Download presentation
Presentation is loading. Please wait.
Published byAron Barrett Modified over 9 years ago
1
Vision & Recognition
2
From a different direction At different times, particularly if it has been modified in the interval In different light A particular object may have different visual attributes when viewed: Observations
3
Be able to distinguish between different objects with the same appearance Be able to recognize the same object viewed from different directions or in different light Be able to recognize the same object after modification Be able to distinguish between an object and its reflection Objectives
4
Pattern recognition Robot vision Remotely operated devices Security related software Disease Diagnosis Applications
5
5 The Minimum 3-D Feature Set The Minimum 3-D Feature Set Two cubes of the same color are indistinguishable. Cubes are distinguished by color, color count and color position
6
6 The Minimum 3-D Feature Set The Minimum 3-D Feature Set 2 sides color ‘A’ 2 sides color ‘B’ Maximum of 2 distinguishable cubes Cubes are distinguished by color, color count and color position
7
7 The Minimum 3-D Feature Set The Minimum 3-D Feature Set 3 sides color ‘A’ 3 sides color ‘B’ Maximum of 2 distinguishable cubes. 2 colors -> 8 cubes Cubes are distinguished by color, color count and color position
8
8 The Minimum 3-D Feature Set Like color sides opposite vs. like colored sides adjacent. 3 colors -> 27 cubes Cubes are distinguished by color, color count and color position
9
9 With 4 color cubes, pattern breaks. We would expect 4 3 = 64 But we only get 42 distinguishable cubes. Why? ---> Rotations ! The Minimum 3-D Feature Set
10
10 Rotations and Reflections The Eight Queens Problem for (i = 0; i < 8; i++){ ok = 1; pNextPair->column = i; pPairOnTop = pTop; while (ok = 1 && pPairOnTop != NULL){
12
Hidden patterns revealed by tiling solutions
13
Horizontal Shifts One left succeeds, all others fail to find solution
14
Vertical Shifts One up or one down succeeds; all others fail to find a solution
15
Rotation & Mirror Effects Same object viewed from different angles
16
Diagonal shifts & Mirror Effects
17
Additional Mirror Effects
18
How do we determine which patterns are significant?
19
12 partitions 12 distinct solutions Why not 96 (= 12 x 8) permutations? The answer is that one of our partitions contains only 4 "aliases" because the solution is diagonally symmetric Permutations of the solution vectors
20
Shape detection algorithms Without color… example universe: assembly-line where all parts are uniformly steel-colored
21
Shape detection algorithms Edge detection Using changes in reflectivity
22
Shape detection algorithms Edge detection Edges can intersect with planes, or air Is the background the same object or a different one?
23
Shape data structures Corners have “more information” per point Collection of points and relative distances Collection of lines and intersections Collections of shape primitives
24
Shape data structures Corners can be used to define Collections of edges and intersections Or boundaries of planes
25
Shape data structures Skeletons…AKA Wire-Frames Advantage… easier to morph
26
Shape data structures Volume filling shape primitives advantage: can easily calculate volume as sum of primitives’ volume
27
There are many applications... Volumes of research… And many areas yet unexplored... Vision & Recognition
28
Thank you.
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.