Math 3360 Mathematical Imaging Lecture 10 Types of
- Slides: 15
Math 3360: Mathematical Imaging Lecture 10: Types of noises Prof. Ronald Lok Ming Lui Department of Mathematics, The Chinese University of Hong Kong
Image Enhancement n Linear filtering: n n Modifying a pixel value (in the spatial domain) by a linear combination of neighborhood values. Operations in spatial domain v. s. operations in frequency domains: n n Linear filtering (matrix multiplication in spatial domain) = discrete convolution In the frequency domain, it is equivalent to multiplying the Fourier transform of the image with a certain function that “kills” or modifies certain frequency components
Spatial transform v. s. frequency transform Discrete convolution: n (Matrix multiplication, which define output value as linear combination of its neighborhood) n n n DFT of Discrete convolution: Product of fourier transform DFT(convolution of f and w) = C*DFT(f)*DFT(w) Multiplying the Fourier transform of the image with a certain function that “kills” or modifies certain frequency components
Spatial transform v. s. frequency transform
Spatial transform v. s. frequency transform
Image components n LP = Low Pass; HP = High Pass
Image components
Type of noises n Preliminary statistical knowledge: n n n Random variables; Random field; Probability density function; Expected value/Standard deviation; Joint Probability density function; Linear independence; Uncorrelated; Covariance; Autocorrelation; Cross-correlation; Cross covariance; Noise as random field etc… Please refer to Supplemental note 6 for details.
Type of noises n Impulse noise: n n Change value of an image pixel at random; The randomness follows the Poisson distribution = Probability of having pixels affected by the noise in a window of certain size Poisson distribution: Gaussian noise: n Noise at each pixel follows the Gaussian probability density function:
Type of noises n Additive noise: n n Multiplicative noise: n n Noise parameter for the probability density function at each pixel are the same (same mean and same standard derivation) Zero-mean noise: n n Noisy image = original (clean) image * noise Homogenous noise: n n Noisy image = original (clean) image + noise Mean at each pixel = 0 Biased noise: n Mean at some pixels are not zero
Type of noises n Independent noise: n n Uncorrected noise: n n n Let Xi = noise at pixel i (as random variable); E(Xi Xj) = E(Xi) E(Xj) for all i and j. White noise: n n The noise at each pixel (as random variables) are linearly independent Zero mean + Uncorrelated + additive idd noise: n n n Independent + identically distributed; Noise component at every pixel follows the SAME probability density function (identically distributed) For Gaussian distribution,
Gaussian noise n Example of Gaussian noises:
White noise n Example of white noises:
Image components
Noises as high frequency component Why noises are often considered as high frequency component? (a) Clean image spectrum and Noise spectrum (Noise dominates the high-frequency component); (b) Filtering of high-frequency component
- Math3360
- "green imaging" -g -"green imaging technologies"
- Cis tcp fin services
- Ucf cis 3360
- Cis 3360
- Cis 3360
- Non mathematical economics
- 01:640:244 lecture notes - lecture 15: plat, idah, farad
- Maps and plans maths lit grade 12
- Maps, plans and other representations of the physical world
- Types of scales maths lit
- Types of mathematical models
- Hit the button
- L'objectif de la lecture
- Preapared
- Ishellextinit