1	Announcements Project 2 due today Project 3 out today help session today
2	Recognition Readings C. Bishop, “Neural Networks for Pattern Recognition”, Oxford University Press, 1998, Chapter 1. Forsyth and Ponce, 22.3 (eigenfaces)
3	Recognition Readings C. Bishop, “Neural Networks for Pattern Recognition”, Oxford University Press, 1998, Chapter 1. Forsyth and Ponce, 22.3 (eigenfaces)
4	Recognition problems What is it? Object detection Who is it? Recognizing identity What are they doing? Activities All of these are classification problems Choose one class from a list of possible candidates
5	Face detection How to tell if a face is present?
6	One simple method: skin detection Skin pixels have a distinctive range of colors Corresponds to region(s) in RGB color space for visualization, only R and G components are shown above
7	Skin detection Learn the skin region from examples Manually label pixels in one or more “training images” as skin or not skin Plot the training data in RGB space skin pixels shown in orange, non-skin pixels shown in blue some skin pixels may be outside the region, non-skin pixels inside. Why?
8	Skin classification techniques
9	Probability Basic probability X is a random variable P(X) is the probability that X achieves a certain value or Conditional probability: P(X \| Y) probability of X given that we already know Y
10	Probabilistic skin classification Now we can model uncertainty Each pixel has a probability of being skin or not skin
11	Learning conditional PDF’s We can calculate P(R \| skin) from a set of training images It is simply a histogram over the pixels in the training images each bin R_i contains the proportion of skin pixels with color R_i
12	Learning conditional PDF’s We can calculate P(R \| skin) from a set of training images It is simply a histogram over the pixels in the training images each bin R_i contains the proportion of skin pixels with color R_i
13	Bayes rule In terms of our problem:
14	Bayesian estimation Bayesian estimation Goal is to choose the label (skin or ~skin) that maximizes the posterior this is called Maximum A Posteriori (MAP) estimation
15	Skin detection results
16	General classification This same procedure applies in more general circumstances More than two classes More than one dimension
17	Linear subspaces Classification can be expensive Must either search (e.g., nearest neighbors) or store large PDF’s
18	Dimensionality reduction
19	Linear subspaces
20	Principal component analysis Suppose each data point is N-dimensional Same procedure applies: The eigenvectors of A define a new coordinate system eigenvector with largest eigenvalue captures the most variation among training vectors x eigenvector with smallest eigenvalue has least variation We can compress the data by only using the top few eigenvectors corresponds to choosing a “linear subspace” represent points on a line, plane, or “hyper-plane” these eigenvectors are known as the principal components
21	The space of faces An image is a point in a high dimensional space An N x M image is a point in R^NM We can define vectors in this space as we did in the 2D case
22	Dimensionality reduction The set of faces is a “subspace” of the set of images Suppose it is K dimensional We can find the best subspace using PCA This is like fitting a “hyper-plane” to the set of faces spanned by vectors v₁, v₂, ..., v_K any face
23	Eigenfaces PCA extracts the eigenvectors of A Gives a set of vectors v₁, v₂, v₃, ... Each one of these vectors is a direction in face space what do these look like?
24	Projecting onto the eigenfaces The eigenfaces v₁, ..., v_K span the space of faces A face is converted to eigenface coordinates by
25	Recognition with eigenfaces Algorithm Process the image database (set of images with labels) Run PCA—compute eigenfaces Calculate the K coefficients for each image Given a new image (to be recognized) x, calculate K coefficients Detect if x is a face If it is a face, who is it?
26	Choosing the dimension K How many eigenfaces to use? Look at the decay of the eigenvalues the eigenvalue tells you the amount of variance “in the direction” of that eigenface ignore eigenfaces with low variance
27	Issues: metrics What’s the best way to compare images? need to define appropriate features depends on goal of recognition task
28	Metrics Lots more feature types that we haven’t mentioned moments, statistics metrics: Earth mover’s distance, ... edges, curves metrics: Hausdorff, shape context, ... 3D: surfaces, spin images metrics: chamfer (ICP) ...
29	Issues: feature selection
30	Issues: data modeling Generative methods model the “shape” of each class histograms, PCA, mixtures of Gaussians graphical models (HMM’s, belief networks, etc.) ... Discriminative methods model boundaries between classes perceptrons, neural networks support vector machines (SVM’s)
31	Generative vs. Discriminative
32	Issues: dimensionality What if your space isn’t flat? PCA may not help
33	Other Issues Some other factors Prior information, context Classification vs. inference Representation Other recognition problems individuals classes activities low-level properties materials, super-resolution, edges, circles, etc...
34	Issues: speed Case study: Viola Jones face detector Exploits three key strategies: simple, super-efficient features image pyramids pruning (cascaded classifiers)
35	Viola/Jones: features
36	Integral Image (aka. summed area table) Define the Integral Image Any rectangular sum can be computed in constant time: Rectangle features can be computed as differences between rectangles
37	Viola/Jones: handling scale
38	Viola/Jones: cascaded classifiers Given a nested set of classifier hypothesis classes Computational Risk Minimization
39	Cascaded Classifier first classifier: 100% detection, 50% false positives. second classifier: 100% detection, 40% false positives (20% cumulative) using data from previous stage. third classifier: 100% detection,10% false positive rate (2% cumulative) Put cheaper classifiers up front
40	Viola/Jones results: