Efficient descriptor extraction over multiple levels of an image scale space

作者: Sundeep Vaddadi , John H. Hong , Yuriy Reznik , Chong Uk. Lee , Onur C. Hamsici

DOI:

关键词:

摘要: A local feature descriptor for a point in an image is generated over multiple levels of scale space. The gradually smoothened to obtain plurality spaces. may be identified as the interest within first space from derivatives obtained each orientation maps (from derivatives) Each then (e.g., convolved) corresponding smoothed maps. Therefore, by sparsely sampling two or more spaces

参考文章(45)
Benno Kusstatscher, Gopal Karanam, Edge orientation for second derivative edge detection methods ,(2011)
Shumeet Baluja, Michele Covell, Effective feature classification in images ,(2009)
Trevor Darrell, Kristen Grauman, Pyramid match kernel and related techniques ,(2007)
David Marimon SanJuan, Arturo Bonnin Llofriu, Tomasz Adamek, Roger Gimeno Hernandez, Efficient scale-space extraction and description of interest points ,(2011)
C. Chennubhotla, A. Jepson, Sparse PCA. Extracting multi-scale structure from data international conference on computer vision. ,vol. 1, pp. 641- 647 ,(2001) , 10.1109/ICCV.2001.937579
Masakazu Iwamura, Koichi Kise, Kazuto Noguchi, Image recognition method, image recognition device, and image recognition program ,(2007)
Sundeep Vaddadi, Chong U. Lee, John H. Hong, Yuriy Reznik, Onur C. Hamsici, Fast subspace projection of descriptor patches for image recognition ,(2010)