Download presentation
Presentation is loading. Please wait.
1
Computer and Robot Vision I
Chapter 6 Neighborhood Operators Presented by: 林德垣 指導教授: 傅楸善 博士 Digital Camera and Computer Vision Laboratory Department of Computer Science and Information Engineering National Taiwan University, Taipei, Taiwan, R.O.C.
2
6.1 Introduction neighborhood operator: workhorse of low- level vision
neighborhood operator: performs conditioning, labeling, grouping DC & CV Lab. CSIE NTU
3
6.1 Introduction The output of a neighborhood operator at a given pixel position is a function of the position, of the input pixel value at the position, of the values of the input pixels in some neighborhood around the given input position, and possibly of some values of previously generated output pixels DC & CV Lab. CSIE NTU
4
6.1 Introduction numeric domain: arithmetic operations, +, -, min, max
symbolic domain: Boolean operations, AND, OR, NOT, table-look-up nonrecursive neighborhood operators: output is function of input recursive neighborhood operators: output depends partly on previous output DC & CV Lab. CSIE NTU
5
6.1 Introduction neighborhood might be small and asymmetric or large
DC & CV Lab. CSIE NTU
6
6.1 Introduction : set of neighboring pixel positions around position
general nonrecursive neighborhood operator : input , output DC & CV Lab. CSIE NTU
7
6.1 Introduction linear operator: one common nonrecursive neighborhood operator output: possibly position-dependent linear combination of inputs DC & CV Lab. CSIE NTU
8
6.1 Introduction shift-invariant: position invariant: action same regardless of position composition of shift-invariant operators: shift-invariant [e.g.] N satisfies a Shift invariance: (r’, c’) ∈ N(r,c) (r’- u, c’-v) ∈ N(r-u, c-v) , for all (u,v) DC & CV Lab. CSIE NTU
9
6.1 Introduction cross-correlation of with
: weight function: kernel or mask of weights : domain of DC & CV Lab. CSIE NTU
10
6.1 Introduction common masks for noise cleaning, (a) box filter
DC & CV Lab. CSIE NTU
11
6.1 Introduction common masked for noise cleaning DC & CV Lab.
CSIE NTU
12
6.1 Introduction Different N x N filter effects comparison
Original Image 3 x 3 5 x 5 9 x 9 15 x 15 35 x 35 DC & CV Lab. CSIE NTU
13
6.1 Introduction application of mask with weights to image 7.69
DC & CV Lab. CSIE NTU
14
6.1 Introduction convolution of with
convolution: close relative to cross-correlation convolution: linear shift-invariant if mask symmetric, convolution, and correlation the same DC & CV Lab. CSIE NTU
15
6.2 Symbolic Neighborhood Operators
indexing of neighborhoods DC & CV Lab. CSIE NTU
16
6.2.1 Region-Growing Operator
: projection, outputs first or second argument : background background pixel labeled first nonbackground label DC & CV Lab. CSIE NTU
17
6.2.1 Region-Growing Operator
4-connected: output: DC & CV Lab. CSIE NTU
18
6.2.1 Region-Growing Operator
8-connected: output: DC & CV Lab. CSIE NTU
19
6.2.1 Region-Growing Operator
DC & CV Lab. CSIE NTU
20
6.2.1 Region-Growing Operator
DC & CV Lab. CSIE NTU
21
6.2.1 Region-Growing Operator
DC & CV Lab. CSIE NTU
22
6.2.1 Region-Growing Operator
DC & CV Lab. CSIE NTU
23
6.2.1 Region-Growing Operator
DC & CV Lab. CSIE NTU
24
6.2.2 Nearest Neighbor Sets and Influence Zones
influence zones: nearest neighbor sets influence zones: iteratively region-growing DC & CV Lab. CSIE NTU
25
6.2.2 Nearest Neighbor Sets and Influence Zones
4-neighborhood for city-block distance e.g. ( i , j ), ( k , l ) : | ( k – i ) | + | ( l – j ) | 8-neighborhood for max distance (of horizontal and vertical distances) e.g. ( i , j ), ( k , l ) : max( | k – i | , | l – j | ) alternate 4, 8-neighborhood for Euclidean distance DC & CV Lab. CSIE NTU
26
Take a Break DC & CV Lab. CSIE NTU
27
6.2.3 Region-Shrinking Operator
region-shrinking: changes all border pixels to background region-shrinking: can change connectivity region-shrinking: can entirely delete region if repeatedly applied DC & CV Lab. CSIE NTU
28
6.2.3 Region-Shrinking Operator
: whether or not arguments identical : background border: has different neighbor and becomes background DC & CV Lab. CSIE NTU
29
6.2.3 Region-Shrinking Operator
4-connected: output: DC & CV Lab. CSIE NTU
30
6.2.3 Region-Shrinking Operator
8-connected: output: DC & CV Lab. CSIE NTU
31
6.2.3 Region-Shrinking Operator
region shrinking: related to binary erosion except on labeled region DC & CV Lab. CSIE NTU
32
6.2.3 Region-Shrinking Operator
DC & CV Lab. CSIE NTU
33
6.2.3 Region-Shrinking Operator
DC & CV Lab. CSIE NTU
34
6.2.3 Region-Shrinking Operator
DC & CV Lab. CSIE NTU
35
6.2.3 Region-Shrinking Operator
DC & CV Lab. CSIE NTU
36
6.2.4 Mark-Interior/Border-Pixel Operator
mark-interior/border-pixel operator marks all interior pixels with the label and all border pixels with the label DC & CV Lab. CSIE NTU
37
6.2.4 Mark-Interior/Border-Pixel Operator
: whether or not arguments identical : recognizes whether or not its argument is symbol DC & CV Lab. CSIE NTU
38
6.2.4 Mark-Interior/Border-Pixel Operator
4-connected: output: DC & CV Lab. CSIE NTU
39
6.2.4 Mark-Interior/Border-Pixel Operator
8-connected: output: DC & CV Lab. CSIE NTU
40
6.2.5 Connectivity Number Operator
connectivity number: nonrecursive and symbolic data domain connectivity number: classify the way pixel connected to neighbors six values of connectivity: five for border, one for interior border: isolated, edge, connected, branching, crossing DC & CV Lab. CSIE NTU
41
6.2.5 Connectivity Number Operator
DC & CV Lab. CSIE NTU
42
6.2.5 Connectivity Number Operator
corner neighborhood DC & CV Lab. CSIE NTU
43
6.2.5 Connectivity Number Operator
DC & CV Lab. CSIE NTU
44
Yokoi Connectivity Number
: corner transition : corner all , no transition : center , neighbor , nothing will happen DC & CV Lab. CSIE NTU
45
Yokoi Connectivity Number
5: no transition all 8 neighbors 1, thus interior : 1 transition generates one connected component if center removed DC & CV Lab. CSIE NTU
46
Yokoi Connectivity Number
DC & CV Lab. CSIE NTU
47
Yokoi Connectivity Number
d b c e d b c DC & CV Lab. CSIE NTU
48
Yokoi Connectivity Number
d b c e d b c DC & CV Lab. CSIE NTU
49
Yokoi Connectivity Number
lena.64*64 DC & CV Lab. CSIE NTU
50
Yokoi Connectivity Number
lena.yokoi DC & CV Lab. CSIE NTU
51
Yokoi Connectivity Number
8-connectivity, only slightly different : center and corner transition : corner no transition, all : itself and two 4-neighbors , corner DC & CV Lab. CSIE NTU
52
Yokoi Connectivity Number
DC & CV Lab. CSIE NTU
53
Rutovitz Connectivity Number
Rutovitz connectivity: number of transitions from one symbol to another Rutovitz connectivity number: sometimes called crossing number h(a,b,c) = { 1, if (a=b and a <> c) or (a<>b and a =c) 0, otherwise } a1 = h( X0, X1, X6) a2 = h( X0, X6, X2) a3 = h( X0, X2, X7) a4 = h( X0, X7, X3) a5 = h( X0, X3, X8) a6 = h( X0, X8, X4) a7 = h( X0, X4, X5) a8 = h( X0, X5, X1) DC & CV Lab. CSIE NTU
54
Take a Break DC & CV Lab. CSIE NTU
55
6.2.6 Connected Shrink Operator
connected shrink: recursive operator, symbolic data domain connected shrink: deletes border pixels without disconnecting regions DC & CV Lab. CSIE NTU
56
6.2.6 Connected Shrink Operator
Top-down, left-right scan: deletes edge pixels not right-boundary DC & CV Lab. CSIE NTU
57
這邊是示意圖,後面有計算範例 DC & CV Lab. CSIE NTU
58
6.2.6 Connected Shrink Operator
: determines whether corner connected DC & CV Lab. CSIE NTU
59
6.2.6 Connected Shrink Operator
: background output symbol DC & CV Lab. CSIE NTU
60
6.2.6 Connected Shrink Operator
DC & CV Lab. CSIE NTU
61
6.2.6 Connected Shrink Operator
1 h (b, c, d, e) = { 1, if c= b and (d <> b or e<>b) 0, otherwise } Output symbol y = f (1 , 0 , 0 , 0 , 1) = g DC & CV Lab. CSIE NTU
62
6.2.6 Connected Shrink Operator
g 1 DC & CV Lab. CSIE NTU
63
6.2.7 Pair Relationship Operator
pair relationship: nonrecursive operator, symbolic data domain : determines whether first argument equals label DC & CV Lab. CSIE NTU
64
6.2.7 Pair Relationship Operator
4-connected mode, output : not deletable if Yokoi number or no neighbor : possibly deletable if Yokoi number and some neighbor DC & CV Lab. CSIE NTU
65
6.2.8 Thinning Operator thinning operator is composition of three operators: Mark-Interior/Border-Pixel The pair relationship Connected shrink DC & CV Lab. CSIE NTU
66
6.2.8 Thinning Operator DC & CV Lab. CSIE NTU
67
6.2.8 Thinning Operator lena.thin DC & CV Lab. CSIE NTU
68
6.2.8 Thinning Operator lena.thin DC & CV Lab. CSIE NTU
69
Take a Break DC & CV Lab. CSIE NTU
70
6.2.9 Distance Transformation Operator
distance transformation: produces distance to closest border pixel DC & CV Lab. CSIE NTU
71
6.2.9 Distance Transformation Operator
nonrecursive, iterative, start with : background : border, because distance to border is : interior pixels DC & CV Lab. CSIE NTU
72
6.2.9 Distance Transformation Operator
iteration: label with all with neighbor DC & CV Lab. CSIE NTU
73
6.2.9 Distance Transformation Operator
equivalent algorithm: nonrecursive iterative : if no neighbor labeled, still interior, leave it alone : self interior but neighbor labeled : already labeled, won’t change value since later route farther 4-connected: output DC & CV Lab. CSIE NTU
74
6.2.9 Distance Transformation Operator
distance transformation: produces distance to closest background recursive, two-pass DC & CV Lab. CSIE NTU
75
6.2.9 Distance Transformation Operator
first pass: left-right, top-bottom : if background still background, since min: min of upper and left neighbors and add 4-connected output DC & CV Lab. CSIE NTU
76
6.2.9 Distance Transformation Operator
second pass: right-left, bottom-up 4-connected output DC & CV Lab. CSIE NTU
77
6.2.9 Distance Transformation Operator
DC & CV Lab. CSIE NTU
78
6.2.9 Distance Transformation Operator
after pass 1 DC & CV Lab. CSIE NTU
79
6.2.9 Distance Transformation Operator
pass 1 DC & CV Lab. CSIE NTU
80
Take a Break DC & CV Lab. CSIE NTU
81
Radius of Fusion DC & CV Lab. CSIE NTU
82
Radius of Fusion DC & CV Lab. CSIE NTU
83
6.2.11 Number of Shortest Paths
number of shortest paths for each 0-pixel: to binary-1 pixel set given binary image : can be 4-neighborhood or 8-neighborhood : nonzero, stays unchanged since shortest paths counted : if zero then sum of neighboring shortest paths DC & CV Lab. CSIE NTU
84
6.2.11 Number of Shortest Paths
DC & CV Lab. CSIE NTU
85
6.2.11 Number of Shortest Paths
DC & CV Lab. CSIE NTU
86
6.2.11 Number of Shortest Paths
DC & CV Lab. CSIE NTU
87
Take a Break DC & CV Lab. CSIE NTU
88
6.3 Extremum-Related Neighborhood Operators
DC & CV Lab. CSIE NTU
89
6.3.1 Non-Minima-Maxima Operator
non-minima-maxima: nonrecursive operator, symbolic output DC & CV Lab. CSIE NTU
90
6.3.1 Non-Minima-Maxima Operator
a pixel can be neighborhood maximum not relative maximum DC & CV Lab. CSIE NTU
91
6.3.1 Non-Minima-Maxima Operator
DC & CV Lab. CSIE NTU
92
6.3.1 Non-Minima-Maxima Operator
4-connected: output pixel DC & CV Lab. CSIE NTU
93
6.3.2 Relative Extrema Operator
relative extrema operators relative maximum and minimum operators relative extrema recursive operator, numeric data domain input not changed;output modified top-down, left-right scan then bottom-up, right-left scan until no change DC & CV Lab. CSIE NTU
94
6.3.2 Relative Extrema Operator
output value: of highest extrema reachable by monotonic path relative extrema pixels: output same as input pixels DC & CV Lab. CSIE NTU
95
6.3.2 Relative Extrema Operator
pixel designations for the normal and reverse scans P285 課本的ab圖有錯 DC & CV Lab. CSIE NTU
96
6.3.2 Relative Extrema Operator
DC & CV Lab. CSIE NTU
97
6.3.2 Relative Extrema Operator
two primitive functions and : use new maximum value when ascending : keep original maximum when descending DC & CV Lab. CSIE NTU
98
6.3.2 Relative Extrema Operator
4-connected, output : top-down , left-right : bottom-up , right-left DC & CV Lab. CSIE NTU
99
6.3.2 Relative Extrema Operator
a0 = l0 a1 = h (x0, x1, a0, l1) a2 = h (x0, x2, a1, l2) 3 3,3,3,3 ) x2 , l2 x1 , l1 a0 l0, x0 x2 , l2 x1 , l1 a0 l0, x0 DC & CV Lab. CSIE NTU
100
6.3.2 Relative Extrema Operator
a0 = l0 a1 = h (x0, x1, a0, l1) a2 = h (x0, x2, a1, l2) 5 5, 5, 5, 5) x2 , l2 x1 , l1 a0 l0, x0 x2 , l2 x1 , l1 a0 l0, x0 DC & CV Lab. CSIE NTU
101
6.3.2 Relative Extrema Operator
DC & CV Lab. CSIE NTU
102
6.3.2 Relative Extrema Operator
DC & CV Lab. CSIE NTU
103
6.3.2 Relative Extrema Operator
DC & CV Lab. CSIE NTU
104
6.3.2 Relative Extrema Operator
DC & CV Lab. CSIE NTU
105
6.3.2 Relative Extrema Operator
4 重複以上動作,一直到最後,把每一個Pixel都走過一遍,至此,完成了Left-Right, Top-Down Scan DC & CV Lab. CSIE NTU
106
6.3.2 Relative Extrema Operator
a0 = l0 a1 = h (x0, x1, a0, l1) a2 = h (x0, x2, a1, l2) 6 x2 1 9 1 9 x1 l1 a0 l0 x0 l2 x0 2 x2 x1 l2 a0 l0 DC & CV Lab. CSIE NTU
107
6.3.2 Relative Extrema Operator
DC & CV Lab. CSIE NTU
108
6.3.3 Reachability Operator
successively propagating labels that can reach by monotonic paths descending reachability operator employs DC & CV Lab. CSIE NTU
109
6.3.3 Reachability Operator
g: pixels that are not relative extrema labeled background a: unchanged when neighbor is g or the same with neighbor b: become first propagated label if originally g c: common region more than one extremum can reach it by monotonic path c: already labeled and neighbor has different label, then two extrema reach a: propagate from extremum DC & CV Lab. CSIE NTU
110
6.3.3 Reachability Operator
4-connected, output a0 = l0 a1 = h (a0 , l1 , x0 , x1) a2 = h (a1 , l2 , x0 , x2) DC & CV Lab. CSIE NTU
111
6.3.3 Reachability Operator
DC & CV Lab. CSIE NTU
112
6.3.3 Reachability Operator
DC & CV Lab. CSIE NTU
113
6.3.3 Reachability Operator
DC & CV Lab. CSIE NTU
114
Take a Break DC & CV Lab. CSIE NTU
115
6.4 Linear Shift-Invariant Neighborhood Operators
convolution: commutative, associative, distributor over sums, homogeneous DC & CV Lab. CSIE NTU
116
6.4.1 Convolution and Correlation
convolution of an image f with kernel w DC & CV Lab. CSIE NTU
117
6.4.1 Convolution and Correlation
DC & CV Lab. CSIE NTU
118
6.4.1 Convolution and Correlation
DC & CV Lab. CSIE NTU
119
6.4.1 Convolution and Correlation
DC & CV Lab. CSIE NTU
120
6.4.1 Convolution and Correlation
DC & CV Lab. CSIE NTU
121
6.4.1 Convolution and Correlation
DC & CV Lab. CSIE NTU
122
6.4.1 Convolution and Correlation
DC & CV Lab. CSIE NTU
123
6.4.1 Convolution and Correlation
DC & CV Lab. CSIE NTU
124
6.4.1 Convolution and Correlation
DC & CV Lab. CSIE NTU
125
6.4.2 Separability straightforward computation:
multiplications, additions decomposition: DC & CV Lab. CSIE NTU
126
6.4.2 Separability DC & CV Lab. CSIE NTU
127
Project due Nov. 6 Write a program to generate Yokoi connectivity number You can down sample lena.bmp from 512*512 to 64*64 first. Sample pixels positions at (r, c) = (0,0), (0,8) ……, so everyone will get the same answer . DC & CV Lab. CSIE NTU
128
Project due Nov. 20 Write a program to generate thinned image.
You can down sample lena.bmp from 512*512 to 64*64 first. Sample pixels positions at (r, c) = (0,0), (0,8) ……, so everyone will get the same answer . DC & CV Lab. CSIE NTU
129
Midterm Nov. 13 extent: whatever covered up to Nov. 6 (inclusive)
DC & CV Lab. CSIE NTU
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.