DocumentCode :
2381107
Title :
An Outward-Appearance Patent-Image Retrieval Approach Based on the Contour-Description Matrix
Author :
Zhiyuan, Zeng ; Juan, Zhao ; Bin, Xu
Author_Institution :
Huazhong Univ. of Sci. & Technol., Huazhong
fYear :
2007
fDate :
1-3 Nov. 2007
Firstpage :
86
Lastpage :
89
Abstract :
Since there are mass of images in the outward-appearance patent-image database, a retrieval approach developed for this database is greatly demanded. The shape information of the patent image is the key feature for a patent image. Therefore, we present an outward-appearance patent images retrieval approach based on contour-description matrix. This matrix represents the 2D shape feature and shows the angular and radial distributing information. The proposed representation is invariant to scale, translation and rotation. Our experiments show that the contour-based technique performs significantly better compared to wavelet-based approach previously proposed in the literature.
Keywords :
image retrieval; matrix algebra; 2D shape feature; angular distributing information; contour-description matrix; outward-appearance patent-image retrieval approach; radial distributing information; shape information; wavelet-based approach; Data mining; Feature extraction; Image converters; Image databases; Image edge detection; Image retrieval; Information retrieval; Matrix converters; Shape measurement; Spatial databases;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Frontier of Computer Science and Technology, 2007. FCST 2007. Japan-China Joint Workshop on
Conference_Location :
Wuhan
Print_ISBN :
978-0-7695-3036-9
Type :
conf
DOI :
10.1109/FCST.2007.14
Filename :
4402605
Link To Document :
بازگشت