Object recognition. Object Classes Individual Recognition.

Slides:



Advertisements
Similar presentations
Feature Detection. Description Localization More Points Robust to occlusion Works with less texture More Repeatable Robust detection Precise localization.
Advertisements

Foreground Focus: Finding Meaningful Features in Unlabeled Images Yong Jae Lee and Kristen Grauman University of Texas at Austin.
Generative learning methods for bags of features
Unsupervised Learning of Visual Object Categories Michael Pfeiffer
Visual Recognition Tutorial
Beyond bags of features: Part-based models Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
Probabilistic inference
Bayes Rule How is this rule derived? Using Bayes rule for probabilistic inference: –P(Cause | Evidence): diagnostic probability –P(Evidence | Cause): causal.
Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
Lecture 28: Bag-of-words models
Object Recognition with Informative Features and Linear Classification Authors: Vidal-Naquet & Ullman Presenter: David Bradley.
Lecture 4: Feature matching
Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
Prénom Nom Document Analysis: Data Analysis and Clustering Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
Object Recognition by Parts Object recognition started with line segments. - Roberts recognized objects from line segments and junctions. - This led to.
Feature extraction: Corners and blobs
Object Recognizing We will discuss: Features Classifiers Example ‘winning’ system.
Generative learning methods for bags of features
Object Class Recognition Using Discriminative Local Features Gyuri Dorko and Cordelia Schmid.
5/30/2006EE 148, Spring Visual Categorization with Bags of Keypoints Gabriella Csurka Christopher R. Dance Lixin Fan Jutta Willamowski Cedric Bray.
Object Class Recognition by Unsupervised Scale-Invariant Learning R. Fergus, P. Perona, and A. Zisserman Presented By Jeff.
Venus. Classification Faces – Different Faces -- Same.
CS4670: Computer Vision Kavita Bala Lecture 8: Scale invariance.
Object Recognition Vision Class Object Classes.
Scale-Invariant Feature Transform (SIFT) Jinxiang Chai.
Discriminative and generative methods for bags of features
Object Recognition by Parts Object recognition started with line segments. - Roberts recognized objects from line segments and junctions. - This led to.
Crash Course on Machine Learning
Entropy and some applications in image processing Neucimar J. Leite Institute of Computing
Object Recognizing. Object Classes Individual Recognition.
Step 3: Classification Learn a decision rule (classifier) assigning bag-of-features representations of images to different classes Decision boundary Zebra.
Example 16,000 documents 100 topic Picked those with large p(w|z)
Object Recognizing. Recognition -- topics Features Classifiers Example ‘winning’ system.
Building local part models for category-level recognition C. Schmid, INRIA Grenoble Joint work with G. Dorko, S. Lazebnik, J. Ponce.
Bag-of-features models. Origin 1: Texture recognition Texture is characterized by the repetition of basic elements or textons For stochastic textures,
Beyond Sliding Windows: Object Localization by Efficient Subwindow Search The best paper prize at CVPR 2008.
CSCE 643 Computer Vision: Extractions of Image Features Jinxiang Chai.
Chapter 4: Pattern Recognition. Classification is a process that assigns a label to an object according to some representation of the object’s properties.
ECE 5984: Introduction to Machine Learning Dhruv Batra Virginia Tech Topics: –Unsupervised Learning: Kmeans, GMM, EM Readings: Barber
Latent Dirichlet Allocation D. Blei, A. Ng, and M. Jordan. Journal of Machine Learning Research, 3: , January Jonathan Huang
Visual Categorization With Bags of Keypoints Original Authors: G. Csurka, C.R. Dance, L. Fan, J. Willamowski, C. Bray ECCV Workshop on Statistical Learning.
Topic Models Presented by Iulian Pruteanu Friday, July 28 th, 2006.
Discovering Objects and their Location in Images Josef Sivic 1, Bryan C. Russell 2, Alexei A. Efros 3, Andrew Zisserman 1 and William T. Freeman 2 Goal:
CS654: Digital Image Analysis
Object Recognizing. Object Classes Individual Recognition.
Object Recognizing. Object Classes Individual Recognition.
Ch 1. Introduction (Latter) Pattern Recognition and Machine Learning, C. M. Bishop, Summarized by J.W. Ha Biointelligence Laboratory, Seoul National.
Computer Vision Lecture 7 Classifiers. Computer Vision, Lecture 6 Oleh Tretiak © 2005Slide 1 This Lecture Bayesian decision theory (22.1, 22.2) –General.
Finding Clusters within a Class to Improve Classification Accuracy Literature Survey Yong Jae Lee 3/6/08.
A PPLICATIONS OF TOPIC MODELS Daphna Weinshall B Slides credit: Joseph Sivic, Li Fei-Fei, Brian Russel and others.
Object Recognition by Parts
Chapter 3: Maximum-Likelihood Parameter Estimation
Object Recognizing ..
Interest Points EE/CSE 576 Linda Shapiro.
Distinctive Image Features from Scale-Invariant Keypoints
The topic discovery models
Object Recognition by Parts
The topic discovery models
Object Recognition by Parts
Object Recognition by Parts
Brief Review of Recognition + Context
Where did we stop? The Bayes decision rule guarantees an optimal classification… … But it requires the knowledge of P(ci|x) (or p(x|ci) and P(ci)) We.
The topic discovery models
Object Classes Most recent work is at the object level We perceive the world in terms of objects, belonging to different classes. What are the differences.
LECTURE 23: INFORMATION THEORY REVIEW
Example segmentations - unseen images
Object Recognition by Parts
Object Recognition with Interest Operators
Presentation transcript:

Object recognition

Object Classes

Individual Recognition

Is this a dog?

Variability of Airplanes Detected

Variability of Horses Detected

ClassNon-class

Recognition with 3-D primitives Geons

Visual Class: Common Building Blocks

Optimal Class Components? Large features are too rare Small features are found everywhere Find features that carry the highest amount of information

Entropy Entropy: x =01H p =0.50.5?

Mutual Information I(x,y) X alone: p(x) = 0.5, 0.5H = 1.0 X given Y: Y = 0 Y = 1 p(x) = 0.8, 0.2 H = 0.72 p(x) = 0.1, 0.9 H = 0.47 H(X|Y) = 0.5* *0.47 = H(X) – H(X|Y) = 1 – = I(X,Y) = 0.405

Mutual information H(C) when F=1H(C) when F=0 I(C;F) = H(C) – H(C/F) F=1 F=0 H(C)

Mutual Information II

Computing MI from Examples Mutual information can be measured from examples: 100 Faces100 Non-faces Feature: 44 times 6 times Mutual information: H(C) = 1, H(C|F) =

Full KL Classification Error FC p(F|C) q(C|F) p(C)

Optimal classification features Theoretically: maximizing delivered information minimizes classification error In practice: informative object components can be identified in training images

Selecting Fragments

Adding a New Fragment (max-min selection) ? MIΔ MI = MI [ Δ ; class ] - MI [ ; class ] Select: Max i Min k ΔMI (Fi, Fk) (Min. over existing fragments, Max. over the entire pool)

Highly Informative Face Fragments

Intermediate Complexity

Decision Combine all detected fragments F k : ∑w k F k > θ

Optimal Separation SVMPerceptron ∑wk Fk = θ is a hyperplane

Combining fragments linearly Conditional independence: P(F1,F2 | C) = p(F1|C) p(F2|C) > θ> θ > θ> θ W(Fi) = log Σw(Fi) > θ

If Fi=1 take log If Fi=0 take log Instead: Σ w i > θ On all the detected fragments only With: w i = w(Fi=1) – w(Fi=0)

Class II

ClassNon-class

Fragments with positions ∑w k F k > θ On all detected fragments within their regions

Horse-class features

Examples of Horses Detected

Interest points (Harris) SIFT Descriptors I x 2 I x I y I x I y I y 2 ∑

Harris Corner Operator < I x I y < H = Averages within a neighborhood. Corner: The two eigenvalues λ1, λ2 are large Indirectly: ‘Corner’ = det(H) – k trace 2 (H)

Harris Corner Examples

SIFT descriptor David G. Lowe, "Distinctive image features from scale-invariant keypoints," International Journal of Computer Vision, 60, 2 (2004), pp Example: 4*4 sub-regions Histogram of 8 orientations in each V = 128 values: g 1,1,…g 1,8,……g 16,1,…g 16,8

SIFT

Constellation of Patches Using interest points Fegurs, Perona, Zissermann 2003 Six-part motorcycle model, joint Gaussian,

Bag of words and Unsupervised Classification

Bag of visual words A large collection of image patches –

Each class has its words historgram – – –

pLSA Classify document automatically, find related documents, etc. based on word frequency. Documents contain different ‘topics’ such as Economics, Sports, Politics, France… Each topic has its typical word frequency. Economics will have high occurrence of ‘interest’, ‘bonds’ ‘inflation’ etc. We observe the probabilities p(w i | d n ) of words and documents Each document contains several topics, z k A word has different probabilities in each topic, p(w i | z k ). A given document has a mixture of topics: p(z k | d n ) The word-frequency model is: p(w i | d n ) = Σ k p(w i |z k ) p(z k | d n ) pLSA was used to discover topics, and arrange documents according to their topics.

pLSA The word-frequency model is: p(w i | d n ) = Σ k p(w i |z k ) p(z k | d n ) We observe p(w i | d n ) and find the best p(w i |z k ) and p(z k | d n ) to explain the data pLSA was used to discover topics, and then arrange documents according to their topics.

Discovering objects and their location in images Sivic, Russel, Efros, Freedman & Zisserman CVPR 2005 Uses simple ‘visual words’ for classification Not the best classifier, but obtains unsupervised classification, using pLSA

Visual words – unsueprvised classification Four classes: faces, cars, airplanes, motorbikes, and non-class. Training images are mixed. Allowed 7 topics, one per class, the background includes 3 topics. Visual words: local patches using SIFT descriptors. –(say local 10*10 patches) codewords dictionary

Learning Data: the matrix D ij = p(w i | I j ) During learning – discover ‘topics’ (classes + background) p(w i | I j ) = Σ p(w i | T k ) p(T k | I j ) Optimize over p(w i | T k ), p(T k | I j ) The topics are expected to discover classes Got mainly one topic per class image.

Results of learning

Classifying a new image New image I: Measure p(w i | I) Find topics for the new image: p(w i | I) = Σ p(w i | T k ) p(T k | I) Optimize over the topics T k Find the largest (non-background) topic

Classifying a new image

On general model learning The goal is to classify C using a set of features F. F have been selected (must have high MI(C;F)) The next goal is to use F to decide on the class C. Probabilistic approach: Use observations to learn the joint distribution p(C,F) In a new image, F is observed, find the most likely C, Max (C) p(C,F)

General model learning To learn the joint distribution p(C,F): The model is of the form p θ (C,F) –Or: p θ (C,X,F) For example we had – words in documents: –p(w,D) = Πp(w i,D) –p(w i | D) = Σ p(w i | T k ) p(T k | D) Training examples used to determine optimal θ by maximizing p θ (data) – max (C,X, θ) p θ (C,X,F) When θ known, classify new example: –max (C,X) p θ (C,X,F)