Graph Navigation for Exploring Very Large Image Collections

Kai Uwe Barthel, Nico Hezel

2017

Abstract

We present a new approach to visually browse very large sets of untagged images. In this paper we describe how to generate high quality image descriptors/features using transformed activations of a convolutional neural network. These features are used to model image similarities, which again are used to build a hierarchical image graph. We show how such an image graph can be constructed efficiently. After investigating several browsing and visualization concepts, we found best user experience and ease of usage is achieved by projecting sub-graphs onto a regular 2D-image map. This allows users to explore the image graph similar to navigation services.

References

  1. Razavian, A., Azizpour, H., Sullivan J., Carlsson, S., “CNN Features Off-the-Shelf: An Astounding Baseline for Recognition.”, In CVPR Workshops 2014, pp.512-519.
  2. Barthel, K. U.; Hezel, N. and Mackowiak, R. (2015), ImageMap - Visually Browsing Millions of Images.,in Xiangjian He; Suhuai Luo; Dacheng Tao; Changsheng Xu; Jie Yang and Muhammad Abul Hasan, ed., MMM (2) , Springer, , pp. 287-290 .
  3. Barthel, K., Hezel, N., Mackowiak, R., (2015b), “Navigating a graph of scenes for exploring large video collections”. In 21st International Conference on Multimedia Modelling 2015, Part II, Springer, pp. 418-423.
  4. Barthel, K. U.; Hezel, N. and Mackowiak, R. (2015), Graph-Based Browsing for Large Video Collections in Xiangjian He; Suhuai Luo; Dacheng Tao; Changsheng Xu; Jie Yang and Muhammad Abul Hasan, ed., 'MMM (2)78 , Springer, , pp. 237-242.
  5. Chen, J.-Y.; Bouman, C. A. and Dalton, J. C. (1998), Similarity pyramids for browsing and organization of large image databases, in Bernice E. Rogowitz and Thrasyvoulos N. Pappas, ed., 'Human Vision and Electronic Imaging' , SPIE, pp. 563-575.
  6. He K., Zhang X., Ren S., Sun J. (2016) Identity Mappings in Deep Residual Networks. In: Leibe B., Matas J., Sebe N., Welling M. (eds) Computer Vision - ECCV 2016. ECCV 2016. Lecture Notes in Computer Science, vol. 9908. Springer, Cham.
  7. Heesch, D., (2008), A survey of browsing models for content based image retrieval. Multimedia Tools and Applications archive Volume 40 Issue 2, November 2008, pp. 261 - 284.
  8. Jing, Y., Rowley, H., Rosenberg, C., Wang, J., Zhao, M., Covell, M., (2010), In: IEEE International Conference on Multimedia and Expo, 2010, p 267.
  9. Krizhevsky, A.; Sutskever, I. and Hinton, G. E. (2012), ImageNet Classification with Deep Convolutional Neural Networks., in Peter L. Bartlett; Fernando C. N. Pereira; Christopher J. C. Burges; Léon Bottou and Kilian Q. Weinberger, ed., 'NIPS' , pp. 1106-1114 .
  10. Qiu, S.; Wang, X. and Tang, X. (2013), Visual Semantic Complex Network for Web Images., in 'ICCV' , IEEE Computer Society, , pp. 3623-3630 .
  11. Razavian, A. S., Azizpour, H., Sullivan, J., Carlsson, S., “CNN Features Off-the-Shelf: An Astounding Baseline for Recognition.”, CVPR Workshops 2014, pp. 512- 519.
  12. Russakovsky, O.; Deng, J.; Su, H.; Krause, J.; Satheesh, S.; Ma, S.; Huang, Z.; Karpathy, A.; Khosla, A.; Bernstein, M. S.; Berg, A. C. and Li, F.-F. (2015), 'ImageNet Large Scale Visual Recognition Challenge.78, International Journal of Computer Vision 115 (3), pp. 211-252.
  13. Schoeffmann, K.; Ahlstroem, D.; Bailer, W. and Cobarzan, C. (2013), 'The Video Browser Showdown: a live evaluation of interactive video search tools', International Journal of Multimedia Information Retrieval, Springer Verlag London , pp. 1-15.
  14. Strong, G.; Hoque, E.; Gong, M. and Hoeber, O. (2010), Organizing and Browsing Image Search Results Based on Conceptual and Visual Similarities., in George Bebis; Richard D. Boyle; Bahram Parvin; Darko Koracin; Ronald Chung; Riad I. Hammoud; Muhammad Hussain; Kar-Han Tan; Roger Crawfis; Daniel Thalmann; David Kao and Lisa Avila, ed., 'ISVC (2)78 , Springer, pp. 481-490 .
  15. Wang, J.; Jia, L. and Hua, X.-S. (2011), 'Interactive browsing via diversified visual summarization for image search results.78, Multimedia Syst. 17 (5), pp. 379- 391.
Download


Paper Citation


in Harvard Style

Barthel K. and Hezel N. (2017). Graph Navigation for Exploring Very Large Image Collections . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-226-4, pages 411-416. DOI: 10.5220/0006274804110416


in Bibtex Style

@conference{visapp17,
author={Kai Uwe Barthel and Nico Hezel},
title={Graph Navigation for Exploring Very Large Image Collections},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={411-416},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006274804110416},
isbn={978-989-758-226-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017)
TI - Graph Navigation for Exploring Very Large Image Collections
SN - 978-989-758-226-4
AU - Barthel K.
AU - Hezel N.
PY - 2017
SP - 411
EP - 416
DO - 10.5220/0006274804110416