1. CSE 415 -- (c) S. Tanimoto, 2007 Image Understanding
Outline:
Motivation
Human vision and illusions
Image representation:
Sampling, Quantization, Thresholding
Stereo vision as an AI problem
Stereograms, Geometry of stereograms, Computing
correspondences
Letting cues vote for hypotheses:
Polar representation of a line, Hough transform
Gestalt grouping
CSE (c) S. Tanimoto, Image Understanding

2. CSE 415 -- (c) S. Tanimoto, 2007 Image Understanding
Motivation
Allow computer and robots to read books.
Allow mobile robots to navigate using vision.
Support applications in industrial inspection, medical image analysis, security and surveillance, and remote sensing of the environment.
Permit computers to recognize users’ faces, fingerprints, and to track them in various environments.
Provide prostheses for the blind.
Develop artistic intelligence.
CSE (c) S. Tanimoto, Image Understanding

3. CSE 415 -- (c) S. Tanimoto, 2007 Image Understanding
Human Vision
25% of brain volume is allocated to visual perception.
Human vision is a parallel & distributed system, involving 2 eyes, retinal processing, and multiple layers of processing in the striate cortex.
Most humans are trichromats and they perceive color in a 3-D color space (except for bichromats and monochromats).
Vision provides a high-bandwidth input mechanism... “a picture is worth 1000 words.”
CSE (c) S. Tanimoto, Image Understanding

4. CSE 415 -- (c) S. Tanimoto, 2007 Image Understanding
Visual Illusions
They provide insights about the nature of the human visual system, helping us understand how it works.
Mueller-Lyer illusion
CSE (c) S. Tanimoto, Image Understanding

5. CSE 415 -- (c) S. Tanimoto, 2007 Image Understanding
Herman Grid Illusion
CSE (c) S. Tanimoto, Image Understanding

6. Herman Grid Illusion (dark on light)
CSE (c) S. Tanimoto, Image Understanding

7. Subjective Contour (Triangle)
CSE (c) S. Tanimoto, Image Understanding

8. CSE 415 -- (c) S. Tanimoto, 2007 Image Understanding
Image Representation
Sampling: Number and density of “pixel” measurements
Quantization: Number of levels permitted in pixel values.
CSE (c) S. Tanimoto, Image Understanding

9. Image Representation (cont.)
Sampling: e.g., 4 by 4, square grid, 1 pixel/cm
Quantization: e.g., binary, {0, 1}, 0 = black, 1 = white. 1 1 1 1 1 1
CSE (c) S. Tanimoto, Image Understanding

10. Aliasing due to Under-sampling
Here the apparent frequency is about 1/5 the true frequency.
CSE (c) S. Tanimoto, Image Understanding

11. CSE 415 -- (c) S. Tanimoto, 2007 Image Understanding
Quantization
Capturing a wide dynamic range of brightness levels or colors requires fine quantization. Common is 256 levels of each of red, green and blue.
Segmentation is simplified by having a small number of levels -- provided foreground and background pixels are reliably distinguished by their dark or light value.
Grayscale thresholding is typically to used to reduce the number of quantization levels to 2.
CSE (c) S. Tanimoto, Image Understanding

12. Vision as Inferring Information from Clues
Deriving 3D structure from 2D info requires additional information: e.g., constraints.
Deriving global descriptions from local data requires information fusion, i.e., inference.
CSE (c) S. Tanimoto, Image Understanding

13. Stereo Vision as an AI Problem
Projection from 3 dimension to 2 loses information.
With 2 projections, we can gain back some of that information.
Recovering the missing information is an inference problem.
The missing information is constrained by knowledge about the real world and assumptions about the scene.
The use of knowledge and assumptions to make inferences is a standard approach in artificial intelligence.
CSE (c) S. Tanimoto, Image Understanding

14. CSE 415 -- (c) S. Tanimoto, 2007 Image Understanding
Stereograms
Two-view stereograms:
1. spatially separated left-eye/right-eye pair
(including virtual-reality goggles)
2. superimposed, with separation using color filters.
3. superimposed, with temporal shuttering.
4. superimposed, with separation using polarizing filters.
Single-view stereograms:
1. Magic-eye pictures with depth-modulated carrier.
2. Wallpaper offering depth effects due to its periodicity.
CSE (c) S. Tanimoto, Image Understanding

15. Geometry of Stereograms
CSE (c) S. Tanimoto, Image Understanding

16. Computing Correspondence
Approach 1: Extract features and find a consistent matching of features in each view.
Approach 2: Directly compute a disparity map, performing local correlations of the views.
CSE (c) S. Tanimoto, Image Understanding

17. Inferring Trends via Voting Methods
The classical Hough Transform identifies prominent lines in a scene by letting each edge point vote for the line(s) it is on.
Voting methods can do well under noisy conditions.
Votes are tallied in an array of accumulators, indexed by theta and rho (polar parameters of a line).
ρ = x cos θ + y sin θ.
CSE (c) S. Tanimoto, Image Understanding

18. Letting a Point Vote for all the Lines that Pass Through It
CSE (c) S. Tanimoto, Image Understanding

19. Hough Transform: Polar representation
ρ = x cos θ + y sin θ.
(x, y) ρ
(0, 0) θ
CSE (c) S. Tanimoto, Image Understanding

20. Hough Transform (Cont.)
nondirectional, unweighted Hough Transform:
H(θ,ρ) = Σ Σ f(x,y) δ(x cos θ + y sin θ - ρ).
δ(x) = if | x | < 1
otherwise
CSE (c) S. Tanimoto, Image Understanding

21. CSE 415 -- (c) S. Tanimoto, 2007 Image Understanding
Gestalt Grouping
CSE (c) S. Tanimoto, Image Understanding

22. CSE 415 -- (c) S. Tanimoto, 2007 Image Understanding
Gestalt Grouping
Texture element = “texel”
Texel directionality
Texel granularity
Alignments of endpoints
Spacing of texels
Groups cue for surfaces, objects.
CSE (c) S. Tanimoto, Image Understanding