, Xianyi
    Using artificial intelligence to predict body dimensions rather than measuring them physically is a new research direction in apparel industry. If implemented, this technology can reduce costs and improve efficiency. In this paper, we proposed a back propagation artificial neural network (BP-ANN) model to predict pattern making-related body dimensions by inputting few key human body dimensions. In order to construct the proposed model, anthropometric measurements of 120 young females from the northeastern region of China were collected. The data were then used for training and the proposed model. The results showed that the prediction of the developed BP-ANN model is more accurate and stable than that of linear regression (LR) model. As great as the LR model was at pattern making, the BP-ANN model is even better. In the future, the precision of the proposed model can be further improved if the size of the learning data increases. The proposed method can be especially useful in making garment pattern for form-fitting clothing.
  • Thumbnail Image
    Item
    Fit evaluation of virtual garment try-on by learning from digital pressure data
    (Knowledge-Based Systems, 2017) Liu, Kaixuan; Zeng, Xianyi; Bruniaux, Pascal; Wang, Jianping; Kamalha, Edwin; Tao, Xuyuan
    Presently, garment fit evaluation mainly focuses on real try-on, and rarely deals with virtual try-on. With the rapid development of E-commerce, there is a profound growth of garment purchases through the internet. In this context, fit evaluation of virtual garment try-on is vital in the clothing industry. In this paper, we propose a Naive Bayes-based model to evaluate garment fit. The inputs of the proposed model are digital clothing pressures of different body parts, generated from a 3D garment CAD software; while the output is the predicted result of garment fit (fit or unfit). To construct and train the proposed model, data on digital clothing pressures and garment real fit was collected for input and output learning data respectively. By learning from these data, our proposed model can predict garment fit rapidly and automatically without any real try-on; therefore, it can be applied to remote garment fit evaluation in the context of e-shopping. Finally, the effectiveness of our proposed method was validated using a set of test samples. Test results showed that digital clothing pressure is a better index than ease allowance to evaluate garment fit, and machine learning-based garment fit evaluation methods have higher prediction accuracies.
  • Thumbnail Image
    Item
    Fuzzy classification of young women's lower body based on anthropometric measurement
    (International Journal of Industrial Ergonomics, 2016) Liu, Kaixuan; Wang, Jianping; Tao, Xuyuan; Zeng, Xianyi; Bruniaux, Pascal; Kamalha, Edwin
    The traditional method of body classification is discrete, using crisp and rather dichotomous classification methods; there are many shortcomings for ergonomic design of clothing products by this method. This paper proposes a fuzzy method to classify lower body shapes based on triangular fuzzy numbers. By using factor analysis and correlation analysis, we found that the height, the waist girth, and the difference of hip-waist are crucial dimensions to represent lower body shape. We then classified the lower body shape into three categories according to the difference of hip-to-waist, and finally used the membership of triangular fuzzy numbers to represent the lower body shapes. Results show that the fuzzy method of body classification can more accurately represents body information than the traditional method without increasing the number of body types. Additionally, we established that the mean of the height, waist girth and hip girth of the young women of northeast China increased by about 0.8 cm, 1.5 cm and 1.4 cm respectively compared with ten years ago. Relevance to industry: Anthropometric data is the basis of garment pattern design, and body classification is a necessary precondition for developing a garment size system. These research achievements will add value to the pattern design of young women's lower body clothing, the development of new sizing systems and related industries.
  • Thumbnail Image
    Item
    Garment Fit Evaluation Using Machine Learning Technology
    (Springer, 2018) Liu, Kaixuan; Zeng, Xianyi; Bruniaux, Pascal; Tao, Xuyuan; Kamalha, Edwin; Wang, Jianping
    Presently, garment fit evaluation mainly focuses on real try-on and rarely deals with virtual try-on.With the rapid development of e-commerce, there is a profound growth of garment purchases through the Internet. In this context, fit evaluation of virtual garment try-on is vital in the clothing industry. In this chapter, we propose a Naive Bayes-based model to evaluate garment fit. The inputs of the proposed model are digital clothing pressures of different body parts, generated from a 3D garment CAD software, while the output is the predicted result of garment fit (fit or unfit). To construct and train the proposed model, data on digital clothing pressures and garment real fit was collected for input and output learning data, respectively. By learning from these data, our proposed model can predict garment fit rapidly and automatically without any real try-on; therefore, it can be applied to remote garment fit evaluation in the context of e-shopping. Finally, the effectiveness of our proposed method was validated using a set of test samples. Test results showed that digital clothing pressure is a better index than ease allowance to evaluate garment fit, and machine learning-based garment fit evaluation methods have higher prediction accuracies.
  • Thumbnail Image
    Item
    Parametric design of garment flat based on body dimension
    (International Journal of Industrial Ergonomics, 2018) Liu, Kaixuan; Zeng, Xianyi; Wang, Jianping; Tao, Xuyuan; Xu, Jun; Jiang, Xiaowen; Ren, Jun; Kamalha, Edwin; Agrawal, Tarun-Kumar; Bruniaux, Pascal
    Garment flats have a wide application in product development production and designing stages. However, the traditional drawing methods of garment flat are very time-consuming, and need professional drawing skills. In this paper, a parametric design method was proposed based on body dimension to draw garment flats. The relations among human body, flats and garment show that a garment flat has a close relation with human body and real garment. Graphic analysis shows that a garment flat is constrained by two kinds of parameters: geometric and dimensional parameters. Then, the parametric relation model between garment flat and human body dimensions was constructed. According to the parametric relation model, all the dimensions of a garment flat can be represented by several dimensional parameters and style parameters. Finally, an application program (JFRS, 2016) based on the proposed method was developed to generate garment flats. The result shows that the proposed method is more effective than traditional methods. Moreover, the engineering design methods have been successfully applied to improve design efficiency in artistic design in this research. This is a novel research idea in the field of fashion design, and could be further applied in other design domains.