![ ISSN: 2088-8708
IJECE Vol. 7, No. 5, October 2017 : 2555 – 2564
2556
enhance the MRI Images by developing their appearance and removing the unusual patterns caused by noise
from the interference of different sources. This will result in an alternative image with enhanced and more
noticeably structures. The second part of this work is to extract important image features from the de-noised
images and use these image characteristics in the classification of the MRI images. This will assist the
medical specialist in the interpretation of MRI Brain images.
2. METHODOLOGY AND RESULTS
2.1. Image Database:
MRI brain images used in this work were selected from Harvard Medical School Database [1]
which is a web-based database that contains a large variety of MRI brain slice images. The datasets used in
this work consists of T2-weighted MRI brain images in axial plane. T2 model was chosen in this work since
T2 images are of higher-contrast and clearer vision compared to other modalities.
The number of MRI brain images in the input dataset is Forty. Twenty are of which are normal brain
images and twenty of abnormal brain images. The abnormal brain MR images of the dataset consist of the
following diseases: Acute stroke, Alzheimer's disease, Cerebral Toxoplasmosis, Chronic subdural hematoma,
Hypertensive encephalopathy, Lyme encephalopathy, Metastatic bronchogenic carcinoma, Multiple sclerosis,
Sarcoma, Sub-acute stroke, Multiple embolic infarctions, Fatal stroke, Motor neuron disease, Pick's disease
and Herpes encephalitis.
2.2. Pre-Processing: MRI Image denoing
The Discrete Wavelet Transforms (DWT) decomposition was used along with thresholding
techniques [2] for efficient noise removal. The MATLAB wavelet toolbox was used for this purpose. The
wavelet–based methods used for denoising are depicted in Figure 1 below and can be summarized as:
Decompose: Choose a wavelet and a decomposition level N. Compute the wavelet decomposition of
the image down to level N.
Threshold detail coefficients: For each level from 1 to N, threshold the detail coefficients.
Reconstruct: Compute wavelet reconstruction using the original approximation coefficients of level
N and the modified detail coefficients of levels from 1 to N.
Figure 1. Wavelet Image Denoising
After decomposing the original image that is shown in Figure 2, into its approximation and detail
coefficients as shown in Figure 3, all the detail coefficients (Horizontal, diagonal and vertical details) of each
level are thresholded according to a thresholding method and a thresholding value. Different threshold
methods and different threshold selection values available in MATLAB DWT toolbox were compared. The
threshold methods available are: Hard and Soft threshold, while the threshold selection values are: Fixed
form threshold, Penalize high, Penalize medium, Penalize low and Bal. sparsity-norm (sqrt). The noise
corrupting the images was assumed to be white and thus the available structure of unscaled white noise was
considered for the test experiments of this work.
MRI Brain Image
Apply DWT
Apply Inverse DWT
Reconstructed Denoised MRI Brain Image
Remove noise from detail coefficients](https://image.slidesharecdn.com/v3111jan1722oct1613099-28509-1-edseptian-201028060020/85/SVM-Classification-of-MRI-Brain-Images-for-ComputerAssisted-Diagnosis-2-320.jpg)
![IJECE ISSN: 2088-8708
SVM Classification of MRI Brain Images for Computer-Assisted Diagnosis (Madina Hamiane)
2557
After denoising, the thresholded detail coefficients these were used together with the original
approximation coefficient to reconstruct the denoised image as shown in Figure. 4. The effectiveness of the
denoising process is measured through the use of the three metrics: Peak Signal to Noise Ratio (PSNR),
Signal to Noise Ratio (SNR) and the Mean Squared Error (MSE) [3]-[5].
Figure 2. Original MRI brain image
Figure 3. Approximation and detail coefficients
Figure 4. Denoised image
The de-noising is considered effective when the highest values of PSNR and SNR and the lowest
value of MSE are reached concurrently. The values of MSE, SNR and PSNR obtained from denoising a
sample normal MRI brain image by applying DWT approach with different wavelet types and thresholding
techniques are shown in Table 1, Table 2, Table 3 and Table 4. The wavelet types that were used are: Haar,
Daubechies (db2 and db4), Symlet (sym2 and sym4), Coiflet (coif1), Biorthogonal (bior1.1, bior3.1, rbio1.1)
and dmey. The values in these tables result from the application of soft and hard thresholding to the details of
the first and second DWT level decomposition of the image.
Comparisons between the de-noising results in terms of the computed values of MSE, SNR and
PSNR obtained when applying hard and soft thresholds on the detail coefficients resulting from the first and
second level DWT decomposition of the normal brain images indicate that hard thresholding Is better than
soft thresholding in the first and second levels of DWT. In addition, the comparison between the first and
second level metrics values obtained with hard thresholding of the details gave better results in the first level
of the DWT decomposition, especially with the selection threshold value method of Bal. sparsity-norm (sqrt).](https://image.slidesharecdn.com/v3111jan1722oct1613099-28509-1-edseptian-201028060020/85/SVM-Classification-of-MRI-Brain-Images-for-ComputerAssisted-Diagnosis-3-320.jpg)
![IJECE ISSN: 2088-8708
SVM Classification of MRI Brain Images for Computer-Assisted Diagnosis (Madina Hamiane)
2559
Table 4. Hard Threshold of the Second Level DWT
Fixed Form Threshold Bal. sparsity-norm (sqrt)
MSE SNR PSNR MSE SNR PSNR
haar 6.1712 29.1483 40.2271 6.6652 39.8927 39.8927
db2 6.2036 29.1255 40.2044 8.3351 27.8429 38.9217
db4 6.2313 29.1062 40.185 8.5546 27.73 38.8088
sym2 6.2036 29.1255 40.2044 8.3351 27.8429 38.9217
sym4 6.2315 29.1061 40.1849 8.7586 27.6276 38.7065
coif1 6.2027 29.1262 40.205 9.0768 27.4727 38.5515
bior1.1 6.1712 29.1483 40.2271 6.6652 28.8139 39.8927
bior3.1 6.4499 28.9564 40.0353 7.4515 28.3296 39.4084
rbio1.1 6.1712 29.1483 40.2271 6.6652 28.8139 39.8927
dmey 6.2565 29.0887 40.1675 8.4553 27.7807 38.8595
Table 5. Hard threshold of the First Level DWT with Bal. Sparsity-Norm (sqrt) Method
Bal. sparsity-norm (sqrt)
MSE SNR PSNR
bior1.1 6.0552 29.2307 40.3095
bior1.3 6.0511 29.2336 40.3124
bior1.5 6.0534 29.232 40.3108
bior2.2 6.1998 29.1282 40.207
bior2.4 6.1978 29.1296 40.2084
bior2.6 6.1977 29.1296 40.2085
bior2.8 6.1899 29.1352 40.214
bior3.1 6.2461 29.0959 40.1747
bior3.3 6.2464 29.0957 40.1745
bior3.5 6.2165 29.1165 40.1953
bior3.7 6.2159 29.1169 40.1958
bior3.9 6.2118 29.1198 40.1987
bior4.4 6.1719 29.1478 40.2266
bior5.5 6.1773 29.144 40.2228
bior6.8 6.1902 29.1349 40.2137
rbio1.1 6.0552 29.2307 40.3095
rbio1.3 6.1013 29.1977 40.2766
rbio1.5 6.1116 29.1904 40.2693
rbio2.2 6.172 29.1477 40.2265
rbio2.4 6.1801 29.1421 40.2209
rbio2.6 6.173 29.147 40.2258
rbio2.8 6.1859 29.138 40.2168
rbio3.1 6.6033 28.8544 39.9332
rbio3.3 6.3139 29.049 40.1278
rbio3.5 6.2597 29.0865 40.1653
rbio3.7 6.2472 29.0951 40.1739
rbio3.9 6.2441 29.0973 40.1761
rbio4.4 6.2302 29.107 40.1858
rbio5.5 6.2321 29.1057 40.1845
rbio6.8 6.1859 29.138 40.2168
After testing the above procedure on all normal brain images and identifying the best wavelet type,
best DWT level along with the best thresholding technique, based on the above metrics, the same procedure
of denoising was applied to all MRI brain images in the input data set.
2.3. Image Segmentation
Image segmentation is a method that split an image to a group of non-overlapping areas [6] .The
unification of these areas is the whole image. However, the boundaries of various tissues in brain images are
unclear and the intensities of the gray and white tissues are almost similar. The adjacent tissues are difficult
to be separated because the boundaries are smooth and the intensity does not change too much between these
tissues. Hence, edge detection is required prior to the image segmentation.
Image edges were detected by using the Canny method to find the binary gradient mask [7] as
shown in Figure 5. To detect weak and strong edges, this method uses two thresholds. Hence,
the Canny method is more likely to detect true weak edges, and less likely than the other methods to be
dispersed by noise. After detecting the edges, these edges were outlined on the original image to differentiate
between different tissues of the brain.
After outlining the edges on the image, global threshold using Otsu’s method [8] was applied to
identify the intensity level, and the image was then converted to a binary image and thresholded according to](https://image.slidesharecdn.com/v3111jan1722oct1613099-28509-1-edseptian-201028060020/85/SVM-Classification-of-MRI-Brain-Images-for-ComputerAssisted-Diagnosis-5-320.jpg)
![ ISSN: 2088-8708
IJECE Vol. 7, No. 5, October 2017 : 2555 – 2564
2560
value returned by the function of Otsu’s method. An example of the threshold segmentation output is shown
in Figure 6.
Figure 5. Binary gradient mask and abnormal brain with edges detected
Figure 6. Threshold Segmentation Figure 7. Threshold Segmentation without Edge
Detection
The thresholded image obtained by applying Otsu’s threshold but without edge detection is shown
in Figure 7. and clearly indicates that the edge detection technique is an important step that should not be
suppressed when applying the segmentation step that is based on intensity thresholding.
Figure 8. Tumor Threshold Mask Figure 9. Extracted Tumor Image
After thresholding the image, the holes in the image that are the same as the background were filled.
The thresholded image was then converted to a binary image and morphological operations were applied to
remove isolated pixels which are individual 1s that are surrounded by 0s. Next, another morphological
operation was applied that performs erosion followed by dilation. Erosion removes pixels on object
boundaries while dilation adds pixels to the boundaries of objects in an image. The regions of interest (ROI)
were subsequently extracted from the binary image as shown in Figure 8 displaying a tumor mask. The tumor
was extracted from the brain image by assigning a value of 0 to all pixels except the pixels of the tumor mask
as shown in Figure 9.
2.4. Image Feature Extraction
Various techniques for extracting features from MRI brain images have been reported in the
literature, the most common are: Discrete Wavelet Transform (DWT) [9] , Gabor filters [10] and Gray Level
Co-occurrence Matrix (GLCM) [11]. Both DWT and Gabor Filter methods produce feature vectors with a
large number of elements which necessitates the use of size reduction techniques prior to feeding the feature
vectors to the classifier. On the other hand, The Gray Level Co-occurrence Matrix (GLCM) has proven to be](https://image.slidesharecdn.com/v3111jan1722oct1613099-28509-1-edseptian-201028060020/85/SVM-Classification-of-MRI-Brain-Images-for-ComputerAssisted-Diagnosis-6-320.jpg)
![IJECE ISSN: 2088-8708
SVM Classification of MRI Brain Images for Computer-Assisted Diagnosis (Madina Hamiane)
2561
superior in terms the dimension of the feature vectors and thus is more appropriate for MRI image
classification.
GLCM is a statistical technique for extracting texture features from images [11]. It assumes that the
texture of normal tissues is very different from the texture of tumor tissues. The texture features extracted
from the GLCM matrix are: contrast, correlation, energy, homogeneity. Selecting a good set of features
improve the process of classification. Additional features were also extracted from this matrix which are:
mean, standard deviation, entropy, root mean square, variance, kurtosis, skewness. All features used in this
work are listed in Table 6. These features were extracted from the twenty normal images forming class I
images and the thirty images of abnormal regions of interest forming class II images. The averaged features
values are shown in Table 7.
Table 6. GLCM Features
Features Equation
Contrast
∑ 𝑝(𝑖, 𝑗)|𝑖 − 𝑗|2
𝑁−1
𝑖 , 𝑗 = 0
Correlation ∑ ∑ [𝑖𝑗 𝑝(𝑖, 𝑗)] − 𝛼𝑖 𝛼𝑗𝑗𝑖
𝑝𝑖 𝑝𝑗
Energy
∑ 𝑝(𝑖, 𝑗)2
𝑁−1
𝑖 , 𝑗 = 0
Homogeneity ∑ ∑
𝑝(𝑖, 𝑗)
1 + |𝑖 + 𝑗|𝑗𝑖
Mean ∑ 𝑝(𝑖, 𝑗)𝑁−1
𝑖 , 𝑗
𝑁 − 1
Standard
deviation √
1
𝑁
∑(𝑥𝑖 − 𝜇)2
𝑁
𝑖=1
Entropy − ∑ ∑ 𝑝(𝑖, 𝑗) ln 𝑝(𝑖, 𝑗)
𝑗𝑖
RMS
√
1
𝑁
∑ |𝑋 𝑛|2
𝑁
𝑛 = 1
Variance ∑ ∑ (𝑖
𝑁−1
𝑗
𝑁−1
𝑖
− 𝜇)2
𝑝(𝑖, 𝑗)
Kurtosis
𝑛 =
∑ (𝑋𝑖 − 𝑋 𝑎𝑣𝑔)4𝑛
𝑖=1
(∑ (𝑋𝑖 − 𝑋 𝑎𝑣𝑔)2𝑛
𝑖=1 )2
Skewness
√𝑛
∑ (𝑋𝑖 − 𝑋 𝑎𝑣𝑔)3𝑛
𝑖=1
(∑ (𝑋𝑖 − 𝑋 𝑎𝑣𝑔)2𝑛
𝑖=1 )3/2
Table 7. Extracted features of normal and abnormal images
Class/Feature
Class I
(Normal)
Class I
(Abormal)
Contrast 0.16178 0.053002
Correlation 0.96945 0.95696
Energy 0.482798 0.935961
Homogeneity 0.95239 0.99253
Mean 4088 1020
Standard
Deviation
22527.972 7888.474
Entropy 0.457085 0.923
RMS 10606.13 2854.718
Variance 5.13E+08 62293236
Kurtosis 59.01666 61.9667
Skewness 7.533646 7.806567
2.5. Image Classification
Classification is the process of categorizing a given input by a proper classifier. The objective of
classification is to give a label to each MR brain image based on some image’s features. The structure layout
and design of a classification system involves the choice and calculation of features from the images that we
want to classify as shown in Figure 10 [6].](https://image.slidesharecdn.com/v3111jan1722oct1613099-28509-1-edseptian-201028060020/85/SVM-Classification-of-MRI-Brain-Images-for-ComputerAssisted-Diagnosis-7-320.jpg)
![ ISSN: 2088-8708
IJECE Vol. 7, No. 5, October 2017 : 2555 – 2564
2562
Support Vector Machine (SVM) classifier was used in this work as it has shown to result in greater
accuracy compared to other classifier structures in the classification of MRI images [12] - [13]. The Support
Vector Machine (SVM) is a supervised learning technique that uses a set of labelled training data as input to
train the classifier and produce input-output mapping functions.
Figure 10. Image Classification System structure [6]
For MRI images, the SVM output is a hyperplane that classifies new MRI images. For the case of
the two class-classification used in this work, the process of the SVM technique is to find the hyperplane that
provides the largest minimum distance to the training data as shown in Figure 11. [14]-[15]
Figure 11. Optimal hyperplane in SVM [15]
The SVM classifier used in this work provides the possibility of choosing the kernel function [13].
The kernel function chosen is ‘RBF’ that represents the Gaussian Radial Basis Function kernel. This choice
was based on the excellent performance of this SVM kernel function as reported in the literature. The input
data set was divided in two subsets, a training set consisting of ten normal images and fifteen abnormal
images and a testing set consisting of the remaining ten normal and fifteen abnormal images. The Support
Vector Machine (SVM) classifier was trained after extracting the features and labels from the training set.
After training the classifier, the testing set was used to test the performance of the classifier and its
ability to accurately classify the MRI images as either normal or abnormal. To evaluate our SVM classifier, a
confusion matrix was built as shown in Table 8. and the performance of the classifier evaluated as shown in
Table IX. In the testing test, ten images were labelled as Normal and the remaining fifteen images were
labelled as Abnormal. As indicated in Table 9, the classifier succeeded to classify MRI brain images into
normal and abnormal.
Table 8. Confusion Matrix
Predicted
Normal Abnormal
Truth
Normal 20 0
Abnormal 0 30](https://image.slidesharecdn.com/v3111jan1722oct1613099-28509-1-edseptian-201028060020/85/SVM-Classification-of-MRI-Brain-Images-for-ComputerAssisted-Diagnosis-8-320.jpg)
![IJECE ISSN: 2088-8708
SVM Classification of MRI Brain Images for Computer-Assisted Diagnosis (Madina Hamiane)
2563
Table 9. Performance of RBF SVM classifier
Classes No. of
images
classified
No. of images
misclassified
Sensitivity specificity Accuracy
Class I
(Normal)
20 0 100% 100% 100%
Class II
(Abnormal)
30 0 100% 100% 100%
3. SUMMARY OF RESULTS
In this work, the two dimensional wavelet toolbox of MATLAB was used for the pre-processing of
the images by applying DWT to remove the noise from MRI brain images. The process first decomposes the
image, then applies threshold to the detail coefficients and after that reconstructs the noise-free image.
Different wavelets, thresholding techniques with various threshold selection types were investigated to
choose the best wavelet type and decomposition level along with the best thresholding technique. The
evaluation was done based on the values of the three metrics MSE, SNR and PSNR. Bior1.3 wavelet has
proven to be the best wavelet along with the first level of decomposition, hard thresholding and Bal. sparsity-
norm (sqrt) as the method of threshold selection value. Bior1.3 wavelet was applied on all images that were
used in this work.
MATLAB functions from the Image processing and the bioinformatics toolboxes were then used in
the image processing phase. Edge detection was applied as the first step to detect the edges of MRI brain
images. Canny method was then used which gave very good results. The edges were outlined on the original
image to differentiate between the various tissues of the brain, and then the brain images were segmented
based on intensity segmentation by using Otsu’s method as a second step. The last step of image processing
was to apply the morphological operations of erosion and dilation to extract the region of interest.
The steps used in processing the MRI brain images have shown effective extraction of the region of
interest from the twenty normal and thirty abnormal images. The extracted region of interest was then used in
the post processing step for the extraction of their features. GLCM was used to create a gray level co-
occurrence matrix from images. GLCM yielded 11 distinct features that were subsequently used in the
classification step. The features were extracted from each of the fifty brain images to form the feature matrix
characterising the image. Classification was performed using Support Vector machine with Gaussian Radial
Basis Function kernel which resulted in an effective classification of all images with 100% accuracy.
4. CONCLUSION
MRI images have many advantages in biomedical engineering compared to other imaging
techniques. This work focused on brain images because large areas of the organ process are affected by brain
injuries. Most movement and body functions are controlled and coordinated by the brain.
De-noising of MRI brain images was one of the objectives of this work. It was found that MRI brain
images can be efficiently denoised using the Discrete Wavelet Transforms (DWT) with thresholding as
confirmed by the optimal metrics values obtained. Further enhancement of the images was obtained through
the use of edge detection and threshold segmentation. It was shown that elimination of the edge detection
step resulted in segmentation inaccuracies. In addition, morphological operations were used to extract the
region of interest in the image.
Several features were extracted from the enhanced MRI images and were used to train an SVM
classifier with RBF kernel which succeeded in classifying the MRI brain images as normal or abnormal. The
accuracy of the SVM model was found to be 100% which outperforms results reported in the literature. This
accurate classification of the SVM classifier can be used by neurologists to help them to identify the
abnormality that might be hidden, due to the large number of slices that are obtained from MRI brain images.
REFERENCES
[1] K. & Becker J., The Whole Brain Atlas [http://www. med.harvard .edu/ aanlib/home.html]
[2] A. Dixit, & P. Sharma, “A Comparative Study of Wavelet Thresholding for Image Denoising”, International
Journal of Image, Graphics and Signal Processing, 39-46., 2014.
[3] A. Georg, & A. Prabavathy, “A Survey On Different Approaches Used In Image Quality Assessment”,
International Journal of Emerging Technology and Advanced Engineering, Volume 3, Issue 2, 2013.
[4] C. Varnan, A. Jagan, J. Kaur, D. Jyoti, & D. Rao, “Image Quality Assessment Techniques pn Spatial Domain”,
International Journal of Computer Science and Technology, Vol. 2, Issue 3 , 2011.
[5] S. Nisha, “Image Quality Assessment Techniques”, International Journal of Advanced Research in Computer
Science and Software Engineering, Volume 3, Issue 7, 2013.](https://image.slidesharecdn.com/v3111jan1722oct1613099-28509-1-edseptian-201028060020/85/SVM-Classification-of-MRI-Brain-Images-for-ComputerAssisted-Diagnosis-9-320.jpg)
![ ISSN: 2088-8708
IJECE Vol. 7, No. 5, October 2017 : 2555 – 2564
2564
[6] O. Marques, Practical Image and Video Processing Using MATLAB, by John Wiley & So"ns, Inc.,2011.
[7] A. Kulkarni, & R. Kamathe, “MRI Brain Image Segmentation by Edge Detection and Region Selection”,
International Journal of Technology and Science, Issue. 2, Vol. 1, 2014
[8] G. Evelin Sujji ,Y.V.S.Lakshmi, & G. Wiselin Ji, “MRI Brain Image Segmentation based on Thresholding”,
International Journal of Advanced Computer Research, Vol. 3, No.1 , Issue 8 , 2013.
[9] Icke, Guzide, Kamarthi, V.Sagar , “Feature extraction through discrete wavelet transform coefficients”, Intelligent
Systems in Design and Manufacturing VI, Proceedings of the SPIE, Volume 5999, pp. 27-35, 2005.
[10] S. Shah, & N Chauhan, “Classification of Brain MRI Images using Computational Intelligent Techniques”,
International Journal of Computer Applications, Volume 124 , No.14. 2015.
[11] Zulpe, N. & Pawar, V., “GLCM Textural Features for Brain Tumor Classification”, International Journal of
Computer Science Issues, Vol. 9, Issue 3, No 3, 2012
[12] V. Josephine, & P. Latha, “SVM -Based Automatic Medical Decision Support System For Medical Image”, Journal
of Theoretical and Applied Information Technolog, Vol. 66 No.3., 2014.
[13] A Yuniarti, "Classification and numbering of dental radiographs for an automated human identification system,”
TELKOMNIKA Telecommunication, Computing, Electronics and Control., vol. 10, no. 1, pp. 137-146, 2012.
[14] D. Boswell, Introduction to Support Vector Machines, available at: http://dustwell.com/PastWork/Intro ToSVM .pdf
[15] OpenCV, Introduction to Support Machines, available at: http://docs.opencv.org/2.4/doc/tutorials/ml/introductio
_to_svm/introduction_to_svm.html](https://image.slidesharecdn.com/v3111jan1722oct1613099-28509-1-edseptian-201028060020/85/SVM-Classification-of-MRI-Brain-Images-for-ComputerAssisted-Diagnosis-10-320.jpg)
SVM Classification of MRI Brain Images for ComputerAssisted Diagnosis
- 1. International Journal of Electrical and Computer Engineering (IJECE) Vol. 7, No. 5, October 2017, pp. 2555~2564 ISSN: 2088-8708, DOI: 10.11591/ijece.v7i1.pp2555-2564 2555 Journal homepage: http://iaesjournal.com/online/index.php/IJECE SVM Classification of MRI Brain Images for Computer- Assisted Diagnosis Madina Hamiane1 , Fatema Saeed2 Department of Telecommunication Engineering, Ahlia University, Manama, Bahrain Article Info ABSTRACT Article history: Received Oct 22, 2016 Revised Jan 11, 2017 Accepted Jul 26, 2017 Magnetic Resonance Imaging is a powerful technique that helps in the diagnosis of various medical conditions. MRI Image pre-processing followed by detection of brain abnormalities, such as brain tumors, are considered in this work. These images are often corrupted by noise from various sources. The Discrete Wavelet Transforms (DWT) with details thresholding is used for efficient noise removal followed by edge detection and threshold segmentation of the denoised images. Segmented image features are then extracted using morphological operations. These features are finally used to train an improved Support Vector Machine classifier that uses a Gausssian radial basis function kernel. The performance of the classifier is evaluated and the results of the classification show that the proposed scheme accurately distinguishes normal brain images from the abnormal ones and benign lesions from malignant tumours. The accuracy of the classification is shown to be 100% which is superior to the results reported in the literature. Keyword: Discrete wavelet transform support vector machine Classifier Feature extraction MRI brain image processing Image segmentation Copyright © 2017 Institute of Advanced Engineering and Science. All rights reserved. Corresponding Author: Madina Hamiane Departement of Telecommunication Engineering, Ahlia University, Manama, Kingdom of Bahrain Email: mhhamiane@ahlia.edu.bh 1. INTRODUCTION In the field of medicine, medical Image processing and analysis has excessive significance. It has arisen as one of the greatest significant tools to detect as well as identify many disorders. It enables both doctors and radiologists to reach a specific diagnosis, by visualizing and analyzing the image. Computer-Aided Diagnosis (CAD) is a method that is gaining importance in the day-to-day life. It can help radiologists precisely read images and detect probable findings to avoid improper understanding of lesions. However, it is essential to point out that CAD systems can only provide a second opinion and can by no means replace radiologists or physicians. There are many imaging techniques for the human soft tissue anatomy, such as Computed Tomography (CT), mammogram function, Magnetic Resonance Imaging (MRI) and so on. The focus of this work is on MRI images. MRI is a medical imaging technique that takes images of the inside of the human body. It is a pain-free, non-aggressive, non-radioactive technique for visualizing detailed information regarding the tumors and abnormalities without any human involvement. In digital image processing, image de-noising is an important procedure to obtain quality images, and enhance and recover detailed information that might be hidden in the data. It removes the noise that is acquired by the image during its acquisition or transmission. This noise is an obstacle for efficient image processing since it gives a poor image quality. Medical images are also corrupted by noise that lowers the visibility of low contrast objects and creates undesirable visual quality. The de-noising process facilitates the image classification accuracy and enhances the medical diagnosis. The objective of this work is to provide an automatic diagnostic tool that will help medical practitioners in diagnosing brain lesions by distinguishing them from normal brain tissue. The first step is to
- 2. ISSN: 2088-8708 IJECE Vol. 7, No. 5, October 2017 : 2555 – 2564 2556 enhance the MRI Images by developing their appearance and removing the unusual patterns caused by noise from the interference of different sources. This will result in an alternative image with enhanced and more noticeably structures. The second part of this work is to extract important image features from the de-noised images and use these image characteristics in the classification of the MRI images. This will assist the medical specialist in the interpretation of MRI Brain images. 2. METHODOLOGY AND RESULTS 2.1. Image Database: MRI brain images used in this work were selected from Harvard Medical School Database [1] which is a web-based database that contains a large variety of MRI brain slice images. The datasets used in this work consists of T2-weighted MRI brain images in axial plane. T2 model was chosen in this work since T2 images are of higher-contrast and clearer vision compared to other modalities. The number of MRI brain images in the input dataset is Forty. Twenty are of which are normal brain images and twenty of abnormal brain images. The abnormal brain MR images of the dataset consist of the following diseases: Acute stroke, Alzheimer's disease, Cerebral Toxoplasmosis, Chronic subdural hematoma, Hypertensive encephalopathy, Lyme encephalopathy, Metastatic bronchogenic carcinoma, Multiple sclerosis, Sarcoma, Sub-acute stroke, Multiple embolic infarctions, Fatal stroke, Motor neuron disease, Pick's disease and Herpes encephalitis. 2.2. Pre-Processing: MRI Image denoing The Discrete Wavelet Transforms (DWT) decomposition was used along with thresholding techniques [2] for efficient noise removal. The MATLAB wavelet toolbox was used for this purpose. The wavelet–based methods used for denoising are depicted in Figure 1 below and can be summarized as: Decompose: Choose a wavelet and a decomposition level N. Compute the wavelet decomposition of the image down to level N. Threshold detail coefficients: For each level from 1 to N, threshold the detail coefficients. Reconstruct: Compute wavelet reconstruction using the original approximation coefficients of level N and the modified detail coefficients of levels from 1 to N. Figure 1. Wavelet Image Denoising After decomposing the original image that is shown in Figure 2, into its approximation and detail coefficients as shown in Figure 3, all the detail coefficients (Horizontal, diagonal and vertical details) of each level are thresholded according to a thresholding method and a thresholding value. Different threshold methods and different threshold selection values available in MATLAB DWT toolbox were compared. The threshold methods available are: Hard and Soft threshold, while the threshold selection values are: Fixed form threshold, Penalize high, Penalize medium, Penalize low and Bal. sparsity-norm (sqrt). The noise corrupting the images was assumed to be white and thus the available structure of unscaled white noise was considered for the test experiments of this work. MRI Brain Image Apply DWT Apply Inverse DWT Reconstructed Denoised MRI Brain Image Remove noise from detail coefficients
- 3. IJECE ISSN: 2088-8708 SVM Classification of MRI Brain Images for Computer-Assisted Diagnosis (Madina Hamiane) 2557 After denoising, the thresholded detail coefficients these were used together with the original approximation coefficient to reconstruct the denoised image as shown in Figure. 4. The effectiveness of the denoising process is measured through the use of the three metrics: Peak Signal to Noise Ratio (PSNR), Signal to Noise Ratio (SNR) and the Mean Squared Error (MSE) [3]-[5]. Figure 2. Original MRI brain image Figure 3. Approximation and detail coefficients Figure 4. Denoised image The de-noising is considered effective when the highest values of PSNR and SNR and the lowest value of MSE are reached concurrently. The values of MSE, SNR and PSNR obtained from denoising a sample normal MRI brain image by applying DWT approach with different wavelet types and thresholding techniques are shown in Table 1, Table 2, Table 3 and Table 4. The wavelet types that were used are: Haar, Daubechies (db2 and db4), Symlet (sym2 and sym4), Coiflet (coif1), Biorthogonal (bior1.1, bior3.1, rbio1.1) and dmey. The values in these tables result from the application of soft and hard thresholding to the details of the first and second DWT level decomposition of the image. Comparisons between the de-noising results in terms of the computed values of MSE, SNR and PSNR obtained when applying hard and soft thresholds on the detail coefficients resulting from the first and second level DWT decomposition of the normal brain images indicate that hard thresholding Is better than soft thresholding in the first and second levels of DWT. In addition, the comparison between the first and second level metrics values obtained with hard thresholding of the details gave better results in the first level of the DWT decomposition, especially with the selection threshold value method of Bal. sparsity-norm (sqrt).
- 4. ISSN: 2088-8708 IJECE Vol. 7, No. 5, October 2017 : 2555 – 2564 2558 Table 1. Soft Threshold of the First Level DWT Fixed Form Threshold Bal. sparsity-norm (sqrt) MSE SNR PSNR MSE SNR PSNR haar 6.8441 28.6988 39.7776 6.2676 29.081 40.1598 db2 7.0249 28.5856 39.6644 12.2775 26.1609 37.2397 db4 7.1624 28.5014 39.5802 14.5285 25.4298 36.5086 sym2 7.0249 28.5856 39.6644 12.2775 26.1609 37.2397 sym4 7.0913 28.5447 39.6235 12.3006 26.1527 37.2315 coif1 7.0695 28.5581 39.6369 12.4009 26.1175 37.1963 bior1.1 6.8441 28.6988 39.7776 6.2676 29.081 40.1598 bior3.1 7.2066 28.4747 39.5535 12.5871 26.0527 37.1316 rbio1.1 6.8441 28.6988 39.7776 6.2676 29.081 40.1598 dmey 8.4339 27.7917 38.8705 12.3989 26.1182 37.197 Table 2. Hard Threshold of the First Level DWT Fixed Form Threshold Bal. sparsity-norm (sqrt) MSE SNR PSNR MSE SNR PSNR Haar 6.0745 29.2169 40.2957 6.0552 29.2307 40.3095 db2 6.0687 29.221 40.2998 6.1166 29.1869 40.2657 db4 6.0973 29.2006 40.2794 6.241 29.0994 40.1782 sym2 6.0687 29.221 40.2998 6.1166 29.1869 40.2657 sym4 6.0984 29.1998 40.2787 6.1783 29.1433 40.2221 coif1 6.0979 29.2002 40.279 6.1894 29.1355 40.2143 bior1.1 6.0745 29.2169 40.2957 6.0552 29.2307 40.3095 bior3.1 6.1221 29.183 40.2618 6.2461 29.0959 40.1747 rbio1.1 6.0745 29.2169 40.2957 6.0552 29.2307 40.3095 dmey 6.1068 29.1938 40.2727 6.1981 29.1294 40.2082 Table III. Soft threshold of the Second level DWT Fixed Form Threshold Bal. sparsity-norm (sqrt) MSE SNR PSNR MSE SNR PSNR haar 7.5359 28.2806 39.3595 16.1744 24.9637 36.0425 db2 7.6185 28.2333 39.3121 17.7031 24.5715 35.6503 db4 7.5661 28.2633 39.3421 17.7031 24.8113 35.6503 sym2 7.6185 28.2333 39.3121 17.7031 24.5715 35.6503 sym4 7.642 28.2199 39.2987 18.0929 24.4769 35.5557 coif1 7.6258 28.2291 39.3079 20.0744 24.0256 35.1044 bior1.1 7.5359 28.2806 39.3595 16.1744 24.9637 36.0425 bior3.1 7.9474 28.0498 39.1286 11.7208 26.3624 37.4412 rbio1.1 7.5359 28.2806 39.3595 16.1744 24.9637 36.0425 dmey 7.646 28.2176 39.2964 16.632 24.8425 35.9214 The Penalize high, medium and low method does not differentiate significantly between the different decomposition levels, the different wavelets and between the thresholding methods as it gave the same metrics values for all wavelets and both levels of DWT decomposition as well as the same metrics values for hard and soft thresholding methods. We can therefore conclude that this thresholding technique is not suitable for denoising of MRI brain images that were used in this work and was discarded from the analysis. The first level of DWT denoising with hard thresholding and with the “Bal. sparsity-norm (sqrt)” techniques of thresholding gave the best results. Since the same results were obtained for the Haar, Bior and Rbio wavelets, the denoising process was thus repeated for the members of the same wavelets and the results were tabulated in Table 5 which indicates that inBior1.3 gave the minimum MSE, highest SNR and highest PSNR values for the five images compared to other wavelet members.
- 5. IJECE ISSN: 2088-8708 SVM Classification of MRI Brain Images for Computer-Assisted Diagnosis (Madina Hamiane) 2559 Table 4. Hard Threshold of the Second Level DWT Fixed Form Threshold Bal. sparsity-norm (sqrt) MSE SNR PSNR MSE SNR PSNR haar 6.1712 29.1483 40.2271 6.6652 39.8927 39.8927 db2 6.2036 29.1255 40.2044 8.3351 27.8429 38.9217 db4 6.2313 29.1062 40.185 8.5546 27.73 38.8088 sym2 6.2036 29.1255 40.2044 8.3351 27.8429 38.9217 sym4 6.2315 29.1061 40.1849 8.7586 27.6276 38.7065 coif1 6.2027 29.1262 40.205 9.0768 27.4727 38.5515 bior1.1 6.1712 29.1483 40.2271 6.6652 28.8139 39.8927 bior3.1 6.4499 28.9564 40.0353 7.4515 28.3296 39.4084 rbio1.1 6.1712 29.1483 40.2271 6.6652 28.8139 39.8927 dmey 6.2565 29.0887 40.1675 8.4553 27.7807 38.8595 Table 5. Hard threshold of the First Level DWT with Bal. Sparsity-Norm (sqrt) Method Bal. sparsity-norm (sqrt) MSE SNR PSNR bior1.1 6.0552 29.2307 40.3095 bior1.3 6.0511 29.2336 40.3124 bior1.5 6.0534 29.232 40.3108 bior2.2 6.1998 29.1282 40.207 bior2.4 6.1978 29.1296 40.2084 bior2.6 6.1977 29.1296 40.2085 bior2.8 6.1899 29.1352 40.214 bior3.1 6.2461 29.0959 40.1747 bior3.3 6.2464 29.0957 40.1745 bior3.5 6.2165 29.1165 40.1953 bior3.7 6.2159 29.1169 40.1958 bior3.9 6.2118 29.1198 40.1987 bior4.4 6.1719 29.1478 40.2266 bior5.5 6.1773 29.144 40.2228 bior6.8 6.1902 29.1349 40.2137 rbio1.1 6.0552 29.2307 40.3095 rbio1.3 6.1013 29.1977 40.2766 rbio1.5 6.1116 29.1904 40.2693 rbio2.2 6.172 29.1477 40.2265 rbio2.4 6.1801 29.1421 40.2209 rbio2.6 6.173 29.147 40.2258 rbio2.8 6.1859 29.138 40.2168 rbio3.1 6.6033 28.8544 39.9332 rbio3.3 6.3139 29.049 40.1278 rbio3.5 6.2597 29.0865 40.1653 rbio3.7 6.2472 29.0951 40.1739 rbio3.9 6.2441 29.0973 40.1761 rbio4.4 6.2302 29.107 40.1858 rbio5.5 6.2321 29.1057 40.1845 rbio6.8 6.1859 29.138 40.2168 After testing the above procedure on all normal brain images and identifying the best wavelet type, best DWT level along with the best thresholding technique, based on the above metrics, the same procedure of denoising was applied to all MRI brain images in the input data set. 2.3. Image Segmentation Image segmentation is a method that split an image to a group of non-overlapping areas [6] .The unification of these areas is the whole image. However, the boundaries of various tissues in brain images are unclear and the intensities of the gray and white tissues are almost similar. The adjacent tissues are difficult to be separated because the boundaries are smooth and the intensity does not change too much between these tissues. Hence, edge detection is required prior to the image segmentation. Image edges were detected by using the Canny method to find the binary gradient mask [7] as shown in Figure 5. To detect weak and strong edges, this method uses two thresholds. Hence, the Canny method is more likely to detect true weak edges, and less likely than the other methods to be dispersed by noise. After detecting the edges, these edges were outlined on the original image to differentiate between different tissues of the brain. After outlining the edges on the image, global threshold using Otsu’s method [8] was applied to identify the intensity level, and the image was then converted to a binary image and thresholded according to
- 6. ISSN: 2088-8708 IJECE Vol. 7, No. 5, October 2017 : 2555 – 2564 2560 value returned by the function of Otsu’s method. An example of the threshold segmentation output is shown in Figure 6. Figure 5. Binary gradient mask and abnormal brain with edges detected Figure 6. Threshold Segmentation Figure 7. Threshold Segmentation without Edge Detection The thresholded image obtained by applying Otsu’s threshold but without edge detection is shown in Figure 7. and clearly indicates that the edge detection technique is an important step that should not be suppressed when applying the segmentation step that is based on intensity thresholding. Figure 8. Tumor Threshold Mask Figure 9. Extracted Tumor Image After thresholding the image, the holes in the image that are the same as the background were filled. The thresholded image was then converted to a binary image and morphological operations were applied to remove isolated pixels which are individual 1s that are surrounded by 0s. Next, another morphological operation was applied that performs erosion followed by dilation. Erosion removes pixels on object boundaries while dilation adds pixels to the boundaries of objects in an image. The regions of interest (ROI) were subsequently extracted from the binary image as shown in Figure 8 displaying a tumor mask. The tumor was extracted from the brain image by assigning a value of 0 to all pixels except the pixels of the tumor mask as shown in Figure 9. 2.4. Image Feature Extraction Various techniques for extracting features from MRI brain images have been reported in the literature, the most common are: Discrete Wavelet Transform (DWT) [9] , Gabor filters [10] and Gray Level Co-occurrence Matrix (GLCM) [11]. Both DWT and Gabor Filter methods produce feature vectors with a large number of elements which necessitates the use of size reduction techniques prior to feeding the feature vectors to the classifier. On the other hand, The Gray Level Co-occurrence Matrix (GLCM) has proven to be
- 7. IJECE ISSN: 2088-8708 SVM Classification of MRI Brain Images for Computer-Assisted Diagnosis (Madina Hamiane) 2561 superior in terms the dimension of the feature vectors and thus is more appropriate for MRI image classification. GLCM is a statistical technique for extracting texture features from images [11]. It assumes that the texture of normal tissues is very different from the texture of tumor tissues. The texture features extracted from the GLCM matrix are: contrast, correlation, energy, homogeneity. Selecting a good set of features improve the process of classification. Additional features were also extracted from this matrix which are: mean, standard deviation, entropy, root mean square, variance, kurtosis, skewness. All features used in this work are listed in Table 6. These features were extracted from the twenty normal images forming class I images and the thirty images of abnormal regions of interest forming class II images. The averaged features values are shown in Table 7. Table 6. GLCM Features Features Equation Contrast ∑ 𝑝(𝑖, 𝑗)|𝑖 − 𝑗|2 𝑁−1 𝑖 , 𝑗 = 0 Correlation ∑ ∑ [𝑖𝑗 𝑝(𝑖, 𝑗)] − 𝛼𝑖 𝛼𝑗𝑗𝑖 𝑝𝑖 𝑝𝑗 Energy ∑ 𝑝(𝑖, 𝑗)2 𝑁−1 𝑖 , 𝑗 = 0 Homogeneity ∑ ∑ 𝑝(𝑖, 𝑗) 1 + |𝑖 + 𝑗|𝑗𝑖 Mean ∑ 𝑝(𝑖, 𝑗)𝑁−1 𝑖 , 𝑗 𝑁 − 1 Standard deviation √ 1 𝑁 ∑(𝑥𝑖 − 𝜇)2 𝑁 𝑖=1 Entropy − ∑ ∑ 𝑝(𝑖, 𝑗) ln 𝑝(𝑖, 𝑗) 𝑗𝑖 RMS √ 1 𝑁 ∑ |𝑋 𝑛|2 𝑁 𝑛 = 1 Variance ∑ ∑ (𝑖 𝑁−1 𝑗 𝑁−1 𝑖 − 𝜇)2 𝑝(𝑖, 𝑗) Kurtosis 𝑛 = ∑ (𝑋𝑖 − 𝑋 𝑎𝑣𝑔)4𝑛 𝑖=1 (∑ (𝑋𝑖 − 𝑋 𝑎𝑣𝑔)2𝑛 𝑖=1 )2 Skewness √𝑛 ∑ (𝑋𝑖 − 𝑋 𝑎𝑣𝑔)3𝑛 𝑖=1 (∑ (𝑋𝑖 − 𝑋 𝑎𝑣𝑔)2𝑛 𝑖=1 )3/2 Table 7. Extracted features of normal and abnormal images Class/Feature Class I (Normal) Class I (Abormal) Contrast 0.16178 0.053002 Correlation 0.96945 0.95696 Energy 0.482798 0.935961 Homogeneity 0.95239 0.99253 Mean 4088 1020 Standard Deviation 22527.972 7888.474 Entropy 0.457085 0.923 RMS 10606.13 2854.718 Variance 5.13E+08 62293236 Kurtosis 59.01666 61.9667 Skewness 7.533646 7.806567 2.5. Image Classification Classification is the process of categorizing a given input by a proper classifier. The objective of classification is to give a label to each MR brain image based on some image’s features. The structure layout and design of a classification system involves the choice and calculation of features from the images that we want to classify as shown in Figure 10 [6].
- 8. ISSN: 2088-8708 IJECE Vol. 7, No. 5, October 2017 : 2555 – 2564 2562 Support Vector Machine (SVM) classifier was used in this work as it has shown to result in greater accuracy compared to other classifier structures in the classification of MRI images [12] - [13]. The Support Vector Machine (SVM) is a supervised learning technique that uses a set of labelled training data as input to train the classifier and produce input-output mapping functions. Figure 10. Image Classification System structure [6] For MRI images, the SVM output is a hyperplane that classifies new MRI images. For the case of the two class-classification used in this work, the process of the SVM technique is to find the hyperplane that provides the largest minimum distance to the training data as shown in Figure 11. [14]-[15] Figure 11. Optimal hyperplane in SVM [15] The SVM classifier used in this work provides the possibility of choosing the kernel function [13]. The kernel function chosen is ‘RBF’ that represents the Gaussian Radial Basis Function kernel. This choice was based on the excellent performance of this SVM kernel function as reported in the literature. The input data set was divided in two subsets, a training set consisting of ten normal images and fifteen abnormal images and a testing set consisting of the remaining ten normal and fifteen abnormal images. The Support Vector Machine (SVM) classifier was trained after extracting the features and labels from the training set. After training the classifier, the testing set was used to test the performance of the classifier and its ability to accurately classify the MRI images as either normal or abnormal. To evaluate our SVM classifier, a confusion matrix was built as shown in Table 8. and the performance of the classifier evaluated as shown in Table IX. In the testing test, ten images were labelled as Normal and the remaining fifteen images were labelled as Abnormal. As indicated in Table 9, the classifier succeeded to classify MRI brain images into normal and abnormal. Table 8. Confusion Matrix Predicted Normal Abnormal Truth Normal 20 0 Abnormal 0 30
- 9. IJECE ISSN: 2088-8708 SVM Classification of MRI Brain Images for Computer-Assisted Diagnosis (Madina Hamiane) 2563 Table 9. Performance of RBF SVM classifier Classes No. of images classified No. of images misclassified Sensitivity specificity Accuracy Class I (Normal) 20 0 100% 100% 100% Class II (Abnormal) 30 0 100% 100% 100% 3. SUMMARY OF RESULTS In this work, the two dimensional wavelet toolbox of MATLAB was used for the pre-processing of the images by applying DWT to remove the noise from MRI brain images. The process first decomposes the image, then applies threshold to the detail coefficients and after that reconstructs the noise-free image. Different wavelets, thresholding techniques with various threshold selection types were investigated to choose the best wavelet type and decomposition level along with the best thresholding technique. The evaluation was done based on the values of the three metrics MSE, SNR and PSNR. Bior1.3 wavelet has proven to be the best wavelet along with the first level of decomposition, hard thresholding and Bal. sparsity- norm (sqrt) as the method of threshold selection value. Bior1.3 wavelet was applied on all images that were used in this work. MATLAB functions from the Image processing and the bioinformatics toolboxes were then used in the image processing phase. Edge detection was applied as the first step to detect the edges of MRI brain images. Canny method was then used which gave very good results. The edges were outlined on the original image to differentiate between the various tissues of the brain, and then the brain images were segmented based on intensity segmentation by using Otsu’s method as a second step. The last step of image processing was to apply the morphological operations of erosion and dilation to extract the region of interest. The steps used in processing the MRI brain images have shown effective extraction of the region of interest from the twenty normal and thirty abnormal images. The extracted region of interest was then used in the post processing step for the extraction of their features. GLCM was used to create a gray level co- occurrence matrix from images. GLCM yielded 11 distinct features that were subsequently used in the classification step. The features were extracted from each of the fifty brain images to form the feature matrix characterising the image. Classification was performed using Support Vector machine with Gaussian Radial Basis Function kernel which resulted in an effective classification of all images with 100% accuracy. 4. CONCLUSION MRI images have many advantages in biomedical engineering compared to other imaging techniques. This work focused on brain images because large areas of the organ process are affected by brain injuries. Most movement and body functions are controlled and coordinated by the brain. De-noising of MRI brain images was one of the objectives of this work. It was found that MRI brain images can be efficiently denoised using the Discrete Wavelet Transforms (DWT) with thresholding as confirmed by the optimal metrics values obtained. Further enhancement of the images was obtained through the use of edge detection and threshold segmentation. It was shown that elimination of the edge detection step resulted in segmentation inaccuracies. In addition, morphological operations were used to extract the region of interest in the image. Several features were extracted from the enhanced MRI images and were used to train an SVM classifier with RBF kernel which succeeded in classifying the MRI brain images as normal or abnormal. The accuracy of the SVM model was found to be 100% which outperforms results reported in the literature. This accurate classification of the SVM classifier can be used by neurologists to help them to identify the abnormality that might be hidden, due to the large number of slices that are obtained from MRI brain images. REFERENCES [1] K. & Becker J., The Whole Brain Atlas [http://www. med.harvard .edu/ aanlib/home.html] [2] A. Dixit, & P. Sharma, “A Comparative Study of Wavelet Thresholding for Image Denoising”, International Journal of Image, Graphics and Signal Processing, 39-46., 2014. [3] A. Georg, & A. Prabavathy, “A Survey On Different Approaches Used In Image Quality Assessment”, International Journal of Emerging Technology and Advanced Engineering, Volume 3, Issue 2, 2013. [4] C. Varnan, A. Jagan, J. Kaur, D. Jyoti, & D. Rao, “Image Quality Assessment Techniques pn Spatial Domain”, International Journal of Computer Science and Technology, Vol. 2, Issue 3 , 2011. [5] S. Nisha, “Image Quality Assessment Techniques”, International Journal of Advanced Research in Computer Science and Software Engineering, Volume 3, Issue 7, 2013.
- 10. ISSN: 2088-8708 IJECE Vol. 7, No. 5, October 2017 : 2555 – 2564 2564 [6] O. Marques, Practical Image and Video Processing Using MATLAB, by John Wiley & So"ns, Inc.,2011. [7] A. Kulkarni, & R. Kamathe, “MRI Brain Image Segmentation by Edge Detection and Region Selection”, International Journal of Technology and Science, Issue. 2, Vol. 1, 2014 [8] G. Evelin Sujji ,Y.V.S.Lakshmi, & G. Wiselin Ji, “MRI Brain Image Segmentation based on Thresholding”, International Journal of Advanced Computer Research, Vol. 3, No.1 , Issue 8 , 2013. [9] Icke, Guzide, Kamarthi, V.Sagar , “Feature extraction through discrete wavelet transform coefficients”, Intelligent Systems in Design and Manufacturing VI, Proceedings of the SPIE, Volume 5999, pp. 27-35, 2005. [10] S. Shah, & N Chauhan, “Classification of Brain MRI Images using Computational Intelligent Techniques”, International Journal of Computer Applications, Volume 124 , No.14. 2015. [11] Zulpe, N. & Pawar, V., “GLCM Textural Features for Brain Tumor Classification”, International Journal of Computer Science Issues, Vol. 9, Issue 3, No 3, 2012 [12] V. Josephine, & P. Latha, “SVM -Based Automatic Medical Decision Support System For Medical Image”, Journal of Theoretical and Applied Information Technolog, Vol. 66 No.3., 2014. [13] A Yuniarti, "Classification and numbering of dental radiographs for an automated human identification system,” TELKOMNIKA Telecommunication, Computing, Electronics and Control., vol. 10, no. 1, pp. 137-146, 2012. [14] D. Boswell, Introduction to Support Vector Machines, available at: http://dustwell.com/PastWork/Intro ToSVM .pdf [15] OpenCV, Introduction to Support Machines, available at: http://docs.opencv.org/2.4/doc/tutorials/ml/introductio _to_svm/introduction_to_svm.html