Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical...

20
Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University
  • date post

    21-Dec-2015
  • Category

    Documents

  • view

    222
  • download

    0

Transcript of Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical...

Page 1: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

Elements of Biomedical Image ProcessingBMI 731 Winter 2005

Kun HuangDepartment of Biomedical Informatics

Ohio State University

Page 2: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

- Introduction to imaging processing- Mathematical background

- Convolution and Fourier transform- Filtering

- Image enhancement- Noise removal- Color correction and color space transform

- Feature extraction- Edge, point, line (Hugh transform)

- 3-D reconstruction - Radon transform

Page 3: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

- Image Processing : what should be done?- Image restoration and enhancement- Feature extraction- Pattern recognition

Page 4: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

- Mathematical Background- Convolution

- 2-D convolution

17 241 8 15

23 57 14 16

4 613 20 22

10 12 19 21 3

11 18 25 2 9

2 9 4

7 5 3

6 1 8

1x2+8x9+15x4+7x7+14x5+16x3+13x6+20x1+22x8=575

Page 5: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

- Mathematical Background- Fourier transform (FT)

- Mathematics

- 2-D FT

Page 6: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

- Mathematical Background- Fourier transform (FT)

- Fast FT (FFT)

Page 7: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

- Mathematical Background- Convolution and Fourier transform (FT)

Page 8: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

- Mathematical Background- Filtering

- High-pass filter, low-pass filter, band pass filter

- Gradient filters

1 1 -1 -1

1 1 -1 -1

1 1 -1 -1

1 1 -1 -1

-1 -1 -1 -1

-1 -1 -1 -1

1 1 1 1

1 1 1 1

Page 9: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

- Mathematical Background- Filtering

- Wiener filter and deblurring

Page 10: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

- Image Enhancement- Denoise

- Averaging

- Median filter

1/9 1/9 1/9

1/9 1/9 1/9

1/9 1/9 1/9

20 5 43

78 3 22

115 189 200

43

Page 11: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

- Image Enhancement- Denoise/restoration

From Gonzalez, Woods, and Eddins

Page 12: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

- Image Enhancement- Color and intensity adjustment

- Histogram equalization

Page 13: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

- Image Enhancement- Color space transform

RGB -> HSV, HSL, YCbCr, …

R = 64G = 31B = 62

R = 125G = 80B = 147

H = 199S = 117V = 147

H = 214S = 132V = 64

Page 14: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

- Feature Extraction- Region detection – morphology manipulation

- Dilate and Erode

- Open- Erode dilate - Small objects are removed

- Close- Dilate Erode - Holes are closed

- Skeleton and perimeter

Page 15: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

- Feature Extraction- Edge detection

- Gradients

- Canny edge detector- Gaussian smoothing- Gradients- Two thresholds- Thinning

1 1 -1 -1

1 1 -1 -1

1 1 -1 -1

1 1 -1 -1

-1 -1 -1 -1

-1 -1 -1 -1

1 1 1 1

1 1 1 1

Page 16: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

- Feature Extraction- Point detection

- Harris detector

x

Page 17: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

- Feature Extraction- Radon transform

- Straight line detection- Hugh transform

y

y

Page 18: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

- Feature Extraction- Straight line detection

- Hugh transform

From Gonzalez, Woods, and Eddins

Page 19: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

- 2-D/3-D reconstruction- Radon/inverse radon transforms and

backprojection

Page 20: Elements of Biomedical Image Processing BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.

- Reference- Digital Image Processing using Matlab

By R.C.Gonzalez, R.E.Woods, and S.L.EddinsPublished by Printice-Hall, 2004