DocumentCode
2843726
Title
Application Research of Homogeneous Texture Descriptor in Content-Based Image Retrieval
Author
Shao, Hong ; Ji, Jun ; Kang, Yan ; Zhao, Hong
Author_Institution
Sch. of Sino-Dutch Biomed. & Inf. Eng., Northeastern Univ., Shenyang, China
fYear
2009
fDate
19-20 Dec. 2009
Firstpage
1
Lastpage
4
Abstract
The homogeneous texture descriptor is one of MPEG-7 texture descriptors. This descriptor describes the texture information of an image or the region of interest in an image. A new texture feature wedge feature is proposed, which emphasizes the texture direction. The homogeneous texture descriptor owning the new feature is more suitable to content-based image retrieval system. The experimental results show this method can get better retrieval recall and accuracy ratio comparing with that of only using the texture energy or the generalized gray co-occurrence matrix.
Keywords
Fourier transforms; Gabor filters; content-based retrieval; image retrieval; image texture; MPEG-7 texture descriptor; content-based image retrieval; feature wedge feature; gray co-occurrence matrix method; homogeneous texture descriptor; Biomedical engineering; Content based retrieval; Feature extraction; Frequency domain analysis; Humans; IEC standards; ISO standards; Image retrieval; MPEG 7 Standard; Wavelet transforms;
fLanguage
English
Publisher
ieee
Conference_Titel
Information Engineering and Computer Science, 2009. ICIECS 2009. International Conference on
Conference_Location
Wuhan
Print_ISBN
978-1-4244-4994-1
Type
conf
DOI
10.1109/ICIECS.2009.5364946
Filename
5364946
Link To Document