SlideShare a Scribd company logo
1 of 17
CERVICAL CANCER CLASSIFICATION
     USING GABOR FILTERS


2011 First IEEE International Conference on Healthcare
      Informatics, Imaging and Systems Biology




              Advisor : Yin-Fu Huang


              Student : Chen-Ju Lai
OUTLINE
 INTRODUCTION
 DATA COLLECTION

 METHODOLOGY AND RESULT

 CONCLUSION
INTRODUCTION
 Cervical cancer
 Biopsy test

 Cervical intraepithelial neoplasia (CIN)



   Input : histology images
    Feature extraction : texture , using Gabor filter
    Classification method : K-Means Clustering
    Output : Normal/CIN1/CIN2/CIN3/Malignant
                            Pre-cancer
DATA COLLECTION
 Pathology anatomy laboratory of Saiful Anwar
  hospital
 Biopsy images : resolution 4080 x 3072 pixels

  (categorized by an expert pathologist)
 475 labelled images are used in this study



    Normal    CIN1       CIN2      CIN3     Malignant
      60       70         50        50        245
DATA COLLECTION
CANCER
  GRADING
METHODOLOGY
    AND
   RESULT
GABOR FILTER
                                         Spatial domain

Gabor elementary function


2D Gaussian function

                         x'=x cos θ +y sin θ and y'=-x sin θ+y cos θ.

              From (1) and (2), the Gabor elementary function
              can be rewritten as
                              centre frequency



σx and σy are the spread of the Gaussian in x and y directions
GABOR FILTER
                              Frequency domain
 Assuming σx and σy are the same




  u'=u cos θ +v sin θ and v'=u sin θ+v cos θ


      v
                                 (U,V) can decision (U0 ,θ)
  V                    φ

          U0

          θ                u
                 U
GABOR FILTER
   Sample




     Original          (a) f = 0.2,θ = 0 0      (b) f = 0.2,θ = 45 0




(c) f = 0.2,θ = 90 0    (d) f = 0.2,θ = 135 0
COMPARE TEMPLATE
 Compare each pixel with the templates.
 Supervised Training : generated templates
       24 distinctive Gabor filters are used to generate a
        feature vector for each pixel and its neighbors.


        background      basal       stroma       normal      abnormal
                                                  cells        cells
         500 pixels   500 pixels   500 pixels   500 pixels   500 pixels
         average      average      average      average      average
SEGMENTED IMAGE & K-MEAN
CLUSTERING
   Segmentation
       After each pixel compare with the five feature vector
        templates.
         blue : background , yellow : basal , white : stroma,
         green : normal cell , red : abnormal cell


   K-Means Clustering
       Based on the color.
       Quantify the normal nuclei and abnormal nuclei.
SEGMENTED IMAGE & K-MEAN
CLUSTERING
CALCULATE THE RATIO AND GRADING
   How to classify the image into categories ?
        Use the ratio of number of normal and abnormal cells.


        Benign      the number of abnormal cells < 5
        CIN 1       ratio between abnormal and normal cells <
                    1/3
        CIN 2       ratio between abnormal and normal cells
                    between 1/3 ~ 2/3
        CIN 3       ratio between abnormal and normal cells
                    > 2/3 or full
        Malignant   ratio between abnormal and normal cells >
                    CIN 3
CALCULATE THE RATIO AND GRADING
   Table 1 shows the sample of the ratio between abnormal
    and normal cell.
CALCULATE THE RATIO AND GRADING
   Table 2 shows the confusion matrix of the Gabor filter
    hybrid with K-means clustering.
   The sensitivity of normal is 87%, CIN 1 is 86%, CIN 2 82
    %,CIN 3 84% and malignant is 89%.
   The percentage of specificity of this system is 85%.



                                                       (52/60)=0.87
                                                       (60/70)=0.86
                                                       (41/50)=0.82
                                                       (42/50)=0.84
                                                       (219/245)=0.89
COMPARED WITH SERVAL METHOD
   Gray level Features , color K-mean and incremental
    thresholding.
CONCLUSION
   A methodology of Gabor filter bank with hybrid K-
    means clustering algorithm has been proposed.

   Designing Gabor filter bank with the optimum
    selection parameters and different classification
    method can improve performance using this
    algorithm.

More Related Content

Viewers also liked

Features image processing and Extaction
Features image processing and ExtactionFeatures image processing and Extaction
Features image processing and ExtactionAli A Jalil
 
Contouring Guidelines for Gynecological Malignancy
Contouring Guidelines for Gynecological MalignancyContouring Guidelines for Gynecological Malignancy
Contouring Guidelines for Gynecological MalignancyJyotirup Goswami
 
Conventional Brachytherapy in carcinoma cervix
Conventional Brachytherapy in carcinoma cervixConventional Brachytherapy in carcinoma cervix
Conventional Brachytherapy in carcinoma cervixIsha Jaiswal
 
Contouring guidelines Cervix IMRT
Contouring guidelines Cervix IMRTContouring guidelines Cervix IMRT
Contouring guidelines Cervix IMRTDebarshi Lahiri
 
image guided brachytherapy carcinoma cervix
image guided brachytherapy carcinoma cerviximage guided brachytherapy carcinoma cervix
image guided brachytherapy carcinoma cervixIsha Jaiswal
 
Radiotherapy in carcinoma cervix
Radiotherapy in carcinoma cervixRadiotherapy in carcinoma cervix
Radiotherapy in carcinoma cervixDebarshi Lahiri
 
Neck node & Contouring Guidelines
Neck node & Contouring GuidelinesNeck node & Contouring Guidelines
Neck node & Contouring GuidelinesManoj Gupta
 
Altered Fractionation Radiotherapy in Head-Neck Cancer
Altered Fractionation Radiotherapy in Head-Neck CancerAltered Fractionation Radiotherapy in Head-Neck Cancer
Altered Fractionation Radiotherapy in Head-Neck CancerJyotirup Goswami
 
EBRT IN CARCINOMA CERVIX
EBRT IN CARCINOMA CERVIXEBRT IN CARCINOMA CERVIX
EBRT IN CARCINOMA CERVIXIsha Jaiswal
 
Feature Extraction
Feature ExtractionFeature Extraction
Feature Extractionskylian
 
Image feature extraction
Image feature extractionImage feature extraction
Image feature extractionRushin Shah
 
HPV and Cervical Cancer: Mechanisms
HPV and Cervical Cancer: MechanismsHPV and Cervical Cancer: Mechanisms
HPV and Cervical Cancer: Mechanismsbrandolina1
 
Atlas of organs at risk delineation head and neck region
Atlas of organs at risk  delineation head and neck regionAtlas of organs at risk  delineation head and neck region
Atlas of organs at risk delineation head and neck regionRajesh Balakrishnan
 
Cervical Cancer Educational Presentation
Cervical Cancer Educational PresentationCervical Cancer Educational Presentation
Cervical Cancer Educational Presentationrinki singh
 
Management of carcinoma hypopharynx
 Management  of carcinoma hypopharynx  Management  of carcinoma hypopharynx
Management of carcinoma hypopharynx Isha Jaiswal
 

Viewers also liked (19)

Features image processing and Extaction
Features image processing and ExtactionFeatures image processing and Extaction
Features image processing and Extaction
 
Feature Extraction
Feature ExtractionFeature Extraction
Feature Extraction
 
Contouring Guidelines for Gynecological Malignancy
Contouring Guidelines for Gynecological MalignancyContouring Guidelines for Gynecological Malignancy
Contouring Guidelines for Gynecological Malignancy
 
Conventional Brachytherapy in carcinoma cervix
Conventional Brachytherapy in carcinoma cervixConventional Brachytherapy in carcinoma cervix
Conventional Brachytherapy in carcinoma cervix
 
Contouring guidelines Cervix IMRT
Contouring guidelines Cervix IMRTContouring guidelines Cervix IMRT
Contouring guidelines Cervix IMRT
 
image guided brachytherapy carcinoma cervix
image guided brachytherapy carcinoma cerviximage guided brachytherapy carcinoma cervix
image guided brachytherapy carcinoma cervix
 
Radiotherapy in carcinoma cervix
Radiotherapy in carcinoma cervixRadiotherapy in carcinoma cervix
Radiotherapy in carcinoma cervix
 
Neck node & Contouring Guidelines
Neck node & Contouring GuidelinesNeck node & Contouring Guidelines
Neck node & Contouring Guidelines
 
Altered Fractionation Radiotherapy in Head-Neck Cancer
Altered Fractionation Radiotherapy in Head-Neck CancerAltered Fractionation Radiotherapy in Head-Neck Cancer
Altered Fractionation Radiotherapy in Head-Neck Cancer
 
EBRT IN CARCINOMA CERVIX
EBRT IN CARCINOMA CERVIXEBRT IN CARCINOMA CERVIX
EBRT IN CARCINOMA CERVIX
 
Feature Extraction
Feature ExtractionFeature Extraction
Feature Extraction
 
Image feature extraction
Image feature extractionImage feature extraction
Image feature extraction
 
HPV and Cervical Cancer: Mechanisms
HPV and Cervical Cancer: MechanismsHPV and Cervical Cancer: Mechanisms
HPV and Cervical Cancer: Mechanisms
 
Atlas of organs at risk delineation head and neck region
Atlas of organs at risk  delineation head and neck regionAtlas of organs at risk  delineation head and neck region
Atlas of organs at risk delineation head and neck region
 
Cervical Cancer
Cervical CancerCervical Cancer
Cervical Cancer
 
Radiation for Cervix Cancer
Radiation for Cervix CancerRadiation for Cervix Cancer
Radiation for Cervix Cancer
 
Cervical Cancer Educational Presentation
Cervical Cancer Educational PresentationCervical Cancer Educational Presentation
Cervical Cancer Educational Presentation
 
Female pelvis ppt
Female pelvis pptFemale pelvis ppt
Female pelvis ppt
 
Management of carcinoma hypopharynx
 Management  of carcinoma hypopharynx  Management  of carcinoma hypopharynx
Management of carcinoma hypopharynx
 

Similar to Cervical Cancer Classification Using Gabor Filters

Translational health research
Translational health researchTranslational health research
Translational health researchKrishna Karri
 
Seminar Slides
Seminar SlidesSeminar Slides
Seminar Slidespannicle
 
mlsb07_zhao_iob.ppt
mlsb07_zhao_iob.pptmlsb07_zhao_iob.ppt
mlsb07_zhao_iob.pptbutest
 
Machine vision system for the automatic segmentation of plants under differen...
Machine vision system for the automatic segmentation of plants under differen...Machine vision system for the automatic segmentation of plants under differen...
Machine vision system for the automatic segmentation of plants under differen...Mehran Mesbahzadeh
 
In-silico structure activity relationship study of toxicity endpoints by QSAR...
In-silico structure activity relationship study of toxicity endpoints by QSAR...In-silico structure activity relationship study of toxicity endpoints by QSAR...
In-silico structure activity relationship study of toxicity endpoints by QSAR...Kamel Mansouri
 
Analysis of pancreas histological images for glucose intollerance identificat...
Analysis of pancreas histological images for glucose intollerance identificat...Analysis of pancreas histological images for glucose intollerance identificat...
Analysis of pancreas histological images for glucose intollerance identificat...Tathagata Bandyopadhyay
 
IRJET- Analysis of Alzheimer’s Disease on MRI Image using Transform and Featu...
IRJET- Analysis of Alzheimer’s Disease on MRI Image using Transform and Featu...IRJET- Analysis of Alzheimer’s Disease on MRI Image using Transform and Featu...
IRJET- Analysis of Alzheimer’s Disease on MRI Image using Transform and Featu...IRJET Journal
 
Application of a Selective Gaussian Naïve Bayes Model for Diffuse-Large B-Cel...
Application of a Selective Gaussian Naïve Bayes Model for Diffuse-Large B-Cel...Application of a Selective Gaussian Naïve Bayes Model for Diffuse-Large B-Cel...
Application of a Selective Gaussian Naïve Bayes Model for Diffuse-Large B-Cel...NTNU
 
Avery Yip poster
Avery Yip posterAvery Yip poster
Avery Yip posterAvery Yip
 
Image segmentation
Image segmentationImage segmentation
Image segmentationkhyati gupta
 
www.ijera.com 68 | P a g e Leaf Disease Detection Using Arm7 and Image Proces...
www.ijera.com 68 | P a g e Leaf Disease Detection Using Arm7 and Image Proces...www.ijera.com 68 | P a g e Leaf Disease Detection Using Arm7 and Image Proces...
www.ijera.com 68 | P a g e Leaf Disease Detection Using Arm7 and Image Proces...IJERA Editor
 
Classification and Segmentation of Glaucomatous Image Using Probabilistic Neu...
Classification and Segmentation of Glaucomatous Image Using Probabilistic Neu...Classification and Segmentation of Glaucomatous Image Using Probabilistic Neu...
Classification and Segmentation of Glaucomatous Image Using Probabilistic Neu...ijsrd.com
 
Anomaly Detection using SIngle Class SVM with Gaussian Kernel
Anomaly Detection using SIngle Class SVM with Gaussian KernelAnomaly Detection using SIngle Class SVM with Gaussian Kernel
Anomaly Detection using SIngle Class SVM with Gaussian KernelAnoop Vasant Kumar
 
Anomaly Detection using SIngle Class SVM with Gaussian Kernel
Anomaly Detection using SIngle Class SVM with Gaussian KernelAnomaly Detection using SIngle Class SVM with Gaussian Kernel
Anomaly Detection using SIngle Class SVM with Gaussian KernelAnoop Vasant Kumar
 
Cytoscan_Copy_Number_Confirmation_with_SYBR_Green_qPCR_white_paper
Cytoscan_Copy_Number_Confirmation_with_SYBR_Green_qPCR_white_paperCytoscan_Copy_Number_Confirmation_with_SYBR_Green_qPCR_white_paper
Cytoscan_Copy_Number_Confirmation_with_SYBR_Green_qPCR_white_paperAndrea Ujvari
 
MAMMOGRAM IMAGE ANALYSIS
MAMMOGRAM IMAGE ANALYSISMAMMOGRAM IMAGE ANALYSIS
MAMMOGRAM IMAGE ANALYSISajayhakkumar
 

Similar to Cervical Cancer Classification Using Gabor Filters (20)

Translational health research
Translational health researchTranslational health research
Translational health research
 
Seminar Slides
Seminar SlidesSeminar Slides
Seminar Slides
 
Cluster Validation
Cluster ValidationCluster Validation
Cluster Validation
 
303 306
303 306303 306
303 306
 
mlsb07_zhao_iob.ppt
mlsb07_zhao_iob.pptmlsb07_zhao_iob.ppt
mlsb07_zhao_iob.ppt
 
Machine vision system for the automatic segmentation of plants under differen...
Machine vision system for the automatic segmentation of plants under differen...Machine vision system for the automatic segmentation of plants under differen...
Machine vision system for the automatic segmentation of plants under differen...
 
In-silico structure activity relationship study of toxicity endpoints by QSAR...
In-silico structure activity relationship study of toxicity endpoints by QSAR...In-silico structure activity relationship study of toxicity endpoints by QSAR...
In-silico structure activity relationship study of toxicity endpoints by QSAR...
 
Microarray Analysis
Microarray AnalysisMicroarray Analysis
Microarray Analysis
 
Analysis of pancreas histological images for glucose intollerance identificat...
Analysis of pancreas histological images for glucose intollerance identificat...Analysis of pancreas histological images for glucose intollerance identificat...
Analysis of pancreas histological images for glucose intollerance identificat...
 
IRJET- Analysis of Alzheimer’s Disease on MRI Image using Transform and Featu...
IRJET- Analysis of Alzheimer’s Disease on MRI Image using Transform and Featu...IRJET- Analysis of Alzheimer’s Disease on MRI Image using Transform and Featu...
IRJET- Analysis of Alzheimer’s Disease on MRI Image using Transform and Featu...
 
Application of a Selective Gaussian Naïve Bayes Model for Diffuse-Large B-Cel...
Application of a Selective Gaussian Naïve Bayes Model for Diffuse-Large B-Cel...Application of a Selective Gaussian Naïve Bayes Model for Diffuse-Large B-Cel...
Application of a Selective Gaussian Naïve Bayes Model for Diffuse-Large B-Cel...
 
Avery Yip poster
Avery Yip posterAvery Yip poster
Avery Yip poster
 
Image segmentation
Image segmentationImage segmentation
Image segmentation
 
poster_silhouette
poster_silhouetteposter_silhouette
poster_silhouette
 
www.ijera.com 68 | P a g e Leaf Disease Detection Using Arm7 and Image Proces...
www.ijera.com 68 | P a g e Leaf Disease Detection Using Arm7 and Image Proces...www.ijera.com 68 | P a g e Leaf Disease Detection Using Arm7 and Image Proces...
www.ijera.com 68 | P a g e Leaf Disease Detection Using Arm7 and Image Proces...
 
Classification and Segmentation of Glaucomatous Image Using Probabilistic Neu...
Classification and Segmentation of Glaucomatous Image Using Probabilistic Neu...Classification and Segmentation of Glaucomatous Image Using Probabilistic Neu...
Classification and Segmentation of Glaucomatous Image Using Probabilistic Neu...
 
Anomaly Detection using SIngle Class SVM with Gaussian Kernel
Anomaly Detection using SIngle Class SVM with Gaussian KernelAnomaly Detection using SIngle Class SVM with Gaussian Kernel
Anomaly Detection using SIngle Class SVM with Gaussian Kernel
 
Anomaly Detection using SIngle Class SVM with Gaussian Kernel
Anomaly Detection using SIngle Class SVM with Gaussian KernelAnomaly Detection using SIngle Class SVM with Gaussian Kernel
Anomaly Detection using SIngle Class SVM with Gaussian Kernel
 
Cytoscan_Copy_Number_Confirmation_with_SYBR_Green_qPCR_white_paper
Cytoscan_Copy_Number_Confirmation_with_SYBR_Green_qPCR_white_paperCytoscan_Copy_Number_Confirmation_with_SYBR_Green_qPCR_white_paper
Cytoscan_Copy_Number_Confirmation_with_SYBR_Green_qPCR_white_paper
 
MAMMOGRAM IMAGE ANALYSIS
MAMMOGRAM IMAGE ANALYSISMAMMOGRAM IMAGE ANALYSIS
MAMMOGRAM IMAGE ANALYSIS
 

More from es712

Extracting ocean
Extracting oceanExtracting ocean
Extracting oceanes712
 
Feature selection and classification in supporting report based self-manageme...
Feature selection and classification in supporting report based self-manageme...Feature selection and classification in supporting report based self-manageme...
Feature selection and classification in supporting report based self-manageme...es712
 
Exploiting social tagging in a web 2.0 recommender system(lab)
Exploiting social tagging in a web 2.0 recommender system(lab)Exploiting social tagging in a web 2.0 recommender system(lab)
Exploiting social tagging in a web 2.0 recommender system(lab)es712
 
A framework for emotion mining from text in online social networks(final)
A framework for emotion mining from text in online social networks(final)A framework for emotion mining from text in online social networks(final)
A framework for emotion mining from text in online social networks(final)es712
 
Pca and kpca of ecg signal
Pca and kpca of ecg signalPca and kpca of ecg signal
Pca and kpca of ecg signales712
 
Automatic road environment classification 20121002
Automatic road environment classification 20121002Automatic road environment classification 20121002
Automatic road environment classification 20121002es712
 
Classification of commercial and personal profiles on my space
Classification of commercial and personal profiles on my spaceClassification of commercial and personal profiles on my space
Classification of commercial and personal profiles on my spacees712
 
Tennis video shot classification based on support vector
Tennis video shot classification based on support vectorTennis video shot classification based on support vector
Tennis video shot classification based on support vectores712
 
Social media recommendation based on people and tags (final)
Social media recommendation based on people and tags (final)Social media recommendation based on people and tags (final)
Social media recommendation based on people and tags (final)es712
 

More from es712 (9)

Extracting ocean
Extracting oceanExtracting ocean
Extracting ocean
 
Feature selection and classification in supporting report based self-manageme...
Feature selection and classification in supporting report based self-manageme...Feature selection and classification in supporting report based self-manageme...
Feature selection and classification in supporting report based self-manageme...
 
Exploiting social tagging in a web 2.0 recommender system(lab)
Exploiting social tagging in a web 2.0 recommender system(lab)Exploiting social tagging in a web 2.0 recommender system(lab)
Exploiting social tagging in a web 2.0 recommender system(lab)
 
A framework for emotion mining from text in online social networks(final)
A framework for emotion mining from text in online social networks(final)A framework for emotion mining from text in online social networks(final)
A framework for emotion mining from text in online social networks(final)
 
Pca and kpca of ecg signal
Pca and kpca of ecg signalPca and kpca of ecg signal
Pca and kpca of ecg signal
 
Automatic road environment classification 20121002
Automatic road environment classification 20121002Automatic road environment classification 20121002
Automatic road environment classification 20121002
 
Classification of commercial and personal profiles on my space
Classification of commercial and personal profiles on my spaceClassification of commercial and personal profiles on my space
Classification of commercial and personal profiles on my space
 
Tennis video shot classification based on support vector
Tennis video shot classification based on support vectorTennis video shot classification based on support vector
Tennis video shot classification based on support vector
 
Social media recommendation based on people and tags (final)
Social media recommendation based on people and tags (final)Social media recommendation based on people and tags (final)
Social media recommendation based on people and tags (final)
 

Cervical Cancer Classification Using Gabor Filters

  • 1. CERVICAL CANCER CLASSIFICATION USING GABOR FILTERS 2011 First IEEE International Conference on Healthcare Informatics, Imaging and Systems Biology Advisor : Yin-Fu Huang Student : Chen-Ju Lai
  • 2. OUTLINE  INTRODUCTION  DATA COLLECTION  METHODOLOGY AND RESULT  CONCLUSION
  • 3. INTRODUCTION  Cervical cancer  Biopsy test  Cervical intraepithelial neoplasia (CIN)  Input : histology images Feature extraction : texture , using Gabor filter Classification method : K-Means Clustering Output : Normal/CIN1/CIN2/CIN3/Malignant Pre-cancer
  • 4. DATA COLLECTION  Pathology anatomy laboratory of Saiful Anwar hospital  Biopsy images : resolution 4080 x 3072 pixels (categorized by an expert pathologist)  475 labelled images are used in this study Normal CIN1 CIN2 CIN3 Malignant 60 70 50 50 245
  • 7. GABOR FILTER Spatial domain Gabor elementary function 2D Gaussian function x'=x cos θ +y sin θ and y'=-x sin θ+y cos θ. From (1) and (2), the Gabor elementary function can be rewritten as centre frequency σx and σy are the spread of the Gaussian in x and y directions
  • 8. GABOR FILTER Frequency domain  Assuming σx and σy are the same u'=u cos θ +v sin θ and v'=u sin θ+v cos θ v (U,V) can decision (U0 ,θ) V φ U0 θ u U
  • 9. GABOR FILTER  Sample Original (a) f = 0.2,θ = 0 0 (b) f = 0.2,θ = 45 0 (c) f = 0.2,θ = 90 0 (d) f = 0.2,θ = 135 0
  • 10. COMPARE TEMPLATE  Compare each pixel with the templates.  Supervised Training : generated templates  24 distinctive Gabor filters are used to generate a feature vector for each pixel and its neighbors. background basal stroma normal abnormal cells cells 500 pixels 500 pixels 500 pixels 500 pixels 500 pixels average average average average average
  • 11. SEGMENTED IMAGE & K-MEAN CLUSTERING  Segmentation  After each pixel compare with the five feature vector templates.  blue : background , yellow : basal , white : stroma,  green : normal cell , red : abnormal cell  K-Means Clustering  Based on the color.  Quantify the normal nuclei and abnormal nuclei.
  • 12. SEGMENTED IMAGE & K-MEAN CLUSTERING
  • 13. CALCULATE THE RATIO AND GRADING  How to classify the image into categories ?  Use the ratio of number of normal and abnormal cells. Benign the number of abnormal cells < 5 CIN 1 ratio between abnormal and normal cells < 1/3 CIN 2 ratio between abnormal and normal cells between 1/3 ~ 2/3 CIN 3 ratio between abnormal and normal cells > 2/3 or full Malignant ratio between abnormal and normal cells > CIN 3
  • 14. CALCULATE THE RATIO AND GRADING  Table 1 shows the sample of the ratio between abnormal and normal cell.
  • 15. CALCULATE THE RATIO AND GRADING  Table 2 shows the confusion matrix of the Gabor filter hybrid with K-means clustering.  The sensitivity of normal is 87%, CIN 1 is 86%, CIN 2 82 %,CIN 3 84% and malignant is 89%.  The percentage of specificity of this system is 85%. (52/60)=0.87 (60/70)=0.86 (41/50)=0.82 (42/50)=0.84 (219/245)=0.89
  • 16. COMPARED WITH SERVAL METHOD  Gray level Features , color K-mean and incremental thresholding.
  • 17. CONCLUSION  A methodology of Gabor filter bank with hybrid K- means clustering algorithm has been proposed.  Designing Gabor filter bank with the optimum selection parameters and different classification method can improve performance using this algorithm.