1	Texture This isn’t described in Trucco and Verri Parts are described in: Computer Vision, a Modern Approach by Forsyth and Ponce “Texture Synthesis by Non-parametric Sampling”, by Efros and Leung, Int. Conf. On Comp. Vis. 1999.
2	Texture Edge detectors find differences in overall intensity. Average intensity is only simplest difference.
3
4
5	Issues: 1) Discrimination/Analysis
6	2) Synthesis
7	Many more issues 3. Texture boundary detection. 4. Shape from texture. We’ll focus on 1 and 2.
8	What is texture? Something that repeats with variation. Must separate what repeats and what stays the same. Model as repeated trials of a random process The probability distribution stays the same. But each trial is different. This may be true (eg., pile of objects) Or not really (tile floor).
9	Simplest Texture Each pixel independent, identically distributed (iid). Examples: Region of constant intensity. Gaussian noise pattern. Speckled pattern Matlab
10	Texture Discrimination is then Statistics Two sets of samples. Do they come from the same random process?
11	Simplest Texture Discrimination Compare sample distributions (histograms). Divide intensities into discrete ranges. Count how many pixels in each range.
12	How/why to compare Simplest comparison is SSD, many others. Can view probabilistically. Histogram is a set of samples from a probability distribution. With many samples it approximates distribution. Test probability samples drawn from same distribution. Ie., is difference greater than expected when two samples come from same distribution?
13
14	More Complex Discrimination Histogram comparison is very limiting Every pixel is independent. Everything happens at a tiny scale. Matlab
15	Wavelet representations Wavelet coefficients are less dependent than pixels Neighboring pixels are very dependent. This is why used for compression (JPEG2000). Less local, seem to capture more info.
16	Example (Forsyth & Ponce)
17
18	Difference of Gaussian Filters
19	Spots and Oriented Bars (Malik and Perona)
20
21
22	Gabor Filters
23
24	Gabor filters are examples of Wavelets We know two bases for images: Pixels are localized in space. Fourier are localized in frequency. Wavelets are a little of both. Good for measuring frequency locally.
25	Synthesis with this Representation (Bergen and Heeger)
26
27
28	Modeling Dependencies Pairwise dependencies Co-occurrence of intensities at different distance/angles. Covariance matrix of pixel and all nearby pixels.
29	Gabor vectors Compute Gabors at (8) different orientations and (5) scales. Each image point -> a point in an 80 dimensional space (each Gabor output is complex). Compare histograms in 80D This is hard part. Dividing space into regular buckets doesn’t work. Cluster points Assign each point to a cluster Implicitly, this partitions space more intelligently. Compare using Chi-Squared or whatever you like.
30	Markov Model Captures local dependencies. Each pixel depends on neighborhood. Example, 1D first order model P(p1, p2, …pn) = P(p1)P(p2\|p1)P(p3\|p2,p1)… = P(p1)P(p2\|p1)P(p3\|p2)P(p4\|p3)*…
31	Markov model of Printed English From Shannon: “A mathematical theory of communication.” Think of text as a 1D texture Choose next letter at random, based on previous letters.
32
33
34
35
36	"Zero’th order" Zero’th order: XFOML RXKHJFFJUJ ZLPWCFWKCYJ FFJEYVKCQSGHYD QPAAMKBZAACIBZIHJQD First order: OCRO HLI RGWR NMIELWIS EU LL NBNESEBYA TH EEI ALHENHTTPA OOBTTVA NAH BRI Second order ON IE ANTSOUTINYS ARE T INCTORE T BE S DEAMY ACHIN D ILONASIVE TUCOOWE AT TEASONARE FUSO TIZIN ANDY TOBE SEACE CTISBE Third order: IN NO IST LAT WHEY CRATICT FROURE BIRS GROCID PONDENOME OF DEMONSTURES OF THE REPTAGIN IS REGOACTIONA OF CRE.
37	Markov models of words First order: REPRESENTING AND SPEEDILY IS AN GOOD APT OR COME CAN DIFFERENT NATURAL HERE HE THE A IN CAME THE TO OF TO EXPERT GRAY COME TO FURNISHES THE LINE MESSAGE HAD BE THESE. Second order: THE HEAD AND IN FRONTAL ATTACK ON AN ENGLISH WRITER THAT THE CHARACTER OF THIS POINT IS THEREFORE ANOTHER METHOD FOR THE LETTERS THAT THE TIME OF WHO EVER TOLD THE PROBLEM FOR AN UNEXPECTED.
38	Example 1^st Order Markov Model Each pixel is like neighbor to left + noise with some probability. Matlab These capture a much wider range of phenomena. Think about two images with identical histograms created with imresize.
39	There are dependencies in Filter Outputs Edge Filter responds at one scale, often does at other scales. Filter responds at one orientation, often doesn’t at orthogonal orientation. Synthesis using wavelets and Markov model for dependencies: DeBonet and Viola Portilla and Simoncelli
40
41
42	We can do this without filters Each pixel depends on neighbors. As you synthesize, look at neighbors. Look for similar neighborhood in sample texture. Copy pixel from that neighborhood. Continue.
43
44	This is like copying, but not just repetition
45	With Blocks
46
47
48	Conclusions Model texture as generated from random process. Discriminate by seeing whether statistics of two processes seem the same. Synthesize by generating image with same statistics.
49	To Think About 3D effects Shape: Tiger’s appearance depends on its shape. Lighting: Bark looks different with light angle Given pictures of many chairs, can we generate a new chair?
50	Textons
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66