How to Use SIFT Vectors to Analyze an Image with Database Templates
During last years, local image descriptors have received much attention because of their efficiency for several computer vision tasks such as image retrieval, image comparison, features matching for 3D reconstruction... Recent surveys have shown that Scale Invariant Features Transform (SIFT) vectors are the most efficient for several criteria. In this article, we use these descriptors to analyze how a large input image can be decomposed by small template images contained in a database. Affine transformations from database images onto the input image are found as described in . The large image is thus covered by small patches like a jigsaw puzzle. We introduce a filtering step to ensure that found images do not overlap themselves when warped on the input image. A typical new application is to retrieve which products are proposed on a supermarket shelf. This is achieved using only a large picture of the shelf and a database of all products available in the supermarket. Because the database can be large and the analysis should ideally be done in a few seconds, we compare the performances of two state of the art algorithms to search SIFT correspondences: Best-Bin-First algorithm on Kd-Tree and Locality Sensitive Hashing. We also introduce a modification in the LSH algorithm to adapt it to SIFT vectors.
KeywordsInput Image Hash Function Database Image Hash Table Scale Invariant Feature Transform
Unable to display preview. Download preview PDF.
- 2.Beis, J.S., Lowe, D.G.: Shape indexing using approximate nearest-neighbour search in high-dimensional spaces. In: CVPR 1997: Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR 1997), p. 1000. IEEE Computer Society Press, Washington, DC, USA (1997)Google Scholar
- 7.Foo, J.J., Sinha, R.: Pruning sift for scalable near-duplicate image matching. In: Bailey, J., Fekete, A. (eds.) Eighteenth Australasian Database Conference (ADC 2007), Ballarat, Australia. CRPIT, vol. 63, pp. 63–71. ACS (2007)Google Scholar
- 9.Gionis, A., Indyk, P., Motwani, R.: Similarity search in high dimensions via hashing. The VLDB Journal, 518–529 (1999)Google Scholar
- 10.Joly, A., Frélicot, C., Buisson, O.: Feature statistical retrieval applied to content-based copy identification. In: ICIP, pp. 681–684 (2004)Google Scholar
- 12.Ke, Y., Sukthankar, R.: Pca-sift: A more distinctive representation for local image descriptors. In: CVPR (2), pp. 506–513 (2004)Google Scholar
- 15.Liu, T., Moore, A.W., Gray, A.G., Yang, K.: An investigation of practical approximate nearest neighbor algorithms. In: NIPS (2004)Google Scholar
- 20.Yang, Z., Ooi, W.T., Sun, Q.: Hierarchical, non-uniform locality sensitive hashing and its application to video identification. In: ICME, pp. 743–746 (2004)Google Scholar