Effective image retrieval by shape saliences

Content-based image retrieval (CBIR) systems have been developed aiming at enabling users to search and retrieve images based on their properties such as shape, color and texture. We are concerned with shape-based image retrieval. Here, we discuss a recently proposed shape descriptor, called contour saliences, defined as the influence areas of its higher curvature points. We introduce a robust approach to estimate contour saliences by exploiting the relation between a contour and its skeleton, modifies the original definition to include the location and the value of saliences along the contour, and proposes a new metric to compare contour saliences. We also evaluate the effectiveness of the proposed descriptor with respect to Fourier descriptors, curvature scale space and moment invariants.

[1]  Marcel Worring,et al.  Content-Based Image Retrieval at the End of the Early Years , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Jorge Stolfi,et al.  The image foresting transform: theory, algorithms, and applications , 2004 .

[3]  Mohan S. Kankanhalli,et al.  Shape Measures for Content Based Image Retrieval: A Comparison , 1997, Inf. Process. Manag..

[4]  Alexandre X. Falcão,et al.  Design of connected operators using the image foresting transform , 2001, SPIE Medical Imaging.

[5]  L. F. Estrozi,et al.  Multiresolution shape representation without border shifting , 1999 .

[6]  Miroslaw Bober,et al.  MPEG-7 visual shape descriptors , 2001, IEEE Trans. Circuits Syst. Video Technol..

[7]  L. Costa,et al.  Shape description by image foresting transform , 2002, 2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628).

[8]  Luciano da Fontoura Costa,et al.  A graph-based approach for multiscale shape analysis , 2004, Pattern Recognit..

[9]  Rafael C. González,et al.  Local Determination of a Moving Contrast Edge , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Luciano da Fontoura Costa,et al.  Multiscale skeletons by image foresting transform and its application to neuromorphometry , 2002, Pattern Recognit..

[11]  Clement T. Yu,et al.  Techniques and Systems for Image and Video Retrieval , 1999, IEEE Trans. Knowl. Data Eng..

[12]  Sadegh Abbasi,et al.  Shape similarity retrieval under affine transforms , 2002, Pattern Recognit..

[13]  Anil K. Jain,et al.  Shape-Based Retrieval: A Case Study With Trademark Image Databases , 1998, Pattern Recognit..

[14]  P. Wintz,et al.  An efficient three-dimensional aircraft recognition algorithm using normalized fourier descriptors , 1980 .

[15]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[16]  Alexandre X. Falcão,et al.  The Ordered Queue and the Optimality of the Watershed Approaches , 2000, ISMM.

[17]  Michael Leyton,et al.  Symmetry-curvature duality , 1987, Comput. Vis. Graph. Image Process..

[18]  Alexandre X. Falcão,et al.  Multiscale shape representation by image foresting transform , 2001, SPIE Medical Imaging.

[19]  Luciano da Fontoura Costa,et al.  An integrated approach to shape analysis: results and perspectives , 2001 .

[20]  Josef Kittler,et al.  Enhancing CSS-based shape retrieval for objects with shallow concavities , 2000, Image Vis. Comput..

[21]  Luciano da Fontoura Costa,et al.  Erratum to multiscale skeletons by image foresting transform and its applications to neuromorphometry: [Pattern Recognition 35(7) (2002) 1571-1582] , 2003, Pattern Recognit..

[22]  Robert B. McGhee,et al.  Aircraft Identification by Moment Invariants , 1977, IEEE Transactions on Computers.