ABSTRACT
In recent years, the Bag-of-Words (BoW) model has been widely used in most state-of-the-art large-scale image retrieval systems. However, the standard BoW based systems suffer from low discriminative power of local features as well as quantization errors that significantly affect the retrieval performance. In this paper, twin feature is employed and well combined with two advanced techniques including Hamming Embedding (HE) and Multiple Assignment (MA) to construct a discriminative image retrieval system on BoW representation in an efficient way. Experimental results on two benchmark datasets Oxford5k and Paris6k demonstrate that the proposed technique can greatly refine the visual matching process and enhance the final performance for image retrieval.
- Y. Cao, C. Wang, Z. Li, L. Zhang, and L. Zhang. Spatial-bag-of-features. In Proc. CVPR'10, pages 3352--3359, 2010.Google Scholar
- M. Fischler and R. Bolles. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6):381--395, 1981. Google ScholarDigital Library
- H. Jégou, M. Douze, and C. Schmid. Hamming embedding and weak geometric consistency for large scale image search. In Proc. ECCV'08, pages 304--317, 2008. Google ScholarDigital Library
- H. Jégou, M. Douze, and C. Schmid. Improving bag-of-features for large scale image search. IJCV, 87(3):316--336, May 2010. Google ScholarDigital Library
- H. Jégou, H. Harzallah, and C. Schmid. A contextual dissimilarity measure for accurate and efficient image search. In Proc. CVPR'07, pages 1--8, 2007.Google ScholarCross Ref
- D. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 60(2):91--110, Nov. 2004. Google ScholarDigital Library
- K. Mikolajczyk and C. Schmid. Scale and affine invariant interest point detectors. IJCV, 60(1):63--86, Oct. 2004. Google ScholarDigital Library
- D. Nister and H. Stewenius. Scalable recognition with a vocabulary tree. In Proc. CVPR'06, pages 2161--2168, 2006. Google ScholarDigital Library
- J. Philbin, R. Arandjelovic, and A. Zisserman. Flickr100k image dataset, http://www.robots.ox.ac.uk/~vgg/data/oxbuildings/flickr100k.html.Google Scholar
- J. Philbin, R. Arandjelovic, and A. Zisserman. Oxford5k image dataset. http://www.robots.ox.ac.uk/vgg/data/oxbuildings/.Google Scholar
- J. Philbin, O. Chum, M. Isard, J. Sivic, and A. Zisserman. Object retrieval with large vocabularies and fast spatial matching. In Proc. CVPR'07, pages 1--8, 2007.Google ScholarCross Ref
- J. Philbin, O. Chum, M. Isard, J. Sivic, and A. Zisserman. Lost in quantization: Improving particular object retrieval in large scale image databases. In Proc. CVPR'08, pages 1--8, 2008.Google ScholarCross Ref
- J. Philbin and A. Zisserman. Paris6k image dataset. http://www.robots.ox.ac.uk/vgg/data/parisbuildings/.Google Scholar
- J. Sivic and A. Zisserman. Video google: A text retrieval approach to object matching in videos. In Proc. ICCV'03, pages 1470--1477, Oct. 2003. Google ScholarDigital Library
- L. Wang, H. Wang, and F. Zhu. Twin feature and similarity maximal matching for image retrieval. In Proc. ICMR'15, 2015. Google ScholarDigital Library
- P. Xu, L. Zhang, K. Yang, and H. Yao. Nested-SIFT for efficient image matching and retrieval. MultiMedia, 430(3):34--46, 2013. Google ScholarDigital Library
Index Terms
- Improving bag-of-words representation with efficient twin feature integration
Recommendations
A new bag-of-words model using multi-cue integration for image retrieval
Bag-of-words-based BoW image retrieval has been the most popular method in the image retrieval field. In traditional BoW scheme, the whole scheme for image retrieval utilises only one feature. The images are represented by the visual vocabulary ...
Improving feature matching strategies for efficient image retrieval
A number of state-of-the-art image retrieval systems have been built upon non-aggregated techniques such as Hamming Embedding (HE) and Selective Match Kernel (SMK). However, the retrieval performances of these techniques are directly affected by the ...
Multi-index structure based on SIFT and color features for large scale image retrieval
During the past few years, the Bag-of-Words (BoW) model based on SIFT features has been one of the most adopted approaches by the Content-Based Image Retrieval (CBIR) systems. However, these CBIR systems have shown some weaknesses and shortcomings ...
Comments