Processing math: 100%

1. Derivative Based Algorithms:

  • Thresholded absolute gradient: f=xy|I(x+1,y)I(x,y)|  where   |I(x+1,y)I(x,y)|>threshold;
  • Squared gradient: f=xy(I(x+1,y)I(x,y))2 where (I(x+1,y)I(x,y))2>threshold;
  • Brenner gradient: f=xy(I(x+2,y)I(x,y))2 where (I(x+2,y)I(x,y))2>threshold;
  • Tenenbaum gradient: f=xy(SobelX2(x,y)+SobelY2(x,y));
  • Energy Laplace: f=xy((LI)(x,y))2  where L=[1414204141] 
  • Sum of modified Laplace: f=xy(LaplaceX(x,y)|+|LaplaceY(x,y)|)
  • Sum of squared Gaussian derivatives f=1total pixelsxy((Gaussian derivative X(x,y))2+(Gaussian derivative Y(x,y))2) where σ=d/(23), d = dimension of the smallest feature;

 

2. Statistical Algorithms:

  •  Variance Measure ; f=1total pixelsxy(I(x,y)I)2; where I is the mean of image.
  • Normalized Variance Measure ; f=1total pixels×Ixy(I(x,y)I)2;
  • Auto-correlation Measure: f=xyI(x,y)I(x+1,y)xyI(x,y)I(x+2,y);
  • Standard Deviation-based Correlation: f=xyI(x,y)I(x+1,y)I2(x,y)×total pixels;

3. Histogram-based Algorithms:

  • Range Algorithm: f=max{i|histogram(i)>0}min{i|histogram(i)>0};
  • Entropy Algorithm: f=255i=0p(i)log2p(i) where p(i)=histogram(i)/total pixels;

4. Other Algorithms:

  • Threshold Contents: f=xyI(x,y) where I(x,y)threshold;
  • Thresholded Pixel Count: f=xyθ(thresholdI(x,y)); where θ(x) is the step-function.
  • Image Power: f=xyI2(x,y) where I(x,y)threshold;

Ref: Dynamic evaluation of autofocusing for automated microscopic analysis of blood smear and pap smear, J. Microscopy,227, 15(2007).                           

 

728x90

'Image Recognition' 카테고리의 다른 글

Union-Find Connected Component Labeling  (0) 2012.11.01
RANSAC: Ellipse Fitting  (1) 2012.10.07
Statistical Region Merging  (2) 2012.03.25
Local Histogram Equalization  (0) 2012.03.10
2차원 Savitzky-Golay Filters 응용  (0) 2012.02.28
,