Presentation is loading. Please wait.

Presentation is loading. Please wait.

Image Transforms 主講人:虞台文. Content Overview Convolution Edge Detection – Gradients – Sobel operator – Canny edge detector – Laplacian Hough Transforms.

Similar presentations


Presentation on theme: "Image Transforms 主講人:虞台文. Content Overview Convolution Edge Detection – Gradients – Sobel operator – Canny edge detector – Laplacian Hough Transforms."— Presentation transcript:

1 Image Transforms 主講人:虞台文

2 Content Overview Convolution Edge Detection – Gradients – Sobel operator – Canny edge detector – Laplacian Hough Transforms Geometric Transforms – Affine Transform – Perspective Transform Histogram Equalization

3 Image Transforms Overview

4 Image Transform Concept T[]

5 Image Transform Concept T[]

6 Image Transforms Convolution

7 Image Convolution g(x,y) is known as convolution kernel.

8 Image Convolution g(x,y) is known as convolution kernel. height 2h + 1 width 2w + 1

9 Image Convolution g(x,y) is known as convolution kernel. height 2h + 1 width 2w + 1

10 Some Convolution Kernels

11 OpenCV Implementation  Image Filter void cvFilter2D( const CvArr* src, CvArr* dst, const CvMat* kernel, CvPoint anchor=cvPoint(-1, -1) ); void cvFilter2D( const CvArr* src, CvArr* dst, const CvMat* kernel, CvPoint anchor=cvPoint(-1, -1) );

12 Deal with Convolution Boundaries void cvCopyMakeBorder( const CvArr* src, CvArr* dst, CvPoint offset, int bordertype, CvScalar value=cvScalarAll(0) ); void cvCopyMakeBorder( const CvArr* src, CvArr* dst, CvPoint offset, int bordertype, CvScalar value=cvScalarAll(0) );

13 Image Transforms Edge Detection

14 Convert a 2D image into a set of curves – Extracts salient features of the scene – More compact than pixels

15 Origin of Edges depth discontinuity surface color discontinuity illumination discontinuity surface normal discontinuity Edges are caused by a variety of factors

16 Edge Detection How can you tell that a pixel is on an edge?

17 Edge Types Step Edges Roof Edge Line Edges

18 Real Edges Noisy and Discrete! x I We want an Edge Operator that produces: – Edge Magnitude – Edge Orientation – High Detection Rate and Good Localization

19 Derivatives of Image in 1D Edges can be characterized as either: – local extrema of  I(x) – zero-crossings of  2 I(x)  1D image  gradient  Laplacian

20 2D-Image Gradient

21 Gives the direction of most rapid change in intensity Gradient direction: Edge strength:

22 Classification of Points To precisely locate the edge, we need to thin. Ideally, edges should be only one point thick. T Non-zero edge width

23 The Sobel Operators 01 -202 01 121 000 -2 Sobel (3 x 3): Sobel (5 x 5): -2021 -3032 -5053 -2-3032 -2021 12321 23532 00000 -3-5-3-2 -2-3-2 Good Localization Noise Sensitive Poor Detection Poor Localization Less Noise Sensitive Good Detection

24 OpenCV Implementation  The Sobel Operators void cvSobel( const CvArr* src, CvArr* dst, int xorder, int yorder, int aperture_size = 3 ); void cvSobel( const CvArr* src, CvArr* dst, int xorder, int yorder, int aperture_size = 3 );

25 OpenCV Implementation  The Scnarr Operator void cvSobel( const CvArr* src, CvArr* dst, int xorder, int yorder, int aperture_size = 3 ); void cvSobel( const CvArr* src, CvArr* dst, int xorder, int yorder, int aperture_size = 3 ); aperture_size CV_SCHARR

26 Demonstration

27 Exercise Download Test Program Download Test Program

28 Effects of Noise Where is the edge? Consider a single row or column of the image

29 Solution: Smooth First

30 Where is the edge?

31 Derivative Theorem of Convolution Gaussian:

32 Derivative Theorem of Convolution saves us one operation.

33 Optimal Edge Detection: Canny Assume: – Linear filtering – Additive iid Gaussian noise An "optimal" edge detector should have: – Good Detection Filter responds to edge, not noise. – Good Localization detected edge near true edge. – Single Response one per edge.

34 Optimal Edge Detection: Canny Based on the first derivative of a Gaussian Detection/Localization trade-off – More smoothing improves detection – And hurts localization.

35 Stages of the Canny algorithm Noise reduction Size of Gaussian filter Finding the intensity gradient of the image Non-maximum suppression Tracing edges through the image and hysteresis thresholding High threshold Low threshold

36 Parameters of Canny algorithm Noise reduction – Size of Gaussian filter Finding the intensity gradient of the image Non-maximum suppression Tracing edges through the image and hysteresis thresholding – High threshold – Low threshold

37 OpenCV Implementation  The Canny Operator void cvCanny( const CvArr* img, CvArr* edges, double lowThresh, double highThresh, int apertureSize = 3 ); void cvCanny( const CvArr* img, CvArr* edges, double lowThresh, double highThresh, int apertureSize = 3 );

38 Example: Canny Edge Detector Download Test Program Download Test Program

39 Review: Derivatives of Image in 1D Edges can be characterized as either: – l– local extrema of  I(x) – z– zero-crossings of  2 I(x)  1D image  gradient  Laplacian

40 Laplacian A scalar  isotropic. Edge detection: Find all points for which  2 I(x, y) = 0 No thinning is necessary. Tends to produce closed edge contours.

41 Laplacian

42 Discrete Laplacian Operators

43 OpenCV Implementation  The Discrete Laplacian Operators void cvLaplace( const CvArr* src, CvArr* dst, int apertureSize = 3 ); void cvLaplace( const CvArr* src, CvArr* dst, int apertureSize = 3 );

44 Example

45 Laplician for Edge Detection Find zero-crossing on the Laplacian image.

46 Zero Crossing Detection There is a little bug in the above algorithm. Try to design your own zero-crossing detection algorithm.

47 Example: Laplician for Edge Detection Download Test Program Download Test Program

48 Laplacian for Image Sharpening

49 Example: Laplacian for Image Sharpening Sharpened Image

50 Laplacian of Gaussian (LoG) Gaussian:

51 Some LoG Convolution Kernels

52 Example: LoG for Edge Detection by LoG by Laplacian

53 Image Transforms Hough Transforms

54 Goal of Hough Transforms A technique to isolate the curves of a given shape / shapes in a given image Classical Hough Transform – can locate regular curves like straight lines, circles, parabolas, ellipses, etc. Generalized Hough Transform – can be used where a simple analytic description of feature is not possible

55 HT for Line Detection x y m b (m, b) A line in xy-plane is a point in mb-plane.

56 HT for Line Detection x y m b (m 1, b 1 ) (m 2, b 2 ) (m 3, b 3 ) All lines passing through a point in xy-plane is a line in mb-plane. A line in xy-plane is a point in mb-plane.

57 HT for Line Detection x y m b (m 1, b 1 ) (m 2, b 2 ) (m 3, b 3 ) All lines passing through a point in xy-plane is a line in mb-plane. A line in xy-plane is a point in mb-plane. Given a point in xy-plane, we draw a line in mb-plane.

58 HT for Line Detection x y m b A line in xy-plane is a point in mb-plane. A line in xy-plane is then transformed in to a set of lines in mb-plane, which intersect at a common point. Given a point in xy-plane, we draw a line in mb-plane. (m, b)

59 HT for Line Detection x y m b A line in xy-plane is a point in mb-plane. A line in xy-plane is then transformed in to a set of lines in mb-plane, which intersect at a common point. Given a point in xy-plane, we draw a line in mb-plane. (m, b) How to implement? Is mb representation suitable?

60 HT Line Detection by  -representation x y     ( ,  ) A line in xy-plane is a point in  -plane.

61 HT Line Detection by  -representation x y   A line in xy-plane is a point in  -plane. 1 2 3 4 4 3 2 1 All lines passing through a point in xy-plane is a curve in  -plane.

62 HT Line Detection by  -representation x y   A line in xy-plane is a point in  -plane. 1 2 3 4 4 3 2 1 All lines passing through a point in xy-plane is a curve in  -plane. Given a point in xy-plane, we draw a curve in  -plane.

63 HT Line Detection by  -representation x y   A line in xy-plane is a point in  -plane. Given a point in xy-plane, we draw a curve in  -plane. A line in xy-plane is then transformed in to a set of curves in  -plane, which intersect at a common point. ( ,  )

64 HT Line Detection by  -representation A line in xy-plane is a point in  -plane. Given a point in xy-plane, we draw a curve in  -plane. A line in xy-plane is then transformed in to a set of curves in  -plane, which intersect at a common point.

65 OpenCV Implementation  Hough Line Transform CvSeq* cvHoughLines2( CvArr* image, void* line_storage, int method, double rho, double theta, int threshold, double param1 = 0, double param2 = 0 ); CvSeq* cvHoughLines2( CvArr* image, void* line_storage, int method, double rho, double theta, int threshold, double param1 = 0, double param2 = 0 );

66 Example: Hough Line Transform Download Test Program Download Test Program

67 Hough Circle Transform Circle equation: x y r a b image spaceparameter space

68 Hough Circle Transform Circle equation: x y r a b image spaceparameter space Cost ineffective & time consuming

69 Hough Gradient Method Circle equation: x y image space Parametric form:

70 Hough Gradient Method Circle equation: x y image space Parametric form: The value of can be obtained from the edge detection process.

71 Hough Gradient Method Quantize the parameter space for the parameters a and b. Zero the accumulator array M(a, b). Compute the gradient magnitude G(x, y) and angle  (x, y). For each edge (x 0, y 0 ) point in G(x, y), increment all points in the accumulator array M(a, b) along the line Local maxima in the accumulator array correspond to centers of circles in the image. Circle equation: x y image space

72 OpenCV Implementation  Hough Circle Transform CvSeq* cvHoughCircles( CvArr* image, void* circle_storage, int method, double dp, double min_dist, double param1=100, double param2=100 int min_radius=0, int max_radius=0 ); CvSeq* cvHoughCircles( CvArr* image, void* circle_storage, int method, double dp, double min_dist, double param1=100, double param2=100 int min_radius=0, int max_radius=0 );

73 Example: Hough Circle Transform Download Test Program Download Test Program

74 Image Transforms Geometric Transforms

75 Geometric Transforms  Stretch, Shrink, Warp, and Rotate

76 Scaling, Rotation, Translation Scaling Rotation Translation

77 Scaling, Rotation + Translation Scaling Rotation Translation + Translation + Translation

78 Homogeneous Coordinate

79 Scaling, Rotation + Translation Scaling Rotation + Translation + Translation 2  3 matrix

80 Affine Transformation An affine transformation is any transformation that can be expressed in the form of a matrix multiplication followed by a vector addition. – In OpenCV the standard style of representing such a transformation is as a 2-by-3 matrix. 2  3 matrix

81 Affine Transformation

82 GetAffineTransform

83

84 Get 2D Rotation Matrix

85 WarpAffine

86 GetQuadrangleSubPix

87 Example: Affine Transform Download Test Program Download Test Program

88 GetQuadrangleSubPix

89 Sparse Affine Transformation

90 Perspective Transform

91

92

93 Affine Transform vs. Perspective Transform Affine Transform: Perspective Transform:

94 Get Perspective Transform

95 WarpPerspective

96 Sparse Perspective Transformation

97 Image Transforms Histogram Equalization

98 Graylevel Histogram of Image

99 Goal of Histogram Equalization

100 Image Enhancement

101 Method  Graylevel Remapping 0 1 fX(x)fX(x) x 0 1 fY(y)fY(y) y y x X Y

102 Probability Theory y x X Y pdf cdf

103 Example: Gaussian

104

105 Demonstration

106 OpenCV Implementation

107 Example Download Test Program Download Test Program


Download ppt "Image Transforms 主講人:虞台文. Content Overview Convolution Edge Detection – Gradients – Sobel operator – Canny edge detector – Laplacian Hough Transforms."

Similar presentations


Ads by Google