Costume Expert Recommendation System Based on Physical Features

  • Aihua DongEmail author
  • Qin Li
  • Qingqing Mao
  • Yuxuan Tang
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 849)


In this paper, we design a Costume Expert Recommendation System (CERS) based on customers’ physical features. First, we obtain images of customers, and use a multi-classifier model based on Support Vector Machine (SVM) to extract physical features of customers. The physical features include four features: skin-color, face-shape, shoulder-shape and body-shape. Second, CERS stores the specific physical feature of customers into the Fact Base of the Expert System. It then stores expert knowledge on costume matching into the rule base in the manner of production rules. Finally, the CERS adopts inference engine, namely, blackboard model algorithms to obtain the recommended costume that suits the physical features of the customer. Therefore, the proposed system provides customers an intelligent costume recommendation strategy in accordance with SVM and Expert System.


Support vector machine Expert system Physical features Costume recommendation 


  1. 1.
    Mundhe, M., Phadnis, S., Rathi, P., Aghav, J.: A beacon based retail industry analytics framework. Int. J. Web Sci. Eng. Smart Devices 4(1), 27–32 (2017)Google Scholar
  2. 2.
    Yang, E.K., Kim, S.-J.: 3D character virtual costume making software usability assessment—focusing on poser 3D character virtual costume making. J. Digital Des. 14(1), 863–876 (2014)CrossRefGoogle Scholar
  3. 3.
    Zheng A.: Research on apparel type recommendation method based on BP neural network, pp. 1–20. Cloth Institute, Zhejiang University of Science and Technology, Zhejiang (2010)Google Scholar
  4. 4.
    Kim, S., Han, D.S.: Real time traffic light detection algorithm based on color map and multilayer HOG-SVM. J. Broadcast Eng. 22(1), 62–69 (2017)CrossRefGoogle Scholar
  5. 5.
    Ibrahim, A.W., Sartep, H.: Grayscale image coloring by using YCbCr and HSV color spaces. Int. J. Mod. Trends Eng. Res. 4(4), 130–136 (2017)CrossRefGoogle Scholar
  6. 6.
    Agrawal, N., Bohra, S.: Face feature based extraction and classification for gender recognition and age estimation using fuzzy model: a review. Int. J. Recent Trends Eng. Res. 3(4), 146–148 (2017)CrossRefGoogle Scholar
  7. 7.
    Liu, Y., Zeng, L., Huang, Y.: An efficient HOG–ALBP feature for pedestrian detection. SIViP 8(S1), 125–134 (2014)CrossRefGoogle Scholar
  8. 8.
    Sunitha, B., Seetha, M.: Enhancing the performance of SVM classification based on fisher linear discriminant. Int. J. Res. Eng. Technol. 03(17), 48–54 (2014)CrossRefGoogle Scholar
  9. 9.
    Zamsuri, A., Syafitri, W., Sadar, M.: Web based cattle disease expert system diagnosis with forward chaining method. IOP Conf. Ser.: Earth Environ. Sci. 97, 012046 (2017)CrossRefGoogle Scholar
  10. 10.
    Mao, Q., Dong, A., Miao, Q., Pan, L.: Intelligent costume recommendation system based on expert system. J. Shanghai Jiaotong Univ. (Science) 23(2), 227–234 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.College of Information Science and TechnologyDonghua UniversityShanghaiChina
  2. 2.Tandon School of EngineeringNew York UniversityBrooklynUSA

Personalised recommendations