presentation in aircraft satellite image identification using bayesian decision theory and moment...
TRANSCRIPT
![Page 1: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/1.jpg)
Presentation in Aircraft Satellite Image Identification Using Bayesian
Decision Theory And Moment Invariants Feature Extraction
Dickson Gichaga Wambaa
Supervised By Professor Elijah MwangiUniversity Of Nairobi
Electrical And Information Engineering Dept.
• 9th May 2012 IEK Presentation
![Page 2: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/2.jpg)
OUTLINE
Introduction
Statistical Classification
Satellite images Denoising
Results
Conclusion
References
![Page 3: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/3.jpg)
All aircraft are built with the same basic elements: Wings Engine(s) Fuselage Mechanical Controls Tail assembly. The differences of these elements distinguish one aircraft type from another and therefore its identification.
![Page 4: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/4.jpg)
STAGES OF STATISTICAL PATTERN RECOGNITION
• PROBLEM FORMULATION• DATA COLLECTION
AND EXAMINATION• FEATURE
SELECTION OR EXTRACTION
• CLUSTERING• DISCRIMINATION• ASSESSMENT OF
RESULTS• INTERPRETATION
![Page 5: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/5.jpg)
Classification ONE
• There are two main divisions of classification: • Supervised•unsupervised
![Page 6: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/6.jpg)
SUPERVISED CLASSIFICATION
• BAYES CLASSIFICATION IS SELECTED SINCE IT IS POSSIBLE TO HAVE EXTREMELY HIGH VALUES IN ITS OPTIMISATION.
![Page 7: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/7.jpg)
A decision rule partitions the measurement space into C regions.
![Page 8: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/8.jpg)
Preprocessing
![Page 9: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/9.jpg)
PREPROCESSING
IMAGE ACQUISITION
IMAGE ENHANCEMENT
IMAGE BINARIZATION
AND THRESHOLDING
FEATURES EXTRACTION
![Page 10: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/10.jpg)
NOISEIMAGES ARE CONTAMINATED BY
NOISE THROUGH– IMPERFECT INSTRUMENTS– PROBLEMS WITH DATA ACQUISITION PROCESS– NATURAL PHENOMENA INTERFERENCE– TRANSMISSION ERRORS
![Page 11: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/11.jpg)
SPECKLE NOISE(SPKN)
• THE TYPE OF NOISE FOUND IN SATELLITE IMAGES IS SPECKLE NOISE AND THIS DETERMINES THE ALGORITHM USED IN DENOISING.
![Page 12: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/12.jpg)
Speckle Noise (SPKN) 2
• This is a multiplicative noise. The distribution noise can be expressed by:
J = I + n*I • Where, J is the distribution speckle
noise image, I is the input image and n is the uniform noise image.
![Page 13: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/13.jpg)
CHOICE OF FILTER
FILTERING CONSISTS OF MOVING A WINDOW OVER EACH PIXEL OF AN IMAGE AND TO APPLY A MATHEMATICAL FUNCTION TO ACHIEVE A SMOOTHING EFFECT.
![Page 14: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/14.jpg)
CHOICE OF FILTER II
• THE MATHEMATICAL FUNCTION DETERMINES THE FILTER TYPE.• MEAN FILTER-AVERAGES THE
WINDOW PIXELS• MEDIAN FILTER-CALCULATES THE
MEDIAN PIXEL
![Page 15: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/15.jpg)
CHOICE OF FILTER II
• LEE-SIGMA AND LEE FILTERS-USE STATISTICAL DISTRIBUTION OF PIXELS IN THE WINDOW
• LOCAL REGION FILTER-COMPARES THE VARIANCES OF WINDOW REGIONS.
• THE FROST FILTER REPLACES THE PIXEL OF INTEREST WITH A WEIGHTED SUM OF THE VALUES WITHIN THE NxN MOVING WINDOW AND ASSUMES A MULTIPLICATIVE NOISE AND STATIONARY NOISE STATISTICS.
![Page 16: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/16.jpg)
LEE FILTER
Adaptive Lee filter converts the multiplicative model into an additive one.
It preserves edges and detail.
![Page 17: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/17.jpg)
BINARIZATION AND THRESHOLDING
![Page 18: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/18.jpg)
TRAINING DATA SET
AH64 C5 B2
![Page 19: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/19.jpg)
RESULTS: FEATURE EXTRACTION ORIGINAL IMAGES
AircraftsClasses
Ø1 Ø2 Ø3 Ø4 Ø5 Ø6 Ø7
B2(Class 1)
6.6132 14.0538 15.2462 17.4521 33.9469 24.6798 39.2648
AH64(Class 2)
7.1729 16.6723 19.7413 21.8784 42.8038 30.2146 47.1336
C5(Class3)
7.1487 20.2793 22.4129 24.4962 48.0614 34.6401 50.1980
![Page 20: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/20.jpg)
NOISE ADDITION
•Noise with Probabilities of 0.1, 0.2, 0.3 and 0.4 was used for simulation.
![Page 21: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/21.jpg)
FEATURE EXTRACTION:SAMPLE IMAGES
Ø1 Ø2 Ø3 Ø4 Ø5 Ø6 Ø7
B2 Class 1 6.6132 14.0538 15.2462 17.4521 33.9469 24.6798 39.2648
Test Image NOISE FILTERED
6.6001 13.9810 15.1678 17.4434 33.8456 24.6578 40.9765
Test Image ( 0.1 Noise Prob)
6.5579 13.9115 15.0382 17.2442 33.5329 24.4031 41.0169
Test Image (0.2 Noise Prob)
6.5406 13.8898 14.9673 17.1737 33.3923 24.3223 38.6145
Test Image (0.3 Noise Prob)
6.4703 13.7136 14.6351 16.8403 32.7292 23.9045 38.4642
Test Image (0.4 Noise Prob)
6.4124 13.5763 14.2593 16.4614 31.9765 23.4609 36.7216
![Page 22: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/22.jpg)
WHY BAYES CLASSIFICATION 1
Bayes statistical method is the classification of choice because of its minimum error rate.
![Page 23: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/23.jpg)
WHY BAYES CLASSIFICATION 2
• Probabilistic learning: among the most practical approaches to certain types of learning problems• Incremental: Each training example can
incrementally increase/decrease the probability that a hypothesis is correct
![Page 24: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/24.jpg)
WHY BAYES CLASSIFICATION 3
•Probabilistic prediction: Predict multiple hypotheses•Benchmark: Provide a
benchmark for other algorithms
![Page 25: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/25.jpg)
Bayesian Classification
• For a minimum error rate classifier the choice is on the class with maximum posterior probability.
![Page 26: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/26.jpg)
Probabilities
• Let λ be set of 3 classes C1,C2 ,C3.• x be an unknown feature vector of
dimension 7.• Calculate the conditional posterior
probabilities of every class Ci and choose the class with maximum posteriori probability.
![Page 27: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/27.jpg)
Prior Probabilities
• 3 classes of Data which are all likely to happen therefore
P(Ci)= 0.333
![Page 28: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/28.jpg)
Posterior Probability 1
• Posterior = likelihood x prior evidence
• P(Ci\x) = P(x\Ci)P(Ci)
P(x)
![Page 29: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/29.jpg)
POSTERIOR PROBABILITY 2
• Posterior(AH 64)=P(AH 64)P(x/ AH 64) p(evidence)
• Posterior(C5)=P(C5)P(x/ C5) p(evidence)• Posterior(B2)=P(B2)P(x/ B2) p(evidence)
![Page 30: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/30.jpg)
POSTERIOR PROBABILITY 3
Posteriorprobability
Test Image NOISE FILTERED
Test Image ( 0.1 Noise Prob)
Test Image ( 0.2 Noise Prob)
Test Image ( 0.3 Noise Prob)
Test Image ( 0.4 Noise Prob)
AH 64 1.6954X10-2 1.6789X10-2 1.6034X10-2 1.5674X10-2 1.5045X10-2
C5 1.9653X10-2 1.8965X10-2 1.8463X10-2 1.8062X10-2 1.7453X10-2
B2 2.4239X10-2 2.2346X10-2 2.21567X10-2 2.1866X10-2 1.9889X10-2
![Page 31: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/31.jpg)
CONCLUSION
• COMBINING MOMENTS FEATURES EXTRACTION WITH BAYESIAN CLASSIFICATION WHILE USING LEE FILTERS IN PREPROCESSING
• INCREASES THE CHANCES OF CORRECT IDENTIFICATION AS COMPARED TO NON USE OF THE FILTERS
• USE OF OTHER TYPES OF FILTERS THIS IS SEEN BY THE INCREASE OF THE POSTERIOR PROBABILITY VALUES.
![Page 32: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/32.jpg)
References
• [1] Richard O. Duda,Peter E. Hart and David G. Stork.Pattern Classification 2nd edition John Wiley and Sons,US,2007
• [2] Rafael C. Gonzalez,Richard E. Woods and Steven L. Eddins . Digital image processing using matlab 2nd edition Pearson/Prentice Hall,US,2004
• [3] William K. Pratt. Digital image processing 4th edition John Wiley,US,2007• [4] Anil K. Jain. Fundamentals of Digital Image
Processing Prentice Hall,US,1989
![Page 33: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/33.jpg)
References
• [5] Wei Cao, Shaoliang Meng, “Imaging systems and Techniques”,IEEE International Workshop,
IST.2009.5071625,pp 164-167, Shenzhen, 2009• [6] Bouguila.N, Elguebaly.T , “A Bayesian approach
for texture images classification and retrieval”,International Conference on Multimedia Computing and Systems, ICMS.2011.5945719,pp 1-6,Canada, 2011
![Page 34: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/34.jpg)
References
• [7] Dixit. M, Rasiwasia. N, Vasconcelos. N, “Adapted Gaussian models for image classification” ,2011 IEEE Conference on Computer Vision and Pattern, CVPR.2011.5995674, pp 937-943, USA,2011
• [8] Mukesh C. Motwani,Mukesh C. Gadiya,Rakhi C. Motwani, Frederick C. Harris Jr. , “Survey Of Image Denoising Techniques”,University of Nevada Reno, US, 2001
![Page 35: Presentation in Aircraft Satellite Image Identification Using Bayesian Decision Theory And Moment Invariants Feature Extraction Dickson Gichaga Wambaa](https://reader030.vdocuments.us/reader030/viewer/2022032701/56649c7b5503460f9492fa1c/html5/thumbnails/35.jpg)