references - shodhgangashodhganga.inflibnet.ac.in/bitstream/10603/18614/... · boniface kayode,...
TRANSCRIPT
83
REFERENCES
[1] AhsanunNasehKhudori, Muhammad Faisal, RirienKusumawati, 2012,
Fingerprint Identification System Using Wavelet Transform And Artificial
Neural Network, International Journal of Science and Technology, Vol.1,
No.1, pp.12-17.
[2] Amit Kaul, Arora, A.S., Sushil Chauhan, 2012, Rotation Invariant
Fingerprint Core-Point Detection Using DWT, International Journal of
Computer Applications, pp.32-35.
[3] Andrej Kisel, AlexejKochetkov, and Justas Kranauskas, 2008,
Fingerprint Minutiae Matching without Global Alignment Using Local
Structures, Informatica, Vol.19, No.1,pp.31-44.
[4] ArumugaPerumal S., Rajakumar T.C., Krishnan N., 2011, Fuzzy based
Filtering Approach on Histogram Specification for Fingerprint Image
Enhancement, International Journal of Computer Applications, Vol.23,
No.8, pp.30-33.
[5] Ashish kumarDass, RabindrakumarShial and BhabaniSankar Gouda,
2012, Improving MSN and PSNR for Finger-print Image noised by
Gaussian and Salt and Pepper, The International Journal of Multimedia
and its Application, Vol.4, No.4, pp.59-72.
[6] Atanu Chatterjee, ShuvankarMandal, AtiqurRahaman G. M., and Abu
Shamim Mohammad Arif, 2010, Fingerprint Identification and
Verification System by Minutiae Extraction using Artificial Neural
Network, Journal of Convergence Information Technology, Vol.1, Issue
1, pp.12-16.
[7] AvinashPokhriyal and SushmaLehri, 2010, A New method of Fingerprint
Authentication Using 2D Wavelets, Journal of Theoretical and Applied
Information Technology, Vol.13, No.2, pp.131-138.
84
[8] BhupeshGour, Bandopadhyaya T.K., and Sudhir Sharma, 2008,
Fingerprint Feature Extraction Using Midpoint ridge Contour Method and
Neural Network, International Journal of Computer Science and Network
Security, Vol.8, No.7, pp.99-103.
[9] Bhuyan M.H., and Bhattacharyya D.K., 2011, An Effective Fingerprint
Classification and Search Method, International Journal of Computer
Science and Network Security, Vol.9, No.11, pp.39-48.
[10] ChaitanyaKommini, SrinivasuluAsadi, KamaleshEllanti, 2011,
Scale and Rotation Independent Fingerprint Recognition, International
Journal of Computer Science and Information Technologies, Vol.2, No.4,
pp.1764-1773.
[11] Chandra E., and Kanagalakshmi K., 2011, Noise Elimination in
Fingerprint Image Using Median Filter, International Journal Advanced
Networking and Applications, Vol.2, Issue 6, pp.950-955.
[12] Ching-Tang Hsieh, Shys-RongShyu and Kuo-Ming Hung, 2009, An
Effective Method for Fingerprint Classification, Tamkang Journal of
Science and Engineering, Vol.12, No.2, pp.169-182.
[13] Chitreshsaraswat and Amit Kumar, 2010, An Efficient Automatic
Attendance System using Fingerprint Verification Technique,
International Journal on Computer Science and Engineering, Vol.2,
No.2, pp.264-269.
[14] Dattatray V. Jadhav, Pawan K.,Ajmera, 2010, Multi resolution
Feature Based Subspace Analysis for Fingerprint Recognition,
International Journal of Computer Applications, Vol.1, No.13, pp.1-4.
[15] David Zhang, 2011, Selecting a Reference High Resolution for
Fingerprint Recognition Using Minutiae and Pores, IEEE Transactions on
Instrumentation and Measurement, Vol.60, No.3, pp.863-871.
[16] Divyakant T. Meva, Kumbharana, C.K., and Amit D. Kothari, 2012,
The Study of Adoption of Neural Network Approach in Fingerprint
85
recognition, International Journal of Computer Applications, Vol.40,
No.11, pp.8-11.
[17] Dongjin Kwon, II Dong Yun, Duck Hoon Kim and Sang Uk Lee,
2006, Fingerprint Matching Method Using Minutiae Clustering and
Warping, IEEE, pp.1-4.
[18] Heeseung Choi, Kyoungtaek Choi and Jaihie Kim, 2011,
Fingerprint Matching Incorporating Ridge Features With Minutiae, IEEE
Transactions on information Forensics and Security, Vol.6, No.2,
pp.338-345.
[19] Iwasokun Gabriel Babatunde, Akinyokun, Oluwole Charles, Alese
Boniface Kayode, OlabodeOlatunbosun, 2011, Adaptive and Faster
Approach to Fingerprint Minutiae and Validation, International Journal
of Computer Science and Security, Vol.5, Issue 4, pp.414-424.
[20] James Stephen M., and Prasad Reddy P.V.G.D., 2012, Enhancing
Fingerprint Image through Ridge Orientation with Neural Network
Approach and Ternarization for Effective Minutiae Extraction,
International Journal of Matching Learning and Computing, Vol.2, No.4,
pp.397-401.
[21] Jianjiang Feng, 2007, Combining minutiae descriptors for
fingerprint matching, The Journal of the pattern Recognition Society,
pp.342-352.
[22] Jossy P. George, Abhilash S.K., and Raja K.B., 2012, Transform
Domain Fingerprint Identification Based on DTCWT, International
Journal of Advanced Computer Science and Applications, Vol.3, No.1,
pp.190-195.
[23] Ju Cheng Yang and Dong Sun Park, 2008, Fingerprint Verification
Based on Invariant Moment Features and Nonlinear BPNN, International
Journal of Control, Automation, Vol.6, No.6, pp.800-808.
86
[24] Jugal Kishore Gupta and Rajendra Kumar, 2010, An efficient ANN
Based approach for Latent Fingerprint Matching, International Journal of
Computer Applications, Vol.7, No.10, pp.18-21.
[25] Kalyani Mali and Samayita Bhattacharya, 2011, Fingerprint
Recognition Using Global and Local Structures, International Journal on
Computer Science and Engineering, Vol.3, No.1, pp.161-172.
[26] Kekre H.B., TanujaSarode, RekhaVig, 2011, Automated
Fingerprint Identification System based on Sectorized Complex Walsh
plane, International Journal of Computer Applications, pp.6-11.
[27] KondreddiGopi and Pramod, J.T., 2012, Fingerprint Recognition
Using Gabor Filter and Frequency Domain Filtering, Journal of
Electronics and Communication Engineering, Vol.2, Issue 6, pp.17-21.
[28] Lakshmi Deepika C., Kandaswamy A., Vimal C., and Sathish B.,
2010, Invariant Feature Extraction from Fingerprint Biometric Using
Pseudo Zernike Moments, International Journal of Computer
Communication and Information System, Vol.2, No.1, pp.104-108.
[29] Lavanya, B.,N., and Raja, K.,B., 2011, Performance Evaluation of
Fingerprints Identification Based on DCT and DWT using Multiple
Matching Techniques, International Journal of Computer Science, Vol.8,
No.1, Issue 6, pp.275-283.
[30] Le Hoang Thai and Ha Nhat Tam, 2010, Fingerprint recognition
using standardized fingerprint model, International Journal of Computer
Science, Vol.7, No.7, Issue 3, pp.11-17.
[31] Leng, W. Y., and Shamsuddin, S. M., 2012, Fingerprint
Identification using Discretization Technique, International Journal of
Computer and Communication Engineering, Vol.6, pp.205-213.
[32] Liu Wei, 2008, Fingerprint Classification Using Singularities
Detection, International Journal of Mathematics and Computers in
Simulation, Vol.2, Issue 2, pp.158-162.
87
[33] lmdadullslam, Md., Nasima Begum, MahbubulAlam and Amin M.
R., 2010, Fingerprint Detection Using Canny Filter and DWT, a new
Approach, Journal of Information Processing Systems, Vol.6, No.4,
pp.511-520.
[34] Manu Garg, Er., Harish Bansal, 2013, Fingerprint Recognition
System using Minutiae Estimation, International Journal of Application
or Innovation in Engineering and Management, Vol.2, Issue 5, pp.31-
36.
[35] Mary Lourde, R., and DushyantKhosla, 2010, Fingerprint
Identification in Biometric Security Systems, International Journal of
Computer and Electrical Engineering, Vol.2, No.5, pp.852-855.
[36] MonowarHussainBhuyan, SaratSaharia, and Dhruba Kr
Bhattacharyya, 2010, An Effective Method for Fingerprint Classification,
International Arab Journal of e-Technology, Vol.1, No.3, pp.89-97.
[37] Mustafa Salah Khalefa, Zaid Amin Abduljabar, and Huda Ameer
Zeki, 2011, Fingerprint Image Enhancement by Develop Mehtre
Technique, Advanced computing An International Journal, Vol.2, No.6,
pp.171-182.
[38] MuzhirShaban Al-Ani, 2013, A Novel Thinning Algorithm for
Fingerprint Recognition, International Journal of Engineering Sciences,
Vol.2, No.2, pp.43-48.
[39] Omobayo A. Esan, Tranos , Seleman M. Ngwira, KeneilweZuva,
2013, Performance Improvement of Authentication of Fingerprints using
Enhancement and Matching Algorithms, International Journal of
Emerging Technology and Advanced Engineering, Vol.3, Issue 2,
pp.472-482.
[40] PankajDeshmukh, SirajPathan, RiyazPathan, 2013, Image
Enhancement Techniques for Fingerprint Identification, International
Journal of Scientific and Research Publications, Vol.3, Issue 3, pp.1-9.
88
[41] Parul Mishra Ajit Kumar Shrivastava and Amit Saxena, 2013,
Enhanced Thinning Based Finger Print Recognition, International Journal
on Cybemetics and Informatics, Vol.2, No.2, pp.33-46.
[42] Patil S.R., and Suralkar S R., 2013, Neural Network based
Fingerprint Classification, International Journal of Science and Research,
Vol.2, Issue 1, pp.58-62.
[43] Patil S.R., and Suralkar S.R., 2012, Fingerprint Classification using
Artificial Neural Network, International Journal of Emerging Technology
and Advanced Engineering, Vol.2, Issue 10, pp.513-517.
[44] Prasanna Lakshmi G., Chandulal J. A., Gopalakrishna Y., 2012,
Fingerprint Analysis and Matching using fuzzy logic design, Journal of
Computer Engineering (IOSRJCE), vol.1, Issue 6, pp.04-08.
[45] Preeti Pathak, 2010, Image Compression Algorithms for
Fingerprint System, (IJCSI) International Journal of Computer Science,
Vol.7, Issue 3, No.9, pp.45-50.
[46] Prince, Manvjeet Kaur, Ajay Mittal, 2010, Fingerprint matching
system using Level 3 features, International Journal of Engineering
Science and Technology, Vol.2, No.6, pp.2258-2262.
[47] Rajasekar R., and Meena K., 2013, Fingerprint Recognition Using
Multi-Resolution Techniques, International Journal of Electronics
Communication and Computer Engineering, Vol.4, Issue 2, pp.1-7.
[48] RajuRajkumar and Hemachandran K., 2012, A Secondary
Fingerprint Enhancement and Minutiae Extraction, International Journal
of Signal and Image Processing, Vol.3, No.2, pp.185-196.
[49] RakeshVerma and AnujGoel, 2011, Wavelet Application in
Fingerprint Recognition, (IJSCE) International Journal of Soft computing
and Engineering, Vol.1, Issue 4, pp.129-134.
[50] Ramachandra A.C., Abhilash S.K., Raja K.B., Venugopal K.R., and
Patnaik L.M., 2012, Feature Level Fusion Based Biomodal Biometric
89
using Transformation Domine Techniques, IOSR Journal of Computer
Engineering, Vol.3, Issue 3, pp39-46.
[51] Ravi J., Raja K.B., and Venugopal K.R., 2009, Fingerprint
Recognition using Minutia Score Matching, International Journal of
Engineering Science and Technology, Vol.1, No.2, pp.35-42.
[52] Rijo Jackson Tom and Arulkumaran T., 2013, Fingerprint Based
Gender Classification using 2D Discrete Wavelet Transform and Principal
Component Analysis, International Journal of Engineering Trends and
Technology, Vol.4, Issue 2, pp.199-203.
[53] SangitaBharkad and ManeshKokare, 2012, Hartley Transform
Based Fingerprint Matching, Journal of Information Processing Systems,
Vol.8, No.1, pp.85-100.
[54] SarnaliBasak, lmdadullslam Md., and Amin M.R., 2012, A New
Approach to Fingerprint Detection Using a Combination of Minutiae
Points and Invariant Moments Parameters, Journal of Information
Processing Systems, Vol.8, No.3, pp.421-436.
[55] ShabanaTadvi and Mahesh Kolte, 2010, A Hybrid System for
Fingerprint Identification, International Journal on Computer Science
and Engineering, Vol.2, No.3, pp.767-771.
[56] Shashi Kumar D.R., Raja K.B., Chhotaray R.K.,
SabyasachiPattanaik, 2011, DWT Based Fingerprint Recognition using
Non Minutiae Features, International Journal of Computer Science, Vol.
8, Issue 2, pp.257-265.
[57] Srinivasan, K., and Chandrasekar, C., 2012, An Efficient Fuzzy
Based Filtering Technique for Fingerprint Image Enhancement,
American Journal of Scientific Research, Issue 43, pp.125-140.
[58] SudhaPonnarasi, S., and Rajaram, M., 2011, Estimating the
Impact of Minutia Extraction Algorithms in Fingerprint Recognition,
90
International Journal of Research and Reviews in Computer Science,
Vol.2, No.6, pp.1268-1272.
[59] Sung-Woo Han, Dae-SeongJeoune and Young-woo Yoon, 2013,
Minutiae Detection Algorithm from Fingerprint Image using the
improved Tracing on Ridge Curve, Interntational Journal of Security and
its Applications, Vol.7, No.4, pp.343-352.
[60] Suzan Abdulla Mahmood and Amera Ismail Melhum, 2010, An
Authentication System using Fingerprint Minutiae Extraction and Neural
Network, Journal of Al-Nahrain University, Vol.13, No.4, pp.216-220.
[61] TerjeKristensen, 2012, Two Different Regimes of Fingerprint
Identification–A Comparison, American Journal of Computational and
Applied Mathematics, Vol.2, No.3, pp.64-72.
[62] Thaiyalnayaki K., Syed Abdul Karim S., and VarshaParmar P.,
2010, Finger Print Recognition using Discrete Wavelet Transform,
International Journal of Computer Applications, Vol.1, No.24, pp.96-
100.
[63] The Henry Classification System, International Biometric Group,
New York, USA, 2003
[64] Uma Maheswari, S., and Chandra, E., 2012, A Review study on
Fingerprint Classification Algorithm used for Fingerprint Identification
and Recognition, International Journal of Computer Science and
Technology, Vol.3, Issue 1, pp.739-745.
[65] Verma, R.N., and Chauhan, D.S., 2011, Effect of Pressure
Variation on the Fingerprint Minutiae Based Feature Vector Matching,
World of Computer Science and Information Technology Journal, Vol.1,
No.9, pp. 376-379.
[66] Vidhya, T., and Thivakaran, T.K., 2012, Fingerprint Image
Enhancement using Vavelet over Gabor Filters, International Journal
Computer Technology and Applications, Vol.3, No.3, pp.1049-1054.
91
[67] Vinothkanna R., and Amitabh Wahi, 2012, Feature Extraction from
Blurred Fingerprints Using Image Negative Method, International
Journal of Engineering and Innovative Technology, Vol.1, Issue 6,
pp.208-210.
[68] Waleed A. Mahmud Al-Jouhar, Talib M. Jawad Abbas Al-Talib,
Hamudi A.R., Salman 2010, Fingerprint Image Recognition Using
Walidlet Transform, Australian Journal of Basic and Applied Science,
Vol.4, No.8, pp.3970-3976.
[69] Zahoor Ahmad Jhat, AjazHussain Mir, and SeeminRubab, 2011,
Personal Verification using Fingerprint Texture Feature, International
Journal of Security and its Application, Vol. 5, No.3, pp.11-22.
[70] ZhiHao Lo, Peng Leong Teh, Siak Wang Khor, 2010, An Approach
for Minutiae-based Fingerprint Feature Extraction, Journal of Computer
Science and Engineering, Vol.1, Issue 2, pp.28-33.
92
APPENDIX A
SOURCE CODE
clear all
close all
clc
I=(imread('10_2.bmp'));
[X,map] = rgb2ind(I,128);
surf(double(X))
xlabel('Rows')
ylabel('Columns')
zlabel('Intensity profile')
figure
% plane information
imshow(I(:,:,1))
title('Plane-1')
surf(double(I(:,:,1)))
title('Plane-1')
xlabel('Rows')
ylabel('Columns')
zlabel('Intensity profile')
figure
imshow(I(:,:,2))
title('Plane-2')
surf(double(I(:,:,2)))
title('Plane-2')
xlabel('Rows')
ylabel('Columns')
zlabel('Intensity profile')
93
imshow(I(:,:,3))
title('Plane-1')
figure
surf(double(I(:,:,3)))
title('Plane-3')
xlabel('Rows')
ylabel('Columns')
zlabel('Intensity profile')
figure
imshow(I)
title('True color image')
figure
X=X(1:256,1:256);
nbcol = size(map,1);
[ca1,ch1,cv1,cd1] = dwt2(X,'db1');
[rough_param]=calculate_roughness_L1A(ca1);
L1=rough_param;
figure
[rough_param]=calculate_roughness_L1H(ch1);
L1=[L1 rough_param];
figure
[rough_param]=calculate_roughness_L1V(cv1);
L1=[L1 rough_param];
figure
[rough_param]=calculate_roughness_L1D(cd1);
L1=[L1 rough_param];
close all
[A1]=feature_extraction_wavelet(ca1,ch1,cv1,cd1);
cod_ca1 = wcodemat(ca1,nbcol);
94
figure
surf(cod_ca1)
ylabel('Rows=128')
xlabel('Columns=128')
zlabel('Coefficients')
title('Approximation Level-1')
figure
cod_ch1 = wcodemat(ch1,nbcol);
surf(cod_ch1)
ylabel('Rows=128')
xlabel('Columns=128')
zlabel('Coefficients')
title('Horizontal Level-1')
figure
cod_cv1 = wcodemat(cv1,nbcol);
surf(cod_cv1)
ylabel('Rows=128')
xlabel('Columns=128')
zlabel('Coefficients')
title('Vertical Level-1')
figure
cod_cd1 = wcodemat(cd1,nbcol);
surf(cod_cd1)
ylabel('Rows=128')
xlabel('Columns=128')
zlabel('Coefficients')
title('Diagonal Level-1')
95
figure
image([cod_ca1,cod_ch1;cod_cv1,cod_cd1]);
title('First level decomposition')
figure
% Perform second step decomposition :
% decompose approx. cfs of level 1.
[ca2,ch2,cv2,cd2] = dwt2(ca1,'db1');
[rough_param]=calculate_roughness_L2A(ca2);
L2=rough_param;
figure
[rough_param]=calculate_roughness_L2H(ch2);
L2=[L2 rough_param];
figure
[rough_param]=calculate_roughness_L2V(cv2);
L2=[L2 rough_param];
figure
[rough_param]=calculate_roughness_L2D(cd2);
L2=[L2 rough_param];
[A2]=feature_extraction_wavelet(ca2,ch2,cv2,cd2)
cod_ca2 = wcodemat(ca2,nbcol);
surf(cod_ca2)
ylabel('Rows=64')
xlabel('Columns=64')
zlabel('Coefficients')
title('Approximation Level-2')
figure
cod_ch2 = wcodemat(ch2,nbcol);
surf(cod_ch2)
ylabel('Rows=64')
96
xlabel('Columns=64')
zlabel('Coefficients')
title('Horizontal Level-2')
figure
cod_cv2 = wcodemat(cv2,nbcol);
surf(cod_cv2)
ylabel('Rows=64')
xlabel('Columns=64')
zlabel('Coefficients')
title('Vertical Level-2')
figure
cod_cd2 = wcodemat(cd2,nbcol);
surf(cod_cd2)
ylabel('Rows=64')
xlabel('Columns=64')
zlabel('Coefficients')
title('Diagonal Level-2')
figure
image([[cod_ca2,cod_ch2;cod_cv2,cod_cd2],cod_ch1;cod_cv1,cod_cd1]);
title('Second level decomposition')
close all
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%
%third level decomposition
figure
[ca3,ch3,cv3,cd3] = dwt2(ca2,'db1');
[rough_param]=calculate_roughness_L3A(ca3);
L3=rough_param;
figure
97
[rough_param]=calculate_roughness_L3H(ch3);
L3=[L3 rough_param];
figure
[rough_param]=calculate_roughness_L3V(cv3);
L3=[L3 rough_param];
figure
[rough_param]=calculate_roughness_L3D(cd3);
L3=[L3 rough_param];
[A3]=feature_extraction_wavelet(ca3,ch3,cv3,cd3)
cod_ca3 = wcodemat(ca3,nbcol);
surf(cod_ca3)
ylabel('Rows=32')
xlabel('Columns=32')
zlabel('Coefficients')
title('Approximation Level-3')
figure
cod_ch3 = wcodemat(ch3,nbcol);
surf(cod_ch3)
ylabel('Rows=32')
xlabel('Columns=32')
zlabel('Coefficients')
title('Horizontal Level-3')
figure
cod_cv3 = wcodemat(cv3,nbcol);
surf(cod_cv3)
ylabel('Rows=32')
xlabel('Columns=32')
zlabel('Coefficients')
title('Vertical Level-3')
98
figure
cod_cd3 = wcodemat(cd3,nbcol);
surf(cod_cd3)
ylabel('Rows=32')
xlabel('Columns=32')
zlabel('Coefficients')
title('Diagonal Level-3')
figure
image([[[cod_ca3,cod_ch3;cod_cv3,cod_cd3],cod_ch2;cod_cv2,cod_cd2],co
d_ch1;cod_cv1,cod_cd1]);
title('Third level decomposition')
close all
figure
[ca4,ch4,cv4,cd4] = dwt2(ca3,'db1');
[rough_param]=calculate_roughness_L4A(ca4);
L4=rough_param;
figure
[rough_param]=calculate_roughness_L4H(ch4);
L4=[L4 rough_param];
figure
[rough_param]=calculate_roughness_L4V(cv4);
L4=[L4 rough_param];
figure
[rough_param]=calculate_roughness_L4D(cd4);
L4=[L4 rough_param];
[A4]=feature_extraction_wavelet(ca4,ch4,cv4,cd4)
cod_ca4 = wcodemat(ca4,nbcol);
surf(cod_ca4)
ylabel('Rows=16')
99
xlabel('Columns=16')
zlabel('Coefficients')
title('Approximation Level-4')
figure
cod_ch4 = wcodemat(ch4,nbcol);
surf(cod_ch4)
ylabel('Rows=16')
xlabel('Columns=16')
zlabel('Coefficients')
title('Horizontal Level-4')
figure
cod_cv4 = wcodemat(cv4,nbcol);
surf(cod_cv4)
ylabel('Rows=16')
xlabel('Columns=16')
zlabel('Coefficients')
title('Vertical Level-4')
figure
cod_cd4 = wcodemat(cd4,nbcol);
surf(cod_cd4)
ylabel('Rows=16')
xlabel('Columns=16')
zlabel('Coefficients')
title('Diagonal Level-4')
figure
image([[[[cod_ca4,cod_ch4;cod_cv4,cod_cd4],cod_ch3;cod_cv3,cod_cd3],c
od_ch2;cod_cv2,cod_cd2],cod_ch1;cod_cv1,cod_cd1]);
title('Fourth level decomposition')
close all
100
figure
[ca5,ch5,cv5,cd5] = dwt2(ca4,'db1');
[rough_param]=calculate_roughness_L5A(ca5);
L5=rough_param;
figure
[rough_param]=calculate_roughness_L5H(ch5);
L5=[L5 rough_param];
figure
[rough_param]=calculate_roughness_L5V(cv5);
L5=[L5 rough_param];
figure
[rough_param]=calculate_roughness_L5D(cd5);
L5=[L5 rough_param];
[A5]=feature_extraction_wavelet(ca5,ch5,cv5,cd5)
savecoeffi_ A1 A2 A3 A4 A5
save A1.txt A1 -ascii
save A2.txt A2 -ascii
save A3.txt A3 -ascii
save A4.txt A4 -ascii
save A5.txt A5 -ascii
cod_ca5 = wcodemat(ca5,nbcol);
surf(cod_ca5)
ylabel('Rows=8')
xlabel('Columns=8')
zlabel('Coefficients')
title('Approximation Level-5')
figure
cod_ch5 = wcodemat(ch5,nbcol);
surf(cod_ch5)
101
ylabel('Rows=8')
xlabel('Columns=8')
zlabel('Coefficients')
title('Horizontal Level-5')
figure
cod_cv5 = wcodemat(cv5,nbcol);
surf(cod_cv5)
ylabel('Rows=8')
xlabel('Columns=8')
zlabel('Coefficients')
title('Vertical Level-5')
figure
cod_cd5 = wcodemat(cd5,nbcol);
surf(cod_cd5)
ylabel('Rows=8')
xlabel('Columns=8')
zlabel('Coefficients')
title('Diagonal Level-5')
figure
image([[[[[cod_ca5,cod_ch5;cod_cv5,cod_cd5],cod_ch4;cod_cv4,cod_cd4],
cod_ch3;cod_cv3,cod_cd3],cod_ch2;cod_cv2,cod_cd2],cod_ch1;cod_cv1,co
d_cd1]);
title('Fifth level decomposition')
close all
% storing patterns
figure
Max_min_ca=[A1(3:4,:) A2(3:4,:) A3(3:4,:) A4(3:4,:)];
plot (Max_min_ca(1,:),'-r')
hold on
102
plot (Max_min_ca(2,:),'-g')
legend('Maximum','Minimum')
Title('Approximation at all five levels of decomposition')
ylabel('Coefficients')
xlabel('Levels 1-5')
figure
Max_min_ch=[A1(7:8,:) A2(7:8,:) A3(7:8,:) A4(7:8,:)];
plot (Max_min_ch(1,:),'-r')
hold on
plot (Max_min_ch(2,:),'-g')
legend('Maximum','Minimum')
Title('Horizontal at all five levels of decomposition')
ylabel('Coefficients')
xlabel('Levels 1-5')
figure
Max_min_cv=[A1(11:12,:) A2(11:12,:) A3(11:12,:) A4(11:12,:)];
plot (Max_min_cv(1,:),'-r')
hold on
plot (Max_min_cv(2,:),'-g')
legend('Maximum','Minimum')
Title('Vertical at all five levels of decomposition')
ylabel('Coefficients')
xlabel('Levels 1-5')
figure
Max_min_cd=[A1(15:16,:) A2(15:16,:) A3(15:16,:) A4(15:16,:)];
plot (Max_min_cd(1,:),'-r')
hold on
plot (Max_min_cd(2,:),'-g')
legend('Maximum','Minimum')
103
Title('Diagonal at all five levels of decomposition')
ylabel('Coefficients')
xlabel('Levels 1-5')
save features Max_min_ca
104
function [A]=feature_extraction_wavelet(ca,ch,cv,cd)
A1=mean(ca);%mean Approximation
A2=std(ca);%std
% A3=norm(ca);%norm
A4=max(ca); %maximum
A5=min(ca);%minimum
A6=mean(ch);%mean Detail
A7=std(ch);%std
% A8=norm(ch);%norm
A9=max(ch); %maximum
A10=min(ch);%minimum
A11=mean(cv);%mean Detail
A12=std(cv);%std
% A13=norm(cv);%norm
A14=max(cv); %maximum
A15=min(cv);%minimum
A16=mean(ch);%mean Detail
A17=std(cd);%std
% A18=norm(cd);%norm
A19=max(cd); %maximum
A20=min(cd);%minimum
Aone=[A1;A2;A4;A5];
Atwo=[A6;A7;A9;A10];
Athree=[A11;A12;A14;A15];
Afour=[A16;A17;A19;A20];
A=[Aone;Atwo;Athree;Afour];
105
function [rough_param]=calculate_roughness_L1A(images)
[a,b,c]=size(images);
PSF = fspecial('gaussian',100,20);%answer(1),answer(2));
i=1;
waviness(:,:,i) = imfilter(images(:,:,i),PSF,'conv');
roughness(:,:,i)=images(:,:,i)-waviness(:,:,i);
n=a*b;
fori=1:c
vectorR(:,i)=reshape(roughness(:,:,i), [1,n]);
vectorW(:,i)=reshape(waviness(:,:,i), [1,n]);
RaR(i)=sum(sum(abs(roughness(:,:,i))))/n; %average roughness
RqR(i)=sqrt(mean(vectorR(:,i).^2)); %RMS roughness
RskR(i)=sum(sum(roughness(:,:,i).^3))/(n*RqR(i)^3); %skewness
RkuR(i)=sum(sum(roughness(:,:,i).^4))/(n*RqR(i)^4); % kurtosis
RaW(i)=sum(sum(abs(waviness(:,:,i))))/n; %average roughness
RqW(i)=sqrt(mean(vectorW(:,i).^2)); %RMS roughness
RskW(i)=sum(sum(waviness(:,:,i).^3))/(n*RqW(i)^3); %skewness
RkuW(i)=sum(sum(waviness(:,:,i).^4))/(n*RqW(i)^4); % kurtosis
end
rough_param(:,1)=RaR;
rough_param(:,2)=RqR;
rough_param(:,3)=RskR;
rough_param(:,4)=RkuR;
rough_param(:,5)=RaW;
rough_param(:,6)=RqW;
rough_param(:,7)=RskW;
rough_param(:,8)=RkuW;
saveall_datarough_param roughness waviness images
106
loadall_data
figure
imagesc(waviness(:,:,1)), colormap(gray)
title ('Waviness Level-1, Approximation')
figure
imagesc(roughness(:,:,1)), colormap(gray)
title('Roughness Level-1 Approximation')
figure
plot(mean(waviness(:,:,1)),'-r')
hold on
plot(mean(roughness(:,:,1)),'g')
legend('Roughness','Waviness')
title(' Level-1 Approximation')