21-12-2012, 04:56 PM
IMAGE RETRIEVAL USING CONTOURLET BASED INTEREST POINTS
1IMAGE RETRIEVAL.pdf (Size: 1.13 MB / Downloads: 28)
ABSTRACT
In this work we present the method for image retrieval
based on the Non-Subsampled Contourlet Transform
(NSCT) and the Harris corner detector. The NTSC-based
interest point detector is proposed by combination of
NTSC and Harris corner detector called the Contourlet
Harris detector. We also present the method how to
extract the image features using this Contourlet Harris
detector that is applied for image retrieval. Experiments
are implemented on the WANG database aiming to
compare retrieval effectiveness of proposed method to
some methods have announced. Results demonstrate that
the proposed method shows a quite improvement in the
retrieval effectiveness.
INTRODUCTION
CONTENT-BASED IMAGE RERTIEVAL (CBIR) becomes a
real demand for storage and retrieval of images in digital
image libraries and other multimedia databases.
Basically, CBIR is an automatic process for searching
relevant images to a given query image based on the
primitive low-level image features such as color, texture,
shape, and spatial layout.
References [11], [12] introduced the contourlet
transform with improved characteristics compared with
the wavelet transform. The contourlet transform was
designed by a discrete-domain multiresolution and
multidirection expension using non-separable filter
banks, in much the same way that wavelets were derived
from filter banks. Image decomposition using this
transform has a tlexible multiresolution, and local and
directional expansion for images. Many applications have
been developed based on contourlet transform as image
denoising, enhancement, and CBIR. Reference [4]
introduced a CBIR solution based on contourlet transform
with the results is quite good.
Our Approach
In this paper, we propose a new detector to capture
interest points in images called the Contourlet Harris
detector and design a corresponding descriptor for image
features. The highlights of this approach are: (i) it used
Nonsubsampled Contourlet transform with fully shiftinvariant,
multiscale, and multidirection expansion that
has improved characteristics compared with contourlet
transform is not shift-invariant due to downsamplers and
upsamplers present in both the Laplacian pyramid and the
DFB (directional tlter bank) [2]; (ii) it used the Harris
comer detector [3] extract interest points on subbands of
NTSC; (iii) the image features are computed from
detected interest points and energy of each subband. Our
experiments show that proposed method can outperform
methods based on individual contourlet [4] and NSCT,
coocurrence [14] features for image retrieval.
Related Works
The use of interest points in content-based image
retrieval allows image index based on local properties of
image. A salient detector that extract points where
variations occur in the image, where they are comer-like
or not, is introduced in [7]. With this detector, the
wavelet-based salient points are applied for image
retrieval provides significantly improved results in terms
of retrieval accuracy compared to the global feature
approaches.
Reference [5] presents the method how to combine
interest points and Gabor features to generate a textural
description of images and give good results according to
test image database of the authors.
A contourlet based interest points detector is proposed
based on NSCT and weighted sum of decomposition
levels. The accumulated image from selected directions
can be used to extract the edges from the image which
gives an number of points (only local comers are
extracted) [15].
RESULTS OF WORK
Programs are written in Matlab version R2006a and
use with multiple formats of images such as GIF, JPEG,
PPM, TIFF, PNG. The computer implement these
experiments that have the CPU speed is 2 x I.83GHz and
1 GB of RAM. The image database used for experiments
is WANG database [9] including 1000 images that are
categorized in 10 classes (including africans, beaches,
buildings, buses, dinosaurs, elephants, flowers, horses,
mountains, food) and each class contains 100 pictures in
JPEG format.
CONCLUSION
In this paper, a new detector was presented. The NTSC
and the Harris comer detector were combined to build the
detector called Contourlet Harris detector. This detector
captures local points at a shift-invariant directional
multiresolution image representation to create point sets
corresponding to levels (scales) and directions. The
solution extracts image features from point sets that are
fast and feature vectors are small .