Survey of Image Retrieval via Visual Attention & Saliency Feature

  IJETT-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
  
© 2014 by IJETT Journal
Volume-12 Number-9
Year of Publication : 2014
Authors : Prof. Anand K. Hase , Prof. Baisa L. Gunjal
  10.14445/22315381/IJETT-V12P285

Citation 

Prof. Anand K. Hase , Prof. Baisa L. Gunjal. "Survey of Image Retrieval via Visual Attention & Saliency Feature ", International Journal of Engineering Trends and Technology (IJETT), V12(9),446-448 June 2014. ISSN:2231-5381. www.ijettjournal.org. published by seventh sense research group

Abstract

In the real world applications such as landmark search, copy protection, fake image detection, partial duplicate image retrieval is very important. In the internet era users regularly upload images which are partially duplicate images on the various domains. The partial image is only part of whole image, and the various kind of transformation involves scale, resolution, illumination, viewpoint. This technique is demanded by various real world applications and thus has attracted towards this research. In object based image retrieval methods usually use the whole image as the query. This technique has been compared with the text retrieval system by using the bag of visual words (BOV)[3]. There is lots of background noise in the images and impossible to perform interaction operation on the large scale database of the images. Two observations are notable as a user point of view. First, people show various objects or region through the images which are shared on the web, we also expect that the returned result also focus on the major parts or objects. Regions of interest are only found in salient region of the retrieval. Second, and the similar region in the returned result also identical to the salient region of the images. To filter out the non salient region from the image, which able to eliminate the background noise we introduce visual attention analysis technique. We also want to generate saliency region which having the expected visual contents.

References

[1] Liang Li and Shuqiang Jiang, “Partial image retrieval via saliency guided visual matching,” IEEE computer society, pp. 13_23
[2] Z. Wu et al., ‘‘Adding Affine Invariant GeometricConstraint for Partial-Duplicate Image Retrieval,’’Proc. 20th IEEE Conf. Pattern Recognition (ICPR), IEEE CS, 2010, pp. 842_845.
[3] J. Sivic and A. Zisserman, ‘‘Video Google: A TextRetrieval Approach to Object Matching in Videos,’’Proc. 2003 IEEE Conf. Computer Vision (ICCV),vol. 2, IEEE CS, 2003, pp. 1470_1477.
[4] M. Chen et al., ‘‘Global Contrast Based Salient Region Detection,’’ Proc. 2011 IEEE Conf. Computer Vision and Pattern Recognition (CVPR), IEEE CS, 2011, pp. 409_416.
[5] H. Jegou et al., ‘‘Aggregating Local Descriptorsinto a Compact Image Representation,’’Proc. 2010 IEEE Conf. Computer Vision andPattern Recognition (CVPR), IEEE CS, 2010,pp. 3304_3331.
[6] W. Zhou et al., ‘‘Spatial Coding for Large Scale Partial-Duplicate Web Image Search,’’ Proc. Int’l Conf. Multimedia, ACM, 2010 pp. 510_520.
[7] D. Qin et al., ‘‘Hello Neighbor: Accurate Object Retrieval with k-Reciprocal Nearest Neighbors,’’ Proc. 2011 IEEE Conf. Computer Vision and Pattern Recognition (CVPR), IEEE CS, 2010, pp. 777_784.
[8] Z. Wu et al., ‘‘Bundling Features for Large Scale Partial-Duplicate Web Image Search,’’ Proc. 2009 IEEE Conf. Computer Vision and Pattern Recognition (CVPR), IEEE CS, 2009, pp.25_32.
[9] F. Perronnin et al., ‘‘Large-Scale Image Retrieval with Compressed Fisher Vectors,’’ Proc. 2010 IEEE Conf. Computer Vision and Pattern Recognition (CVPR), IEEE CS, 2010,pp. 3384_3391.
[10] J. Philbin et al., ‘‘Lost in Quantization: Improving Particular Object Retrieval in Large Scale Image Databases,’’ Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR 08), IEEE CS, 2008.
[11] H. Wu et al., ‘‘Resizing by Symmetry-Summarization,’’ ACM Trans. Graphics, vol. 29, no. 6, 2010, article no. 159.
[12] P. Felzenszwalb and D. Huttenlocher, ‘‘Efficient Graph-Based Image Segmentation,’’ Int’l J. Computer Vision, vol. 59, no. 2, 2004, pp. 197_181.
[13] D.G. Lowe, ‘‘Distinctive Image Features fromScale Invariant Keypoints,’’ Int’l J. Computer Vision, vol. 60, no. 2, 2004, pp. 91_110.
[14] X. Wang et al., ‘‘Contextual Weighting for Vocabulary Tree Based Image Retrieval,’’ Proc. 2011 IEEEConf. Computer Vision (ICCV), IEEE CS, 2011,pp. 209_216.
[15] C. Rother, V. Kolmogorov, and A. Blake, ‘‘Grabcut: Interactive Foreground Extraction Using Iterated Graph Cuts,’’ ACM Trans. Graphics, vol. 23, no. 3, 2004, pp. 309_314.

References
Partial Duplicate Image, Bags of Visual Words (BOV), Visual Attention, Saliency Feature, Visually Salient & Rich Region.