EE640 SPRING 2012

GL3Dview will allow you to view, rotate, zoom and crop the mat5 data. Use load to select the “C.bmp” file and it will load the associated mat5. Use the “Left Mouse Button” to crop by selecting the “Select” button, click drag a box around what you want, then click the “Apply” button to crop.

http://www.engr.uky.edu/~lgh/soft/GL3DView.exe

Tutorial for GL3DViewer.avi

PROJECT 1A:

PART A: SYNTHESIS (EE640_Project_1A09.pdf)

Target Data: Target.zip

Clutter Data: Clutter.zip

PROJECT 1B:

PART B: ANALYSIS (EE640_Project1_B09.pdf)

PROJECT 1C:

PART C: DETECTION AND DISCRIMINATION (EE640_Project1_C09.pdf)

Journal References for project 1

(NOT READY FOR 2010) PROJECT 1S: Supplemental

PART S: Supplemental:EE640_Project_1S.pdf

Old stuff

Stationary Colored Noise

Non-Stationary Colored Noise

VISUALIZAIONS (not updated from 2005 yet)

Example of Stationary Colored Noise versus a non-stationary image, both having same PSD

Data Whitening and the Covariance Matrix

LECTURE NOTES

Lecture 1: Historical Perspective and Overview of Probability and Stochastic Processes

Lecture 2: Set Theory and Probability

Lecture 3: Combinatorics

Lecture 4: Random Variables

Lecture 5: Expected Values

Lecture 5X: Non-biased variance estimate

Lecture 6: Characteristic Function and Moment Generating Function

Lecture 7: Random Vectors, Covariance Matrix and Correlation Matrix

Lecture 8: Bi-variate Gaussian r.v and Correlation Coefficient.

Lecture 9: Functions of Random Variables

Lecture 9A: Auxiliary Variable

Lecture 10: Central Limit Theorem

Lecture 11: Bounds and Convergence

Lecture 12: RANDOM PROCESSES

Lecture 13: R.P.: TYPES OF STATIONARITY

Lecture 13 Example: Quantization Noise Model

Lecture 14: R.P.: POWER SPECTRAL DENSITY, AUTOCORRELATION AND MEAN SQARE CALCULAS

Lecture 15: LINEAR TIME-INVARIANT STOCHASTIC SYSTEMS

Lecture 16: STOCHASTIC SERIES EXPANSION

Lecture 17:DETECTION AND DISCRIMINATION

Lecture 18: OPTIMUM DECISION BOUNDARIES

Lecture 19: TYPES OF DECISION BOUNDARIES

Lecture 20: MULTI-VARIANT MLR

Lecture 21: QUADRATURE MODULATION AND DEMODULATION

Lecture 22: SIGNAL SPACE DECISION BOUNDARIES

Lecture 23: OPTIMUM DETECTION FILTER BANKS

Lecture 24: DETECTION FILTER PERFORMANCE MEASURES

Lecture 25: ESTIMATION OF PROBABILITY DENSITY FUNCTION

Lecture 26: ESTIMATION, MINIMUM MEAN SQUARED ERROR

Lecture 27: ESTIMATION, MAXIMUM LIKELIHOOD

Lecture 28: STOCHASTIC FILTER PREDICTORS (WIENER FILTER)

Lecture 29: MINIMUM AVERAGE CORRELATION ENERGY FILTER DERIVATION

OTHER REFERENCES:

1. For Project 1C: Encryption of image data into host image: K. T. Lin, “Information hiding based on binary encoding methods and pixel scrambling techniques,” Applied Optics, Vol 49, No. 2, pp 220-228, January (2010).

2. B.V.K. Vijaya Kumar and L. G. Hassebrook, "Performance Measures for Correlation Filters," Applied Optics, 29, 2997-3006, (July 1990).

HOW TO INPUT BMP INTO MATLAB

B_bmp=double(imread('example.bmp')); % load example.bmp image

Br=B_bmp(:,:,1);

Bg=B_bmp(:,:,2);

Bb=B_bmp(:,:,3);

Bbw=(Br+Bg+Bb)/3;