A New Technique for Accurate Segmentation, and Detection of Outfit Using Convolution Neural Networks

  • Priyal Jain
  • Abhishek Kankani
  • D. Geraldine Bessie AmaliEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 862)


Wearable Detection is a societally and economically critical yet a very challenging issue because of the number of layers and clothing someone could be wearing. Also layering, pose, body style, and shape become an issue. In this paper, we handle the wearable detection issue using recovery approaches. For model picture, we use the comparable styles from substantial database—labeled pictures and utilize cases to perceive dress things in the inquiry. Our tests come about moreover show that the general posture estimation issue can profit by apparel detection. In addition, for the correct detection and classification of what a person is wearing, we use the process of image segmentation and pose estimation to segment the image into superpixels and then analyze accordingly. In addition, we use a large novel dataset and tools for labeling garment items, to retrieve similar style to help with clothing classification.


Conditional Random Field model Convoluted neural networks Nearest neighbor K—nearest neighbor Segmentation 


  1. 1.
    X. He, R.S. Zemel, M.A. Carreira-Perpinan, Multiscale conditional random fields for image labeling, in Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR (2004).
  2. 2.
    G. Mori, X. Ren, A.A. Efros, J. Malik, Recovering Human Body Configurations: Combining Segmentation and Recognition (2004).
  3. 3.
    Large-scale Fashion (DeepFashion) Database:
  4. 4.
    Y. Kalantidis, L. Kennedy, L.-J. Li, Getting the look-clothing recognition and segmentation for automatic product suggestions in everyday photos, in International Conference on Multimedia Retrieval (ICMR), ACM, Dallas, TX, (2013)Google Scholar
  5. 5.
  6. 6.
    L.-X. Chang, W.-D. Gao, X. Zhang, Discussion on fashion color forecasting researches for textile and fashion industries. J. Fiber Bioeng. Inform. 2. Scholar
  7. 7.
    J. Long, E. Shelhamer, T. Darrell, Convolutional networks for semantic segmentation, in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015).
  8. 8.
    P. Guan, A. Weiss, A.O. Balan, M.J. Black, Estimating human shape and pose from a single image. Published in 2009 IEEE 12th International Conference on Computer Vision.
  9. 9.
    J. Shotton, A. Fitzgibbon, M. Cook, T. Sharp, M. Finocchio, Real-time human pose recognition in parts from single depth images, in CVPR 2011 (2011).
  10. 10.
  11. 11.
    J. Lafferty, A. McCallum, A. McCallum, Conditional random fields: probabilistic models for segmenting and labeling sequence data, in ICML’01 Proceedings of the Eighteenth International Conference on Machine Learning, pp. 282–289 (2001)Google Scholar
  12. 12.
    S. Zheng, S. Jayasumana, B. Romera-Paredes, V. Vin, Conditional random fields as recurrent neural networks, in 2015 IEEE International Conference on Computer Vision (ICCV) (2015).
  13. 13.
  14. 14.
    L. Wang, J. Shi, G. Song, Object detection combining recognition and segmentation, in ACCV 2007: Computer Vision, pp. 189–199 (2007) Google Scholar
  15. 15.
    B. Lao, K. Jagadeesh, Convolutional neural networks for fashion classification and object detection, in CCCV 2015: Computer Vision, pp. 120–129Google Scholar
  16. 16.
    Z. Liu, P. Luo, S. Qiu, X. Wang, X. Tang, DeepFashion: powering robust clothes recognition and retrieval with rich annotations, in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016).

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Priyal Jain
    • 1
  • Abhishek Kankani
    • 1
  • D. Geraldine Bessie Amali
    • 1
    Email author
  1. 1.School of Computer Science and EngineeringVellore Institute of TechnologyVelloreIndia

Personalised recommendations