|
|
|||
Image Retrieval using Local Colour and Texture Features Ibrahim El-Henawy (1), Mohamed Eisa (2), A. E. Elalfi (3) , Hans Burkhardt (2) (1) Zagazig university, Faculty of Computer & Information (2) Institute of Computer Science, Albert-Ludwigs-Universität Freiburg (3) Mansoura university, Faculty of Specific Education Abstract:
Colour
histograms proved to be successful in automatic image
retrieval; however, their draw back is that all structural
information is lost. Therefore Siggelkow et al. extended
the colour histogram approach by features that take into
account the relations within a local pixel neighbourhood.
They extracted features that are invariant with respect
to translation and rotation by integrating nonlinear functions
over the group of Euclidean motion. Gabor wavelets proved
to be very useful texture analysis. In this paper we present
an image retrieval method based on nonlinear monomial
kernel function and Gabor filters. Colour features are
found by calculating the 3D colour histogram after applying
the monomial kernel function on the image. Texture features
are found by calculating the mean and standard deviation
of the Gabor filtered image. Experimental results are
shown and discussed.
Key words: Image Retrieval, Knowledge Discovery, Data Mining, Colour Histograms, Intelligent Agent
@ARTICLE{P1150442010, AUTHOR = {Ibrahim El-Henawy and Mohamed Eisa and A. E. Elalfi and Hans Burkhardt}, TITLE = {Image Retrieval using Local Colour and Texture Features }, JOURNAL = {ICGST International Journal on Graphics, Vision and Image Processing}, YEAR = {2005}, MONTH={May}, VOLUME = {SI1} }
(Full Paper, 667 KB) |
|||
|
|
