Download presentation
1
Neighborhood Operations
2
Objectives Why are neighborhoods important?
What is linear convolution? discrete templates, masks or filters algorithm mechanics graphical interpretation Describe non-linear operators maximum minimum median What is tiling?
3
Why are neighbourhoods important?
pixel
4
Because… Provide context for individual pixels.
Relationships between neighbors determine image features. Neighborhood operations: noise reduction edge enhancement zooming
5
Noise reduction Edge Enhancement Zooming
6
Neighbourhood Operations
Linear convolution (*) A*B*C*D = B*C*D*A = …. Non-linear operators median, max, min, ...
7
Convolution versus Spectral
We learnt two methods of processing images: Convolution Spectral We analyzed and demonstrated how to build a processor (systolic, pipelined, parallel, cellular automaton) for 1D convolution. 1D convolution is used in speech processing and in polynomial multiplication. We will use visualized animations now to show in more detail how 2D convolution works for images. This should convince you how important it is to do convolution quickly in modern Spectral Architectures, especially for 3D etc.
8
2D Convolution We will show more examples of convolution now, especially for 2D data Consists of filtering an image A using a filter (mask, template) B. Mask is a small image whose pixel values are called weights. Weights modify relationships between pixels.
9
= A C B Filter, mask or template Input image Convolved Image A1,1
2 2 3 3 4 4
10
A1,1 A1,2 A2,1 A2,2 B1,1 B1,2 B2,1 B2,2 A1,3 A1,4 A2,3 A2,4 A3,1 A3,2 A3,3 A3,4 A4,1 A4,2 A4,3 A4,4 A1,1B1,1 A1,2B1,2 A2,1B2,1 A2,2B2,2 C1,1= A1,1B1,1 A1,2B1,2 A2,1B2,1 A2,2B2,2
11
A1,1 A1,2 A2,1 A2,2 A1,3 A1,4 A2,3 A2,4 A3,1 A3,2 A3,3 A3,4 A4,1 A4,2 A4,3 A4,4 B1,1 B1,2 B2,1 B2,2 A1,2B1,1 A1,3B1,2 A2,2B2,1 A2,3B2,2 C1,2= A1,2B1,1 A1,3B1,2 A2,2B2,1 A2,3B2,2
12
A1,1 A1,2 A2,1 A2,2 A1,3 A1,4 A2,3 A2,4 A3,1 A3,2 A3,3 A3,4 A4,1 A4,2 A4,3 A4,4 B1,1 B1,2 B2,1 B2,2 A1,3B1,1 A1,4B1,2 A2,3B2,1 A2,4B2,2 C1,3= A1,3B1,1 A1,4B1,2 A2,3B2,1 A2,4B2,2
13
A1,3 A1,4 A2,3 A2,4 A3,1 A3,2 A3,3 A3,4 A4,1 A4,2 A4,3 A4,4 A1,1 A1,2 A2,1 A2,2 A2,1B1,1 A2,2B1,2 B1,1 B1,2 B2,1 B2,2 A3,1B2,1 A3,2B2,2 C2,1= A2,1B1,1 A2,2B1,2 A3,1B2,1 A3,2B2,2
14
A1,1 A1,2 A2,1 A2,2 A1,3 A1,4 A2,3 A2,4 A3,1 A3,2 A3,3 A3,4 A4,1 A4,2 A4,3 A4,4 B1,1 B1,2 B2,1 B2,2 B1,1 B1,2 B2,1 B2,2 B1,1 B1,2 B2,1 B2,2
15
Mathematical Notation
A1,1B1,1 A1,2B1,2 A2,1B2,1 A2,2B2,2
16
Convolution = A C B Filter, mask or template Input image Convolved
4 7 9 6 23 21 -1 2 4 3 8 9 = 9 26 19 -1 2 3 5 9 6 10 16 27 17 2 2 3 3 4 4
17
Convolution size Image size = M1 N1 Mask size = M2 N2
M1- M2 +1 N1-N2+1 N1 N2 N1-N2+1 Typical Mask sizes = 33, 5 5, 77, 9 9, 1111 What is the convolved image size for a 128 128 image and 7 7 mask?
18
* = We convolve with 9*9 averaging filter
19
Nonlinear Neighbourhood Operations
Maximum Minimum Median We discussed already sorter architecture (three variants – pipelined, butterfly combinational and sequential controller). It can be used for all these operations, and also for other non-linear operators
20
Max and Min Operations C1,2= 61 62 57 60 59 65 63 56 55 58 49 53 45 1
63=max, 59=min
21
Median Operation 9 8 7 6 5 4 3 2 1 65 63 62 61 62 57 60 59 65 63 56 55 58 49 53 45 1 60 62 60 59 63 65 56 55 58 57 rank 59 58 57 56 C1,2= 59 55
22
9x9 Median
23
Edge Detection What do we mean by edge detection? What is an edge?
24
What is Edge Detection? Redraws the image with only the edges showing
Detects large intensity transitions between pixels Redraws the image with only the edges showing
25
What is an Edge? Edge easy to find
26
What is an Edge? Where is edge? Single pixel wide or multiple pixels?
27
What is an Edge? Noise is here
Noise: have to distinguish noise from actual edge
28
What is an Edge? Is this one edge or two?
29
What is an Edge? Texture discontinuity
30
Edge Detection – so what is an edge to be detected?
A large change in image brightness of a short spatial distance Edge strength = (I(x,y)-I(x+dx,y))/dx But this general definition still allows for many theories, software implementation and hardware architectures.
31
Now we will discuss and illustrate various kinds of filter operators
32
Edge Detection Filters
High - Pass Filtering Eliminates Uniform Regions (Low Frequencies) edge “detection” or “enhancement”
33
Edge Detection Filters
34
Edge Detection Filters
Edge Detection Continued Sum of Kernel Coefficients = 0 differences in signs emphasize differences in pixel values reduces average image intensity Negative pixel values in output?
35
Edge Direction vertical horizontal diagonal
36
Directional High Pass Filters
37
Convolution Edge Detection using Sobel and similar operators
38
Example of Sobel Operator
39
Sobel Edge Detection
40
Convolution Application Examples
We apply Sobel Operator --Edge Detection Column Mask Row Mask as mask to a sub-field of a picture p0, p1, p2 p3, p4, p5 p6, p7, p8 * = (p6-p0)+2(p7-p1)+(p8-p2) The final step of the convolution equation, dividing by the weight , must be ignored We can learn from the result obviously The result of the above calculation for column mask is horizontal difference With Row Mask we will get vertical difference
41
Convolution Application Examples
--Edge Detection with Sobel Operator The weight of a mask determines the grey level of the image after convolution. Like the weight of Sobel Mask W W= (-1) + (-2) + (-1) = 0 The resulting image lost its “lightness” to be dark.
42
Sobel Operator
43
Sobel Operator -1 -2 -1 0 0 0 1 2 1 -1 0 1 -2 0 2 S2 = S1=
S2 = S1= Edge Magnitude = Edge Direction =
44
Comparison of Edge Detection Algorithms
Sobel Canny Prewitt Ticbetts
45
Edge Direction Assymetric kernels detect edges from specific directions NorthEast East North
46
Robinson Operator
47
Robinson Compass Masks
Arrows show edge directions
48
Roberts Operator
49
Roberts Operator or 1 0 0 -1 0 1 + Does not return any information about the orientation of the edge
50
Prewitt Operator -1 -1 -1 0 0 0 1 1 1 -1 0 1 P2 = P1= Edge Magnitude =
P2 = P1= Edge Magnitude = Edge Direction =
51
Edge Detection Filters
Prewitt Row
52
Original and filtered cow
53
Edge Detection Filters: compare Prewitt and Sobel
Edge Detection (continued) First Order (Gradient) Kernels Prewitt Row Sobel Row 1 0 -1 2 0 -2 Combine Row and Column Operators
54
first derivative 1D Laplacian Operator second derivative
55
2D Laplacian Operator Convolution masks approximating a Laplacian
This is just one example of Laplacian, we can use much larger window
56
Input Mask Output
57
Image Processing Operations for Early Vision:
Edge Detection
58
Reminder: Effect of Filters
low high
59
Edges … are the important part of images intensity color edges
simplest, least robust intensity color edges textures contours condensation... most difficult, most robust There are many letters B occluded by black shape here. How to find them?
60
Image Processing Operations
Edge Detection Edges are curves in the image plane across which there is a “significant” change in image brightness. The goal of edge detection is the construction of an idealized line drawing
61
Pixels on edges
62
Edges found
63
Edge effects: rarely ideal edges
Not all information is created equal...
64
Causes of edges Depth discontinuity Surface orientation discontinuity
One surface occludes another Surface orientation discontinuity the edge of a block reflectance discontinuity texture or color changes illumination discontinuity shadows
65
Edges: causes What are they? Why?
four physical events that cause image edges...
66
Edges: causes What are they? Why? discontinuities in
four physical events that cause image edges... surface color/intensity surface normal discontinuities in depth lighting (specularities)
67
Edges: causes Edges are image locations with a local maximum in image gradient in the direction of that gradient (steepness)
68
Formal Model of Edge (cont)
69
Formal Model of Edge: Roberts
Formal Model of Edge (cont) Formal Model of Edge: Roberts
70
Formal Model of Edge: Laplacian and Marr-Hildreth
Formal Model of Edge (cont) Formal Model of Edge: Laplacian and Marr-Hildreth
71
Formal Model of Edge (cont)
72
Formal Model of Edge (cont)
73
Thresholds Thresholds are important, done before or during edge detection. original image very high threshold
74
Thresholds Thresholds original image very high threshold
75
Thresholds original image very high threshold
76
Thresholds original image very high threshold reasonable
77
Thresholds original image very high threshold reasonable too low !
this all takes time...
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.