DocumentCode :
495069
Title :
A Rapid Image Approximation for Keypatches Building
Author :
Yang, Duanduan ; Sluzek, Andrzej
Author_Institution :
Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, Singapore
Volume :
2
fYear :
2009
fDate :
21-22 May 2009
Firstpage :
163
Lastpage :
166
Abstract :
A new type of local features with visual semantics, keypatches, was proposed to improve performances of image retrieval methods. These features are obtained by approximating the content of scanning windows using the predefined geometrical patterns. To build keypatches quickly, this paper proposes a new approximation based on a novel compact gradient mapping table (CGMT). The method includes two stages. First, the approximation candidates can be obtained quickly by constructing and looking up the compact gradient mapping table based on the distribution sharing of the contours characteristics of the patterns. Then, Hough transform needs to be applied only in a very small parameter space defined by the candidates for the final approximation. To demonstrate the effectiveness of the proposed method, we have approximated 1628 image patches from 100 images. Results show the proposed method significantly outperforms the previous Hough transform-based approximation in speed with a very small accuracy loss.
Keywords :
Hough transforms; approximation theory; feature extraction; gradient methods; image retrieval; Hough transform; compact gradient mapping table; content approximation; contours characteristics; feature extraction; image retrieval methods; keypatches building; predefined geometrical patterns; rapid image approximation; scanning windows; visual semantics; Computer vision; Feature extraction; Humans; Image analysis; Image converters; Image retrieval; Information retrieval; Performance analysis; Shape; Windows; Feature extraction; Hough transforms; Image region analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information and Computing Science, 2009. ICIC '09. Second International Conference on
Conference_Location :
Manchester
Print_ISBN :
978-0-7695-3634-7
Type :
conf
DOI :
10.1109/ICIC.2009.150
Filename :
5169034
Link To Document :
بازگشت