ABSTRACT
The bag-of-features model is often deployed in content-based image retrieval to measure image similarity. In cases where the visual appearance of semantically similar images differs largely, feature histograms mismatch and the model fails. We increase the robustness of feature histograms by automatically augmenting them with features of related images. We establish image relations by image web construction and adapt a label propagation scheme from the domain of semi-supervised learning for feature augmentation. While the benefit of feature augmentation has been shown before, our approach refrains from the use of semantic labels. Instead we show how to increase the performance of the bag-of-features model substantially on a completely unlabeled image corpus.
- Y. Bengio, O. Delalleau, and N. Le Roux. Label Propagation and Quadratic Criterion. In O. Chapelle, B. Schölkopf, and A. Zien, editors, Semi-Supervised Learning, pages 193--216. MIT Press, 2006.Google Scholar
- G. Bradski. The OpenCV Library. Dr. Dobb's Journal of Software Tools, 2000.Google Scholar
- O. Chum, J. Philbin, J. Sivic, M. Isard, and A. Zisserman. Total recall: Automatic query expansion with a generative feature model for object retrieval. In IEEE International Conference on Computer Vision, 2007.Google ScholarCross Ref
- K. Heath, N. Gelfand, M. Ovsjanikov, M. Aanjaneya, and L. Guibas. Image webs: Computing and exploiting connectivity in image collections. In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, pages 3432--3439, june 2010.Google ScholarCross Ref
- H. Jegou, M. Douze, and C. Schmid. Hamming embedding and weak geometric consistency for large scale image search. In Proceedings of the 10th European Conference on Computer Vision: Part I, ECCV '08, pages 304--317, Berlin, Heidelberg, 2008. Springer-Verlag. Google ScholarDigital Library
- Y.-h. Kuo, H.-t. Lin, W.-h. Cheng, Y.-h. Yang, and W. H. Hsu. Unsupervised auxiliary visual words discovery for large-scale image object retrieval. Discovery, 1(c):1--8, 2011.Google ScholarDigital Library
- D. G. Lowe. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision, 60(2):91--110, Nov. 2004. Google ScholarDigital Library
- J. Matas, O. Chum, U. Martin, and T. Pajdla. Robust wide baseline stereo from maximally stable extremal regions. In Proceedings of British Machine Vision Conference, volume 1, pages 384--393, London, 2002.Google ScholarCross Ref
- K. Mikolajczyk and C. Schmid. Scale & affine invariant interest point detectors. Int. J. Comput. Vision, 60(1):63--86, Oct. 2004. Google ScholarDigital Library
- K. Mikolajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, T. Kadir, and L. V. Gool. A comparison of affine region detectors. International Journal of Computer Vision, 65(1/2):43--72, 2005. Google ScholarDigital Library
- M. Muja and D. G. Lowe. Fast approximate nearest neighbors with automatic algorithm configuration. In International Conference on Computer Vision Theory and Application VISSAPP'09), pages 331--340. INSTICC Press, 2009.Google Scholar
- J. Philbin, O. Chum, M. Isard, J. Sivic, and A. Zisserman. Object retrieval with large vocabularies and fast spatial matching. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2007.Google ScholarCross Ref
- J. Sivic and A. Zisserman. Video Google: A text retrieval approach to object matching in videos. In Proceedings of the International Conference on Computer Vision, volume 2, pages 1470--1477, Oct. 2003. Google ScholarDigital Library
- G. Yu and J.-M. Morel. ASIFT: An Algorithm for Fully Affine Invariant Comparison. Image Processing On Line, 2011, 2011.Google Scholar
Index Terms
- Feature propagation on image webs for enhanced image retrieval
Recommendations
A Novel Image Retrieval Algorithm Based on ROI by Using SIFT Feature Matching
MMIT '08: Proceedings of the 2008 International Conference on MultiMedia and Information TechnologyThis paper provides a novel content-based image retrieval algorithm based on ROI (Region Of Interest) by using SIFT (Scale Invariant Feature Transform) feature matching. SIFT descriptors, which are invariant to image scaling and transformation and ...
Histogram refinement for texture descriptor based image retrieval
Texture descriptors such as local binary patterns (LBP) have been successfully employed for feature extraction in image retrieval algorithms because of their high discriminating ability and computational efficiency. In this paper, we propose histogram ...
Application of wavelet decomposition and gradient variation in texture image retrieval
MUSP'08: Proceedings of the 8th WSEAS International Conference on Multimedia systems and signal processingTexture gradient is a popular operation for extracting features used for content-based image retrieval (CBIR) of texture images. It is useful for depicting gradient magnitude and direction of adjacent pixels in an image. In this thesis, we proposed two ...
Comments