Advertisement

Extracting Clothing Features for Blind People Using Image Processing and Machine Learning Techniques: First Insights

  • Daniel RochaEmail author
  • Vítor CarvalhoEmail author
  • Filomena SoaresEmail author
  • Eva OliveiraEmail author
Conference paper
  • 408 Downloads
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 34)

Abstract

Vision is one of the senses that dominates the life of humans. It allows them to know and have the perception of the world around them, while giving meaning for objects, concepts and ideas, and tastes. How to dress and the style we prefer for different occasions is part of one’s identity. Blind people do not have this sense, and dressing can be a difficult and stressful task. With the advance of technology it is important to minimize all the limitations of a blind person in the management of garments. Not knowing the colors, the type of pattern, or even the state of the garments make this a daily challenge in which nowadays resources are not the best. Thus, the approach of this project is to address this issue of extracting the basic characteristics and conditions of the garment (in good conditions, dirty or wrinkly) in order to help the blind.

Keywords

Clothes recognition Blind people Image processing Machine learning 

Notes

Acknowledgments

This work has the support of Association of the Blind and Amblyopes of Portugal (ACAPO) and Association of Support for the Visually Impaired of Braga, Portugal (AADVDB). Their considerations gave (and still give) this project the first insights to a viable solution for the blind people community.

References

  1. 1.
    Rocha, D., Carvalho, V., Oliveira, E., et al.: MyEyes-automatic combination system of clothing parts to blind people: first insights. In: 2017 IEEE 5th International Conference Serious Games Applications for Health (SeGAH), pp. 1–5 (2017)Google Scholar
  2. 2.
    Rocha, D., Carvalho, V., Oliveira, E.: MyEyes - automatic combination system of clothing parts to blind people: prototype validation. In: Sensordevices’ 2017 Conference. Rome, Italy, 10–14 September 2017Google Scholar
  3. 3.
    Rocha, D., Carvalho, V., Gonçalves, J., et al.: Development of an automatic combination system of clothing parts for blind people: MyEyes. Sensors Transducers 219, 26–33 (2018)Google Scholar
  4. 4.
    Pal, N.R., Pal, S.K.: A review on image segmentation techniques. Pattern Recognit. 26, 1277–1294 (1993).  https://doi.org/10.1016/0031-3203(93)90135-JCrossRefGoogle Scholar
  5. 5.
    Yamaguchi, K., Kiapour, M.H., Ortiz, L.E., Berg, T.L.: Parsing clothing in fashion photographs. In: 2012 IEEE Conference Computer Vision Pattern Recognition (CVPR), pp. 3570–3577 (2012)Google Scholar
  6. 6.
    Yamaguchi, K., Kiapour, M.H., Ortiz, L.E., Berg, T.L.: Retrieving similar styles to parse clothing. IEEE Trans. Pattern Anal. Mach. Intell. 37, 1028–1040 (2015).  https://doi.org/10.1109/TPAMI.2014.2353624CrossRefPubMedGoogle Scholar
  7. 7.
    Wazarkar, S., Keshavamurthy, B.N.: Fashion image classification using matching points with linear convolution. Multimed. Tools Appl. 77, 25941–25958 (2018).  https://doi.org/10.1007/s11042-018-5829-4CrossRefGoogle Scholar
  8. 8.
    Manfredi, M., Grana, C., Calderara, S., Cucchiara, R.: A complete system for garment segmentation and color classification. Mach. Vis. Appl. 25, 955–969 (2014).  https://doi.org/10.1007/s00138-013-0580-3CrossRefGoogle Scholar
  9. 9.
    Liang, X., Lin, L., Yang, W., et al.: Clothes Co-parsing via joint image segmentation and labeling with application to clothing retrieval. IEEE Trans. Multimed. 18, 1175 (2016).  https://doi.org/10.1109/TMM.2016.2542983CrossRefGoogle Scholar
  10. 10.
    Yuan, S., Tian, Y., Arditi, A.: Clothing matching for visually impaired persons. Technol. Disabil. 23, 75–85 (2011).  https://doi.org/10.3233/TAD-2011-0313CrossRefPubMedPubMedCentralGoogle Scholar
  11. 11.
    Yang, X., Yuan, S., Tian, Y.: Assistive clothing pattern recognition for visually impaired people. IEEE Trans. Hum.-Mach. Syst. 44, 234–243 (2014).  https://doi.org/10.1109/THMS.2014.2302814CrossRefGoogle Scholar
  12. 12.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, pp 886–893 (2005)Google Scholar
  13. 13.
    Sharma, A., Sharma, A.: Machine learning: a review of techniques of machine learning (2018)Google Scholar
  14. 14.
    Muñoz, A., Moguerza, J.M., Venturini, G.A.M.: Support vector machines (2019)Google Scholar
  15. 15.
    Salsa Jeans ® | Jeans, Roupa e Acessórios para Mulher e Homem. https://www.salsajeans.com/pt/?gclid=CjwKCAjwscDpBRBnEiwAnQ0HQH6hls7uDEkOZMqwWww5E68wLSveKTqnIN4OYskqR5VFZtkpzwS-LRoCrEsQAvD_BwE. Accessed 19 Jul 2019
  16. 16.
    Dlib C++ library. http://dlib.net/. Accessed 11 Jul 2019
  17. 17.
    Fashion MNIST | Kaggle. https://www.kaggle.com/zalando-research/fashionmnist. Accessed 15 Jul 2019
  18. 18.
    Train your first neural network: basic classification | TensorFlow Core | TensorFlow. https://www.tensorflow.org/tutorials/keras/basic_classification. Accessed 21 Jul 2019

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Algoritmi R&DUniversity of MinhoGuimarãesPortugal
  2. 2.2Ai Lab, School of TechnologyIPCABarcelosPortugal

Personalised recommendations