Key Points-based Indexing for Pre-attentive Similarities: The KIWI System

Abstract:In this paper, we introduce the general architecture of an image-search engine based on pre-attentive similarities. Local features are computed in key points to represent local properties of the images. The location of key points, where local features are computed, is discussed. We present two new key point detectors designed for image retrieval, both based on multi-resolution: the contrast-based point detector, and the wavelet-based point detector. Four different local features are used in our system: differential invariants, texture, shape and colour. The local information computed in each key point is stored in 2D histograms to allow fast querying. We study the choice of the key points detector depending on the feature used, for different test sets. The Harris corner detector is used for benchmarking. Uniformly distributed points are also used, and we conclude for which applications they are effective. Finally, we show that point detector and feature efficiency depend upon the test set studied.

[1]  Luc Van Gool,et al.  Content-Based Image Retrieval Based on Local Affinely Invariant Regions , 1999, VISUAL.

[2]  E. J. Stollnitz,et al.  Wavelets for Computer Graphics : A Primer , 1994 .

[3]  Benoit Huet,et al.  Relational histograms for shape indexing , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[4]  Simone Santini,et al.  The Graphical Specification of Similarity Queries , 1996, J. Vis. Lang. Comput..

[5]  Touradj Ebrahimi,et al.  Image Retrieval Based on Structural Content , 1999 .

[6]  Leonidas J. Guibas,et al.  A metric for distributions with applications to image databases , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[7]  Nicu Sebe,et al.  Multi-scale sub-image search , 1999, MULTIMEDIA '99.

[8]  B. S. Manjunath,et al.  Texture features and learning similarity , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  Dragutin Petkovic,et al.  Content-Based Representation and Retrieval of Visual Media: A State-of-the-Art Review , 1996 .

[10]  J.-M. Jolion,et al.  Analyse multirésolution du contraste dans les images numériques , 1994 .

[11]  Cordelia Schmid,et al.  Local Grayvalue Invariants for Image Retrieval , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Jean-Michel Jolion,et al.  Detection of Interest Points for Image Indexation , 1999, VISUAL.

[13]  N. Sebe,et al.  Color indexing using wavelet-based salient points , 2000, 2000 Proceedings Workshop on Content-based Access of Image and Video Libraries.

[14]  David Salesin,et al.  Wavelets for computer graphics: a primer.1 , 1995, IEEE Computer Graphics and Applications.

[15]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[16]  Jean-Michel Jolion,et al.  Image indexation and content based search using pre-attentive similarities , 2000, RIAO.

[17]  I. Daubechies.  Orthonormal bases of compactly supported wavelets , 1988 .

[18]  Dragutin Petkovic,et al.  Query by Image and Video Content: The QBIC System , 1995, Computer.

[19]  Nicu Sebe,et al.  Wavelet-based salient points for image retrieval , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[20]  Azriel Rosenfeld,et al.  A distance metric for multidimensional histograms , 1985, Comput. Vis. Graph. Image Process..

[21]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..