CFP last date
20 May 2024
Call for Paper
June Edition
IJCA solicits high quality original research papers for the upcoming June edition of the journal. The last date of research paper submission is 20 May 2024

Submit your paper
Know more
Reseach Article

Real-time Visual Landmark Recognition in Multi-view Image Collections

by Kwisha Hitesh Gohil, Sonal Pravinbhai Rami
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 178 - Number 15
Year of Publication: 2019
Authors: Kwisha Hitesh Gohil, Sonal Pravinbhai Rami
10.5120/ijca2019918922

Kwisha Hitesh Gohil, Sonal Pravinbhai Rami . Real-time Visual Landmark Recognition in Multi-view Image Collections. International Journal of Computer Applications. 178, 15 ( May 2019), 57-61. DOI=10.5120/ijca2019918922

@article{ 10.5120/ijca2019918922,
author = { Kwisha Hitesh Gohil, Sonal Pravinbhai Rami },
title = { Real-time Visual Landmark Recognition in Multi-view Image Collections },
journal = { International Journal of Computer Applications },
issue_date = { May 2019 },
volume = { 178 },
number = { 15 },
month = { May },
year = { 2019 },
issn = { 0975-8887 },
pages = { 57-61 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume178/number15/30610-2019918922/ },
doi = { 10.5120/ijca2019918922 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T00:50:32.314108+05:30
%A Kwisha Hitesh Gohil
%A Sonal Pravinbhai Rami
%T Real-time Visual Landmark Recognition in Multi-view Image Collections
%J International Journal of Computer Applications
%@ 0975-8887
%V 178
%N 15
%P 57-61
%D 2019
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Research and advancement in the Convolution Neural Network have been capable of solving many computer vision problems with higher accuracy than humans at some time. This paper, presents CNN along with its various layers for easy understanding. CNN algorithm has been used here for the landmark recognition problem. In the 3D Visual Phrasing method, SfM has been used to reconstruct a 2D image of a landmark to its 3D image for better classification. To solve the problem of landmark recognition, various approaches have been put forward. Each approach mentioned in the paper is an enhancement of the previously mentioned approach to obtain greater accuracy in landmark recognition.

References
  1. Tang, Kevin, et al. "Improving image classification with location context." Proceedings of the IEEE international conference on computer vision. 2015.
  2. Sy, Angela, and Cynthia Day. "Geo-Locating Images: Where in the world was this picture taken?." (2016).
  3. Weyand, Tobias, Ilya Kostrikov, and James Philbin. "Planet-photo geolocation with convolutional neural networks." European Conference on Computer Vision. Springer, Cham, 2016.
  4. Hochreiter, Sepp, and Jürgen Schmidhuber. "Long short-term memory." Neural computation 9.8 (1997): 1735-1780.
  5. Snavely, Noah, Steven M. Seitz, and Richard Szeliski. "Photo tourism: exploring photo collections in 3D." ACM transactions on graphics (TOG). Vol. 25. No. 3. ACM, 2006.
  6. Snavely, Noah, Steven M. Seitz, and Richard Szeliski. "Modeling the world from internet photo collections." International journal of computer vision 80.2 (2008): 189-210.
  7. Wu, Changchang, et al. "Multicore bundle adjustment." Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. IEEE, 2011.
  8. Hao, Qiang, et al. "3d visual phrases for landmark recognition." Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 2012.
  9. Deng, Jia, et al. "Imagenet: A large-scale hierarchical image database." 2009 IEEE conference on computer vision and pattern recognition. Ieee, 2009.
  10. Goodfellow, Ian J., Jonathon Shlens, and Christian Szegedy. "Explaining and harnessing adversarial examples (2014)." arXiv preprint arXiv:1412.6572.
Index Terms

Computer Science
Information Sciences

Keywords

3D Visual Phrase CleverHans Convolution Neural Network Deep learning Keras Landmark Recognition Machine learning Object detection Pre-trained models TensorFlow