A Novel Texture and Shape Patternbased Feature Extraction Technique For Image Retrieval in Medical Images

International Journal of Emerging Trends & Technology in Computer Science (IJETTCS)
Web Site: www.ijettcs.org Email: editor@ijettcs.org

Volume 5, Issue 3, May-June 2016
ISSN 2278-6856
A NOVEL TEXTURE AND SHAPE PATTERNBASED FEATURE EXTRACTION

TECHNIQUE FOR IMAGE RETRIEVAL IN
MEDICAL IMAGES
A.Srinagesh #1, N.Hanumantha Rao *2 D.Raj Vikas3
#1
CSE Department, RVRJCCE Guntur, India
*2
CSE Department, RVRJCCE Guntur, India

*3
Software Engineer, Hyderabad, India
Abstract
In recent years, especially Image Retrieval (IR) is a very
challenging task and evolves into a complex problem in
particular conventional Ultrasound image processing area or
any other medical images domain. Many researchers have
developed different image retrieval systems for solving this
problem. In this paper, we have presented an image retrieval
system based on the new shape pattern texture feature
extraction using the gradient method in the 3x3
neighbourhoodand also using histograms for improving the
accuracy of object detection and image retrieval is designed.
A new shape feature extraction scheme with the inclusion of
vertical and horizontal gradient information and intensity
information is identified with the formulated fuzzy rules
suitable for an optimum threshold value for region detection
is methodology. The newly extracted shape feature is
represented in a vector form and that is then stored as a single
feature. To this Shape feature, the texture feature is added
and stored as a single feature vector in the database. Finally,
for the query image, features will be extracted and it is
matched with the proper distance measure. Subsequently,
those two features are matched feature library for image
retrieval .In the case of no query image is given and an input
image is taken from the stored database and using the
distance values, the relevant images are retrieved from the
medical image database. The implemented technique works
for both static and sequence of video images i.e., video image
retrieval of same images type.
Keyword-Automated Image Retrieval, Image Processing,

Image Segmentation, Region-based Segmentation, Pixelbased, Histogram, Texture, Shape, query
I.INTRODUCTION
Content-based image retrieval has been learned with
more concentration as enormous amounts of image
Volume 5, Issue 3, May June 2016
data gathered in different fields, e.g., medical images,

satellite images, art collections, commercial images
and general photographs in modern years. The images
are indexed only by keywords set by a human [1] in most
cases and Image databases are generally very big.
Occasionally the keyword approach is not sufficient even
though keywords are the most helpful in retrieving
images that a user needs. As a result, by colour
distribution, texture distribution, shape similarity, or
object presence between the two images, the degree of
comparison between query images and images in
databases can be calculated . By means of colour and
texture property [2], many works have been done.
Texture and shape are extensively used visual features in
content-based image retrieval systems furthermore. The
visual patterns of homogeneity are signified by Texture
and is an inbuilt property of all surfaces. Significant
information associated with the structural display of the
surface, such as clouds, leaves, bricks, fabrics, etc are
there. The correlation between the surface and its
neighbouring surroundings are moreover represented
by it. To be brief, the characteristic physical
composition of a surface is explained by this feature
[5]. For medical image retrievals [4], texture purpose is
absolutely suitable. A few texture features including
entropy, energy, contrast and homogeneity [3] are used by
CBIR.
Formerly techniques of image retrieval were based on the
physical textual annotation of images, a cumbersome and
as well repeatedly a subjective task. Since the fact that
explains what we see is hard to describe by them, the texts
are not only enough. Therefore, stuffing in an image,
Page 241

colour, shape, and texture, started gaining importance.
Image retrievals utilized the content from an image
independently at first. For instance, Huang and Jean [6]
utilized a 2D C+-strings and Huang et al. [7] utilized the
colour information for indexing and its applications.
Currently, using a mixture of contents-based approaches is
gaining importance. Combining shape and colour using
various strategies such as weighted factors [8], histogrambased [9], kernel-based [10], or invariance-based [11] has
been one of the premier combination strategies.
To evaluate image similarity has been presented in [12]
Shape and texture utilizing elastic energy-based approach.
Using binary set representations, Smith and Chang [13]
offered an automatic extraction of colour and texture
information. A colour histogram beside with the texture
and spatial information was used by Li et al. [14].
Semantic Image retrieval had been the center of research
for a few research papers such as [15] and [16]. A
thorough summary on the mixture of literature survey that
is obtainable on CBIR can be found in [17] and [18].
Various similarity measurement techniques that are
discussed can be found in [19].
This paper presents an effective image retrieval system
using features like texture and shape. Firstly, we have
developed new shape region extraction technique for
shape feature. Subsequently, texture feature extraction had
done using existing technique. Then the two features are
stored in the feature library. For retrieval purpose,
matching and Euclidean distance is used. Finally, the
relevant images that have less matched distance than the
predefined threshold value are retrieved from the image
database.
The main contributions of our proposed system are:
One of the contributions of proposed technique is
shape feature extraction. Here, a new shape feature
extraction scheme with the inclusion of vertical and
horizontal gradient information and
intensity
information for accurate of image retrieval is
developed.
F-Measure is computed for proposed image retrieval
techniques
The rest of the paper is organized as follows: Section II
reviews the recent research works with respect to contentbased video retrieval, Section III describes the proposed
system for content-based video retrieval, section IV
explains result and discussion and Section V concludes
the paper.
ISSN 2278-6856
II.LITERATURE REVIEW
Many researchers have implemented several techniques
for the content based image retrieval. Some of the recent
related works regarding the image retrieval technique are
reviewed in the following section. A plan for similaritybased leaf image retrieval has been proposed by Yunyoung
Nam et al. [20]. They have well thought-out shape and
venation features collectively for the valuable
measurement of leaf similarity. A construction made by
them with a matrix of interest points to model the
similarity among two leaf images in the shape domain. An
adaptive grid-based matching algorithm was implemented
by them in order to bring progress in the retrieval
presentation. Algorithm computes the lowest amount of
weight from the constructed matrix and utilizes it as
similarity degree between two leaf images based on the
Nearest Neighbour (NN) search plan. For matching, this
reduces essential search space. An adjacency matrix from
the crossroads and end points of a venation to the model
parallel between two leaf images was constructed by them
in the venation domain.
G. Quellec et al. [21] have proposed content-based image
retrieval (CBIR) method for diagnosis aid in medical
fields with no extraction domain-specific features: a
signature was built for every image from its wavelet
transform images that were indexed in a generic fashion
in the planned system. The sharing of wavelet coefficients
in every sub band of the decomposition are characterized
by those image signatures. A distance measure was next
distinct to compare two image signatures and so get back
the most alike images in a database when a query image
was submitted by a physician. The signatures and the
distance measure must be associated with the medical
interpretation of images to recover related images from a
medical database. Accordingly, they introduced numerous
degrees of freedom in the structure so that it was tuned to
any pathology and image modality. Within the scheme
framework, they planned to become accustomed the
wavelet basis particularly and to utilize a custom
decomposition plan.
To recover the semantic images, an energetic relevance
feedback framework has been planned by Pushpa B. Patil
and Manesh Kokare [22]. In order to decrease the
recovery time, the planned approach addressed the small
training data problem in RF and optimizing the testing
set. Using AdaBoost by texture features, this consequence
feedback framework was tested. On big scale normal
common purpose colour image database, the RF
framework was tested. The framework had verified very
hopeful recovery precision. RF using AdaBoost with
collective texture features RCWF and DT-CWT give
enhanced recovery performance and has been found out
from experimental results.
Page 242

Based on orthogonal polynomials replica, an easy and a
competent Content Based Image Retrieval has been
presented by R. Krishnamoorthi and S Sathiya devi [23].
This replica was built with a set- off cautiously selected
orthogonal polynomials and was utilized to take out the
low-level texture features there in the image under
analysis. The orthogonal polynomials replica coefficients
were reordered into multi-resolution sub band like
configuration. To signify the texture features, easy
statistical and perceptual properties were consequently
from the sub band coefficients and those features form a
feature vector. The competence of the planned feature
vector extraction for texture image recovery is
experimented on the standard Brodatz and MITs VisTex
texture database images by means of the Canberra
distance measure.
Within Medical image processing and analysis field,
Content-based image retrieval is the main problem. A
significant necessity for constructing successful contentbased image retrieval (CBIR) systems is a precise
characterization of visual information. Long-established
image retrieval technique has a few restrictions. Research
focus has been shifted from designing sophisticated
low-level feature extraction algorithms to falling the
semantic gap between the visual features and the
richness of human semantics in order to get better the
recovery exactness of content-based image retrieval
systems. The technique for competent CBIR with highlevel semantic features by utilizing object ontology has
been presented by Anuja Khodaskar and Dr. S.A. Ladke
[24]. The search for the related images will be
optimized while they given that additional information
to the search algorithm. As a result, the semantic
features with object ontology have enlarged the accuracy
and remember values.
An effectual image retrieval to reduce the semantic gap
between the low-level and high-level features has been
developed by Sanjay T. Singh and Trimbak Ramchandra
Sontakke [25]. At first, the low-level features colour,
texture, and shape were removed from the database
images and as well from the query image. Based on these
low-level features, next the images which were related to
the set query image were recovered from the database.
The query keyword which was an elevated level feature
was produced by means of these regained related images
and then by utilizing that query keyword the images which
were relevant to the query keyword were removed. After
that, the images which were equally visually and
semantically the same were recovered by analyzing these
images. By querying the presented approach with
dissimilar types of images the usefulness of it was
explained elaborately in that paper. An image retrieval
technique called kernel density estimation for exploring
fractal coding parameters, which produces a thought for
ISSN 2278-6856
the application of fractal coding in image recovery has

been proposed by Huang Xiaoqing et al. [26]. The
dominance in texture image retrieval was shown by the
experimental results. Both retrieval speed and rate has
been improved compared with the presented method and
hence the planned method was efficient. Besides, the
planned fractal signature, as a significant feature, has set
up an application in the recognition of starch grains,
which were frequently found in colour microscopic images
of Chinese Materia Medica (CMM).
III.PROPOSED
SYSTEM
IMAGE
RETRIEVAL
Image retrieval is a complex problem in medical image

processing due to the presence so many types of input
images. An important constraint for constructing effective
image retrieval systems is an accurate characterization of
visual information. Traditional image retrieval method
has some limitations. In order to improve the retrieval
accuracy, in this paper, we have developed a new image
retrieval system. The overall block diagram of proposed
image retrieval system shown in figure 1.
Figure 1: Overall block diagram of proposed approach

(A) Novel Shape feature Extraction
Normally, an image is a rectangular grid of pixels or
picture elements, illustrates by figure 2. Here, we have
developed new shape feature extraction scheme with the
inclusion of gradient information and intensity
information. The ultimate target of this section is images
shape extraction, therefore, for this purpose, we have
checked the pixels one by one whether the structure of the
image is present in the pixel or not. For this shape feature
extraction, we have used a novel technique based on fourpixel difference conditions. Firstly the input medical
image is segmented into several blocks. Subsequently,
fuzzy rules have generated based on this four conditions
whether the structure of the image is present in the pixel
or not. Consider if A1 is the first pixel and A2 is the
Page 243

neighbour pixel, the following four Properties with certain
threshold based on input image should be satisfied.
Pixel difference (p1)
Block difference (p2)
Gradient change in vertical gradient block difference
(p3)
Gradient change in horizontal gradient block
difference (p4)
Already in the first condition, we took two pixels such as

A1 and A2 and these pixels would be present in the same
block (B1) in figure 2. In the second condition, we have
taken a neighbor block of B1, which means B2 and we
take 3X3 blocks of this B2.Consequently, we have
calculated the distance between these 3X3 blocks. The
Euclidean distance between the 3X3 blocks is calculated
by the following formula
m
P2 d (B2, B1)
(1) Pixel difference (p1)
ISSN 2278-6856
(B2
B1j )2
j 1
(2)
Where, B1 is the first block

B2 is the second block
(3) Pixel difference when Gradient change in vertical
direction (p3)
Figure 2: sample diagram of pixel difference (p1)

The grid image contains several blocks and each block
contains several pixels. The first condition is pixel
difference between two pixels. Here, if we consider A1 is
the starting pixel of one block (B1) and A2 is the
neighbour pixel of A1.The pixel difference is given by
P1 diff ( A1 and A2)
(1)
(2) Block difference (p2)
Figure 4: sample diagram of Pixel difference when

Gradient change in vertical direction (p3)
For this condition, we have converted the original medical
image into vertical gradient direction, after that we
calculate pixel difference between A1 and A2, here A1 is
neighbour pixel of A1. The pixel difference is given by
P3vertical diff ( A1 and A2)
(3)
(4) Pixel difference when Gradient change

horizontal direction (p4)
Figure 3: sample diagram of block difference (p2)
Figure 5: sample diagram of Pixel difference when

Gradient change in horizontal direction (p4)
Page 244
in

For this condition, we have converted the original medical
image into horizontal gradient direction. Subsequently, we
calculate pixel difference between A1 and A2, here A1 is
neighbour pixel of A1. The pixel difference is given by
P3horizontal diff ( A1 and A2)
(4)
Fuzzy rules generation based p1, p2, p3, and p4: From
above the four conditions p1, p2, p3, and p4, we have
generated fuzzy rules for whether the neighbour pixels add
or not with the first pixel. Consider A1 is first pixel and
A2 is the neighbour pixel
Where,
ESR
ISSN 2278-6856
is the extracted shape region.
(C) Texture pattern based feature extraction

From existing paper, we have used texture pattern
extraction process for proposed image retrieval technique.
Generally, texture attribute depicts the surface of an
object. Here, texture feature extraction process is done
based on the histogram of mean and variance with a
threshold. The texture feature extraction process is
depicted in figure 7.
(1) If p1 is high, p2 is high, p3 is high and p4 is high

A1 is no change
(2) If p1 is high, p2 is low, p3 is high and p4 is high
A1 is no change
(3) If p1 is low, p2 is low, p3 is high and p4 is high
A2 is added with A1
From above three fuzzy rules, we have checked the
structure of the image is present in the pixel or not.
(B)Shape representation
Fig: 7. Texture pattern based feature extraction
The texture feature extraction process is done by
following steps,
The input medical images are segmented into a
number of blocks and every block converted into
3 3 matrix form. Consider we have taken one

image
blocks
I and this image is divided into multiple

I B B1 , B2 ,...Bn . and each block is created
3 3 matrix form.
Figure 6: input medical image and corresponding output
After shape region extracted, the shape features are
represented in a vector that is then stored in the feature
database. For this purpose, the extracted image converted
into M N grid image. If the shape region present in
the grid image, we consider one, otherwise zero. Finally,
replace all zeros we get the output of shape region is
shown in figure 6. This process is done by following
1 ,
ESR
0 ,
if presenttheshaperegion
otherwise
(5)
Bn b11,b12,b13,b21,b22,b23,b31,b32,b33
(6)
Subsequently, we have computed mean and variance

for every 3 3 matrix form of the whole image. The
mean and variance are calculated by following
equations (7) and (8),
3
mn
Mean M
m 1
n 1
(7)
Page 245

3
bmn
Variance m1 n1
9
(8)
b
m
n
Here is the value of block,
is row and is column
After mean and variance calculation process, we have
chosen two threshold variance levels. Consequently, two
histograms are plotted using this threshold value. The
threshold formula used to compute the threshold value is
Tf
H1 ,
H 2 ,
T
T
Where, -variance
T -Threshold
(9)
ISSN 2278-6856
retrieval system has been implemented using MATLAB

(Matlab7.12) and the performance of the proposed system
is analyzed using the evaluation metrics including
precision, recall and F-measure.
(A) Datasets description of proposed technique
The collected input images contain the following
categories of all types of image objects as presented in the
Standard medical image dataset. These images such as
MRI brain, CT brain,Ultrasound,Mammogram, and CT
lung. This image dataset contains 200 medical images.
Some of the sample dataset input images of the proposed
CBIR system is given in fig.8.
3.3 Retrieval of Relevant Images

After the feature extraction, the two features such as new
shape feature and texture are stored in the feature library.
Similarity Matching with less distance: The feature
extraction process is applied to the images presented in
the input medical dataset in order to extract the significant
features such as texture and shape. The extracted features
from the input images are then stored in the feature
library. When a query image is given to the proposed
image retrieval system, all the features employed in the
proposed system are obtained using the feature extraction
process. Matching is done in many ways. In this
technique, we use one distance equation namely Euclidean
distance. Then using Euclidean distance, each extracted
feature for query image (texture and shape) is matched
with the respective feature set presented in the feature
library. After that, we have chosen less distance image in
the CBIR database. Subsequently, the computed distance
is utilized to identify the similarity between the query
image and each database images. Lastly, the required
number of images corresponding to the query image is
retrieved from the database. The feature weighted distance
can be determined as,
Fig 8: The sample datasets for proposed image retrieval

system
GUI for image retrieval system:
The GUI developed for image retrieval is given in the
following figure. Here, based on the user requirement, the
user can give appropriate input so that the output such as
corresponding retrieved images, precision, recall and fmeasure. From the figure 9, we can identify that retrieved
images, precision, recall and f-measure.
Re(I query , I data ) EDmin ( I query , texture, shape) (10)

query
data
, I ) Euclidean distance computed

Where, Re( I
by matching the feature
IV.EXPERIMENTAL RESULTS AND
DISCUSSION
The results and discussion of the proposed image retrieval
system are given in this section. The proposed image
Figure 9: Snapshot representation of proposed image

retrieval system
Page 246

ISSN 2278-6856
(B) Image Retrieval

The features including shape and texture are extracted
from the input images and it is stored in the feature
library. For retrieving, the images are given to the
proposed CBIR system that extracts the features and the
features are matched with the feature library using the
designed image matching. The matching score computed
is used to retrieve the images from the dataset and the
retrieved image for the corresponding input images is
given in the following figures 10 to figure 12.
Fig.11. Retrieved videos (a) query image (b) Retrieval

images for the query

images for query
Page 247

ISSN 2278-6856
medical query images and corresponding precision, recall

and F-measure. The figure 13 to 15 shows the
performance of the proposed system in retrieving the
relevant images and it clearly differentiates the results
obtained for different images.
Table.1 Medical query images and corresponding
Precision, Recall and F-measure

image for the query
(C) Quantitative analysis
The performance of the proposed approach system is
evaluated on the input dataset using the precision, recall
and F-measure. For quantitative analysis, images from
each category are given to the proposed system and results
are evaluated with the defined as follows:
Fig.13. Precision graph plotted for different medical

images
In proposed image retrieval system, we have taken 200

medical images, such as MRI brain, CT lung,
Mammogram, and Ultrasound. Table.1 is showed for the
Page 248

ISSN 2278-6856
CBIR system. Subsequently, we have used texture feature

from existing technique. For retrieving, these features are
extracted from the query image and matched with the
feature library using the feature weighted distance. After
that, all feature vectors will be stored in the database.
Finally, the relevant images that have less matched
distance than the predefined threshold value are retrieved
from the image database.
Fig.14. Recall graph plotted for different medical images
Fig.15. F-Measure graph plotted for different medical

images
V.CONCLUSION
In this paper, we have developed a significant image
retrieval system using two basic features texture and shape
for both static and sequence of input images of same
image modality. Here, these two different features such as
texture and shape can. Firstly, I have developed a new
shape feature for improving the retrieval accuracy in
REFERENCES
[1]. Arnold W.M.Smeulders, Marcel Worring, Simone
Santini, Amarnath Gupta, and Ramesh Jain.
Content-Based Image Retrieval at the End of the
Early years, IEEE Transactions on Pattern
Analysis and Machine intelligence, Vol. 22, No. 12,
December 2000.
[2]. S.Arivazhagan,
L.Ganesan,
S.Selvanidhyananthan,"Image Retrieval using Shape
Feature, International Journal of Imaging Science
and Engineering (IJISE), Vol.1, No.3, July 2007.
[3]. Rajshree S.Dubey, Rajnish Choubey , and Joy
Bhattacharjee, "Multi-Feature Content-Based Image
Retrieval", International Journal on Computer
Science and Engineering, Vol.2, No.6, pp.21452149, 2010.
[4]. Nandagopalan, Adiga and Deepak, "A Universal
Model for Content-Based Image Retrieval",
WASET, Vol.46, No.112, pp.644-647, 2008.
[5]. Naresh Babu, Sake.Pothalaiah and Ashok Babu,
"Image retrieval colour, shape and texture features
using content-based", International Journal of
Engineering Science and Technology, Vol.2, No.9,
pp.4278-4287,2010.
[6]. Huang, P., Jean, Y.: Using 2d c+-strings as spatial
knowledge representation for image database
systems, Vol. 27, pp.12491257, 1994.
[7]. Huang, J., Kumar, S.R., Mitra, M., Zhu, W.J., Zabih,
R.: Spatial colour indexing and applications, Int. J.
Comput. Vision,Vol. 35, pp.245268,1999.
[8]. Jain, A., Vailaya, A.: Image retrieval using colour
and shape, Pattern Recognition, Vol. 29, pp.12331244, 1996.
[9]. Saykol, E., Gudukbay, U., Ulusoy, O.: A histogrambased approach for object-based query-by-shape-andcolour in multimedia databases,Technical Report
BU-CE-0201,
Bilkent
University,
Computer
Engineering Dept, 2002.
[10]. Caputo, B., Dorko, G.:How to combine colour and
shape information for 3d object recognition: kernels
do the trick, 2002.
[11]. Diplaros, A., Gevers, T., Patras, I.: Combining colour
and shape information for illumination-viewpoint
invariant object recognition, Vol. 15, pp.111, 2006.
[12]. A.Srinagesh, K.Aravinda, G.P.Saradhi Varma,
A.Govardhan, M. SreeLatha, A Modified Shape
Feature Extraction Technique For Image Retrieval
Page 249

International Journal of Emerging Science and
Engineering (IJESE) ISSN: 23196378, Volume-1,
Issue-8, June 2013.
[13]. Smith, J.R., Chang, S.F.: Automated image retrieval
using colour and texture, Technical Report 414-9520, Columbia University, Department of Electrical
Engineering and Center for Telecommunications
Research, 1995.
[14]. Li, X., Chen, S.C., Shyu, M.L., Furht, B.: Image
retrieval by colour, texture, and spatial information,
In: Proceedings of the 8th International Conference
on Distributed Multimedia Systems (DMS 2002), San
Francisco Bay, CA, USA, pp.152159,2002.
[15]. Carson, C., Thomas, M., Belongie, S., Hellerstein,
J.M., Malik, J.: Blobworld: A system for regionbased image indexing and retrieval, in Third
International Conference on Visual Information
Systems, Springer, Heidelberg, 1999.
[16]. Shao, L., Brady, M.: Invariant salient regions based
image retrieval under viewpoint and illumination
variations, J. Vis. Comun. Image Represent. Vol.17,
pp.1256-1272, 2006.
[17]. Veltkamp, R., Tanase, M.: Content-based image
retrieval systems: A survey, Technical Report UUCS-2000-34, Utrecht University, Department of
Computer Science, 2000.
[18]. Datta, R., Li, J., Wang, J.Z.: Content-based image
retrieval: approaches and trends of the new age,
Proceedings of the 7th ACM SIGMM international
workshop on Multimedia information retrieval, pp.
253262. ACM Press, New York, 2005.
[19]. Chang, H., Yeung, D.Y.: Kernel-based distance
metric learning for content-based image retrieval,
Image Vision Comput.Vol.25, pp.695703, 2007.
[20]. Yunyoung Nam, Eenjun Hwang, Dongyoon Kim, A
similarity-based leaf image retrieval scheme: Joining
shape and venation features, Computer Vision and
Image Understanding, Vol.110, pp.245259, 2008.
[21]. A.Sri Nagesh, et al. "An Enhanced Fuzzy C-Means
Clustering
(ECFMC)
Algorithm
for
Spot
Segmentation."
Signal
Processing,
Image
Processing and Pattern Recognition: International
Conferences, SIP 2011, Held as Part of the Future
Generation Information
Technology
Conference, FGIT 2011, in Conjunction with GDC
2011, Jeju Island, Korea, December 8-10, 2011.
Proceedings.
Vol. 260. Springer, 2011.
[22]. Pushpa B. Patil and Manesh Kokare,"Semantic
Image Retrieval Using Relevance Feedback,
International Journal of Web & Semantic Technology
(IJWesT) Vol.2, No.4, October 2011.
[23]. R. Krishnamoorthi, S. Sathiya devi, A
Multiresolution approach for rotation invariant
texture image retrieval with orthogonal polynomials
model, J. Vis. Commun. Image R. Vol.23, pp.18-30,
2012.
ISSN 2278-6856
[24]. Anuja Khodaskar, Dr. S.A. Ladke,"Content-Based

Image Retrieval with Semantic Features using Object
Ontology, International Journal of Engineering
Research & Technology (IJERT), Vol. 1 Issue 4, June
- 2012
[25]. Sanjay
T.
Singh,
Trimbak
Ramchandra
Sontakke,"Neutralizing the Semantic Gap in the
Content-Based Image Retrieval (CBIR) System,
European Journal of Scientific Research Vol.75
No.4, pp. 536-549, 2012.
[26]. Huang Xiaoqing, Zhang Qin, Liu Wenbo,"A new
method for image retrieval based on analyzing fractal
coding characters,"J. Vis. Commun. Image R.Vol.24,
pp.4247, 2013.
[27]. G. Quellec, M. Lamard, G. Cazuguel, B. Cochener,
C. Roux, Wavelet optimization for content-based
image retrieval in medical databases, Medical Image
Analysis, Vol.14, pp. 227-24, 2010.
[28]. Pala, S.: Image retrieval by shape and texture,
PATREC: Pattern Recognition. Pergamon Press 32,
1999
Page 250

A Novel Texture and Shape Patternbased Feature Extraction Technique For Image Retrieval in Medical Images

Caricato da

Informazioni sul documento

Titolo originale

Copyright

Formati disponibili

Condividi questo documento

Condividi o incorpora il documento

Opzioni di condivisione

Hai trovato utile questo documento?

Questo contenuto è inappropriato?

Copyright:

Formati disponibili

A Novel Texture and Shape Patternbased Feature Extraction Technique For Image Retrieval in Medical Images

Caricato da

Copyright:

Formati disponibili

International Journal of Emerging Trends & Technology in Computer Science (IJETTCS)

Web Site: www.ijettcs.org Email: editor@ijettcs.org