Differential Study of Deep Network Based Image Retrieval Methods

Authors

  • Arpana Mahajan  Research Scholar, Department of Computer Engineering, Madhav University, Rajasthan, India
  • Dr. Sanjay Chaudhary  Research Supervisor, Department of Computer Engineering, Madhav University, Rajasthan, India

DOI:

https://doi.org//10.32628/CSEIT11953130

Keywords:

Image Retrieval, CNN, Alexnet, RCNN, RESNET, GoogleNet.

Abstract

Learning successful component portrayals and likeness measures are essential to the recovery execution of a substance based image recovery (CBIR) framework. In spite of broad research endeavors for quite a long time, it stays one of the most testing open issues that extensively thwarts the accomplishments of genuine world CBIR frameworks. The key test has been ascribed to the outstanding “semantic hole” issue that exists between low-level image pixels caught by machines and elevated level semantic ideas saw by a human. Among different methods, AI has been effectively examined as a conceivable course to connect the semantic hole in the long haul. Propelled by late triumphs of profound learning strategies for PC vision and different applications, in this paper, we endeavor to address an open issue: if profound learning is a desire for spanning the semantic hole in CBIR and how much upgrades in CBIR undertakings can be accomplished by investigating the cutting edge profound learning procedures for learning highlight portrayals and comparability measures. In particular, we research a structure of profound learning with application to CBIR assignments with a broad arrangement of exact investigations by inspecting cutting edge profound learning strategies for CBIR undertakings under shifted settings. From our experimental investigations, we locate some promising outcomes and abridge some significant bits of knowledge for future research.

References

  1. Available at: http://wn- similarity.sourceforge.net/ [Accessed on 15 may 2017].
  2. C.-Y. Lee, S. Xie, P. Gallagher, Z. Zhang, and Z. Tu. Deeplysupervised nets. arXiv:1409.5185, 2014.
  3. Cun. Overfeat: Integrated recognition, localization and detection using convolutional networks. In ICLR, 2014.
  4. Dong-Chul Park, “Image Classification Using Naïve Bayes Classifier”, in International Journal of Computer Science and Electronics Engineering, vol. 4 , pp. 135-139, 2016
  5. Finlayson and Mark Alan “Java Libraries for Accessing the Princeton Wordnet: Comparison and Evaluation” in Proceedings of the 7th International Global WordNet Conference, 2014, pp. 78-85 .
  6. G. Mont´ufar, R. Pascanu, K. Cho, and Y. Bengio. On the number of linear regions of deep neural networks. In NIPS, 2014.
  7. I. J. Goodfellow, D. Warde-Farley, M. Mirza, A. Courville, and Y. Bengio. Maxout networks. arXiv:1302.4389, 2013.
  8. Internet: https://en.wikipedia.org/wiki/Semantic_gap, Apr. 2016.
  9. K. Chatfield, V. Lempitsky, A. Vedaldi, and A. Zisserman. The devil is in the details: an evaluation of recent feature encoding methods. In BMVC, 2011.
  10. K. He and J. Sun. Convolutional neural networks at constrained time cost. In CVPR, 2015.
  11. K. He, X. Zhang, S. Ren, and J. Sun. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In ICCV, 2015.
  12. K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. In ICLR, 2015.
  13. M. D. Zeiler and R. Fergus. Visualizing and understanding convolutional neural networks. In ECCV, 2014.
  14. M. Everingham, L. Van Gool, C. K. Williams, J. Winn, and A. Zisserman. The Pascal Visual Object Classes (VOC) Challenge. IJCV, pages 303–338, 2010.
  15. MATLAB and Statistics Toolbox Release 2013a, The MathWorks, Inc., Natick, Massachusetts, United States
  16. R. Girshick, J. Donahue, T. Darrell, and J. Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. In CVPR, 2014.
  17. R. Girshick. Fast R-CNN. In ICCV, 2015.
  18. R. K. Srivastava, K. Greff, and J. Schmidhuber. Highway networks. arXiv:1505.00387, 2015.
  19. R. K. Srivastava, K. Greff, and J. Schmidhuber. Training very deep networks. 1507.06228, 2015.
  20. T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Doll´ar, and C. L. Zitnick. Microsoft COCO: Common objects in context. In ECCV. 2014.
  21. Ted Pedersen, WordNet::Similarity. [Online]
  22. X. Li, T. Uricchio, L. Ballan, M. Bertini, C. Snoek, and A. Del Bimbo, “Socializing the semantic gap: A comparative survey on image tag assignment, refinement and retrieval,” in ACM Computing Surveys, 2016, in press.
  23. Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell. Caffe: Convolutional architecture for fast feature embedding. arXiv:1408.5093, 2014.

IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology

Downloads

Published

2019-03-30

Issue

Volume 5, Issue 2, March-April-2019

Section

Research Articles

License

Copyright (c) IJSRCSEIT

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Arpana Mahajan, Dr. Sanjay Chaudhary, " Differential Study of Deep Network Based Image Retrieval Methods, IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 5, Issue 2, pp.1310-1315, March-April-2019. Available at doi : https://doi.org/10.32628/CSEIT11953130