Face Detection. Raghuraman Gopalan AT&T Labs-Research, Middletown NJ USA
|
|
- Isabel Thompson
- 5 years ago
- Views:
Transcription
1 Face Detection Raghuraman Gopalan AT&T Labs-Research, Middletown NJ USA Book chapter collaborators: William Schwartz (University of Campinas, Brazil), Rama Chellappa and Ankur Srivastava (University of Maryland, College Park, USA) Image courtesy: Google Images
2 Outline Categorization of face detection methods Detectors Viola-Jones Deep learning Local interest points Role of Context Semantic info. of supporting human Computational Issues Practical Systems 2
3 Pose Facial variations Ageing Lighting Expressions Blur Occlusion 3
4 Overview : Rosenfeld, Kelly, Kanade et al early 90 s: Morphology, knowledgebased, invariants early 2000 s: PCA, Neural net, SVM, Boosting 2000-now: Local features, Context 2005-now: Large-scale deployment Sliding windows 4
5 Sliding-window methodology Basic idea: slide a window across image and evaluate a face model at every location Knowledge-based Feature invariants Template-based Appearance learning Yang et al., Face detection survey article, PAMI 2002, ICPR 2004 Tutorial 5
6 Knowledge-based Feature-based Top-down Human-coded rules Bottom-up Feature invariants Yang and Huang 94, Kotropoulos and Pitas 94 Leung et al. 95, Yow and Cipolla 90 6
7 Template Matching Store a template Predefined: edges or regions Deformable: facial contours (e.g., Snakes) Hand-coded templates (not learned) Use correlation to locate faces 7
8 Appearance-Based Methods: Classifiers Neural network Multilayer Perceptrons Principal Component Analysis (PCA), Factor Analysis Support vector machine (SVM) Mixture of PCA, Mixture of factor analyzers Naïve Bayes classifier Hidden Markov model Sparse network of winnows (SNoW) Kullback relative information Inductive learning: C4.5 Adaboost Deep learning 8
9 The Viola-Jones Face Detector Key ideas Integral images for fast feature evaluation Boosting for feature selection Attentional cascade for fast rejection of non-face windows Viola and Jones CVPR 2001, IJCV
10 Image Features Haar filters (x,y) (x,y) Integral image Value = (pixels in white area) (pixels in black area) 10
11 Feature selection 11
12 Learning Relevant features - Boosting Xt=2 12
13 Boosting - Principle 13
14 Boosting - Principle 14
15 Boosting - Principle 15
16 Boosting - Principle 16
17 Boosting - Principle 17
18 Boosting - Principle 18
19 The Problem of Outliers Ref: Freund and Schapire 97, Dietterich 00, Friedman, Hastie and Tibshirani 00, Freund 01 19
20 % Detection Attentional cascade Chain classifiers that are progressively more complex and have lower false positive rates: Receiver operating characteristic % False Pos 0 50 vs false neg determined by IMAGE SUB-WINDOW Classifier 1 T Classifier 2 T Classifier 3 T FACE F F F NON-FACE NON-FACE NON-FACE 20
21 Output of Face Detector on Test Images 21
22 Profile Detection 22
23 Profile Features 23
24 Other detection tasks Facial Feature Localization Male vs. female 24
25 Summary: Viola-Jones detector Rectangle/ Haar features Integral images for fast computation Feature selection through boosting Attentional cascade for fast rejection of negative windows 25
26 High Precision Systems Deep Learning* Popular Architectures RBM (Restricted Boltzmann Machines) Auto-encoders * deeplearning.net 26
27 Results with Deep Learning* * Osadchy, Le Cun, Miller; JMLR 07 27
28 Local interest points Motivated by topic-models 28
29 Extracting interest points from images Feature description codebook Vector quantization Histogram representation Slide credit (next 3 slides): ICCV 2009 tutorial on Recognizing and learning object categories 29
30 Object Bag of words 30
31 What about spatial info? 31
32 Adding spatial info Feature level Generative models Discriminative models Savarese, Winn and Criminisi, CVPR 2006 Sudderth, Torralba, Freeman & Willsky, 2005, 2006 Niebles & Fei-Fei, CVPR 2007 Lazebnik, Schmid & Ponce,
33 Interest points Sliding windows 33
34 Video-based face detection Part-based Models Fischler and Elschlager 73, Huttenlocher 05, Ramanan 07 Mikolajczyk 01 34
35 Context Objects do not occur in isolation The surrounding scene information does provide some clue about the presence of objects Image Credit: Torralba 03 35
36 Types of Context* *material from Divvala, Hoiem, Hays, Efros, and Hebert, Empirical study of context in object detection, CVPR
37 Face/Human Detection under Partial Occlusions* R. Gopalan, W. Schwartz ACM PerMIS 2010 W. Schwartz, R. Gopalan, R. Chellappa, L.S. Davis ICB
38 Illustration Face detection probability * Person detection probability 0.324** * Probability of presence of a face obtained from Moon et al T-IP (2003) ** Probability of presence of a human obtained from Schwartz et al ICCV (2009) 38
39 Related work Bilattice-based logical reasoning: Shet et al CVPR (2007) Integrating probability of human parts using first-order logic (FOL): Schwartz et al ICB (2009) 39
40 Our approach: Probabilistic logical inference Using Markov logic networks* (MLN) Representing `semantic context between the detection probabilities of parts. Enforce consistency according to spatial location of detectors removal of false alarms. Exploit relations between persons to solve inconsistencies explain occlusions. *Domingos et al, Machine Learning (2006) 40
41 Our approach: An overview Multiple detection windows Part detector s outputs Face detector outputs Learning contextual rules Final Result Instantiation of the MLN Queries: - face/person(d1)? - occluded(d1)? - occludedby(d1,d2)? Inference 41
42 Our approach: An overview Multiple detection windows Part detector s outputs Face detector outputs Learning contextual rules Final Result Instantiation of the MLN Queries: - person(d1)? - occluded(d1)? - occludedby(d1,d2)? Inference 42
43 Part-based detectors To handle human detection under occlusion, our original detector is split into parts, then MLN is used to integrate their outputs. top top-torso Features: edges texture color original torso torso-legs Partial least squares (PLS)- based dimensionality reduction legs top-legs 43
44 Our approach: An overview Multiple detection windows Part detector s outputs Face detector outputs Learning contextual rules Final Result Instantiation of the MLN Queries: - person(d1)? - occluded(d1)? - occludedby(d1,d2)? Inference 44
45 Context: Consistency between the detector outputs top-torso top torso First order logic rules: toptorso(d1) ^ top(d1) ^ torso(d1) person(d1) (consistent) toptorso(d1) ^ ( top(d1) v torso(d1)) person(d1) (false alarm) 45
46 Context: Understanding relationship between different windows d2 First order logic rule: d1 intersect(d1,d2) ^ person(d1) ^ matching(d1,d2) person(d2) ^ occluded(d2) ^ occludedby(d2,d1) matching(d1,d2) is true if: - Detectors at visible parts of d2 have high response. - d1, and d2 are persons - d1 and d2 intersect - detectors at occluded parts of d2 have low response while sensors located at the corresponding positions of d1 have high response. 46
47 Our approach: An overview Multiple detection windows Part detector s outputs Face detector outputs Learning contextual rules Final Result F i Instantiation of the MLN Queries: - person(d1)? - occluded(d1)? - occludedby(d1,d2)? Inference 47
48 Inference using MLN* - The basic idea A logical knowledge base (KB) is a set of hard constraints (F i ) on the set of possible worlds Let s make them soft constraints: A Markov Logic Network (MLN) is a set of pairs (F i, w i ) where F i is a formula in first-order logic w i is the weight of F i (a real number) P(world) exp weights of formulas it satisfies 48
49 Example: Humans & Occlusions 1) Presence of a human implies presence of parts. 2) When two humans occlude, analyzematching context between their windows 49
50 Example: Humans & Occlusions x Human( x) Parts ( x) x, y Occlusion ( x, y) Human( x) Human( y) 50
51 Example: Humans & Occlusions x Human( x) Parts ( x) x, y Occlusion ( x, y) Human( x) Human( y) 51
52 Example: Humans & Occlusions x Human( x) Parts ( x) x, y Occlusion ( x, y) Human( x) Human( y) Two constants: Detection window 1 (D1) and Detection window 2 (D2) D1 D2 52
53 Example: Humans & Occlusions x Human( x) Parts ( x) x, y Occlusion ( x, y) Human( x) Human( y) Two constants: Detection window 1 (D1) and Detection window 2 (D2) Human(D1) Human(D2) One node for each grounding of each predicate in the MLN Parts(D1) Parts(D2) 53
54 Example: Humans & Occlusions x Human( x) Parts ( x) x, y Occlusion ( x, y) Human( x) Human( y) Two constants: Detection window 1 (D1) and Detection window 2 (D2) Occlusion(D1,D2) Occlusion(D1,D1) Human(D1) Human(D2) Occlusion(D2,D2) Parts(D1) Occlusion(D2,D1) Parts(D2) 54
55 Example: Humans & Occlusions x Human( x) Parts ( x) x, y Occlusion ( x, y) Human( x) Human( y) Two constants: Detection window 1 (D1) and Detection window 2 (D2) Occlusion(D1,D2) Occlusion(D1,D1) Human(D1) Human(D2) Occlusion(D2,D2) Parts(D1) Occlusion(D2,D1) Parts(D2) One feature for each grounding of each formula Fi in the MLN, with the corresponding weight wi 55
56 Example: Humans & Occlusions x Human( x) Parts ( x) x, y Occlusion ( x, y) Human( x) Human( y) Two constants: Detection window 1 (D1) and Detection window 2 (D2) Occlusion(D1,D2) Occlusion(D1,D1) Human(D1) Human(D2) Occlusion(D2,D2) Parts(D1) Occlusion(D2,D1) Parts(D2) 56
57 Example: Humans & Occlusions x Human( x) Parts ( x) x, y Occlusion ( x, y) Human( x) Human( y) Two constants: Detection window 1 (D1) and Detection window 2 (D2) Occlusion(D1,D2) Occlusion(D1,D1) Human(D1) Human(D2) Occlusion(D2,D2) Parts(D1) Occlusion(D2,D1) Parts(D2) 57
58 Instantiation MLN is template for ground Markov nets Probability of a world x: 1 P ( x) exp wi ni ( x) Z i Weight of formula Fi No. of true groundings of formula F i Learning of weights, and inference performed using the open-source Alchemy system [Domingos et al (2006)] 58
59 Our approach: An overview Multiple detection windows Part detector s outputs Face detector outputs Learning contextual rules Final Result Instantiation of the MLN Queries: - person(d1)? - occluded(d1)? - occludedby(d1,d2)? Inference 59
60 Results 60
61 Comparisons Dataset details: 200 images 5 to 15 humans per image Occluded humans ~ 35% 61
62 Practical systems Slide credit: Microsoft Research, face.com 62
63 Practical systems Slide credit: Microsoft Research, face.com 63
64 Computational efficiency Matching Branch and bound Dynamic programming Tree/ graph traversal Representation Integral images (Viola and Jones) Contour-based Efficient contour fitting 64
65 Computationally efficient representation of piece-wise linear contours Obtain edge image Line integral image 65
66 Computationally efficient representation of piece-wise linear contours Obtain edge image Line integral image 66
67 Datasets FDDB: Face Detection Data Set and Benchmark (2010) 67
68 Challenges and Conclusion Performance Bounds Multi-modal context Devices Occlusion 68
Detecting Humans under Partial Occlusion using Markov Logic Networks
Detecting Humans under Partial Occlusion using Markov Logic Networks ABSTRACT Raghuraman Gopalan Dept. of ECE University of Maryland College Park, MD 20742 USA raghuram@umiacs.umd.edu Identifying humans
More informationRobust Human Detection Under Occlusion by Integrating Face and Person Detectors
Robust Human Detection Under Occlusion by Integrating Face and Person Detectors William Robson Schwartz, Raghuraman Gopalan 2, Rama Chellappa 2, and Larry S. Davis University of Maryland, Department of
More informationFace Detection and Alignment. Prof. Xin Yang HUST
Face Detection and Alignment Prof. Xin Yang HUST Many slides adapted from P. Viola Face detection Face detection Basic idea: slide a window across image and evaluate a face model at every location Challenges
More informationRecap Image Classification with Bags of Local Features
Recap Image Classification with Bags of Local Features Bag of Feature models were the state of the art for image classification for a decade BoF may still be the state of the art for instance retrieval
More informationWindow based detectors
Window based detectors CS 554 Computer Vision Pinar Duygulu Bilkent University (Source: James Hays, Brown) Today Window-based generic object detection basic pipeline boosting classifiers face detection
More informationClassifier Case Study: Viola-Jones Face Detector
Classifier Case Study: Viola-Jones Face Detector P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. CVPR 2001. P. Viola and M. Jones. Robust real-time face detection.
More informationPart based models for recognition. Kristen Grauman
Part based models for recognition Kristen Grauman UT Austin Limitations of window-based models Not all objects are box-shaped Assuming specific 2d view of object Local components themselves do not necessarily
More informationGeneric Object-Face detection
Generic Object-Face detection Jana Kosecka Many slides adapted from P. Viola, K. Grauman, S. Lazebnik and many others Today Window-based generic object detection basic pipeline boosting classifiers face
More informationDiscriminative classifiers for image recognition
Discriminative classifiers for image recognition May 26 th, 2015 Yong Jae Lee UC Davis Outline Last time: window-based generic object detection basic pipeline face detection with boosting as case study
More informationFace detection and recognition. Detection Recognition Sally
Face detection and recognition Detection Recognition Sally Face detection & recognition Viola & Jones detector Available in open CV Face recognition Eigenfaces for face recognition Metric learning identification
More informationFace detection and recognition. Many slides adapted from K. Grauman and D. Lowe
Face detection and recognition Many slides adapted from K. Grauman and D. Lowe Face detection and recognition Detection Recognition Sally History Early face recognition systems: based on features and distances
More informationPreviously. Window-based models for generic object detection 4/11/2011
Previously for generic object detection Monday, April 11 UT-Austin Instance recognition Local features: detection and description Local feature matching, scalable indexing Spatial verification Intro to
More informationSupervised learning. y = f(x) function
Supervised learning y = f(x) output prediction function Image feature Training: given a training set of labeled examples {(x 1,y 1 ),, (x N,y N )}, estimate the prediction function f by minimizing the
More informationHuman-Robot Interaction
Human-Robot Interaction Elective in Artificial Intelligence Lecture 6 Visual Perception Luca Iocchi DIAG, Sapienza University of Rome, Italy With contributions from D. D. Bloisi and A. Youssef Visual Perception
More informationObject recognition (part 1)
Recognition Object recognition (part 1) CSE P 576 Larry Zitnick (larryz@microsoft.com) The Margaret Thatcher Illusion, by Peter Thompson Readings Szeliski Chapter 14 Recognition What do we mean by object
More informationOverview of section. Lecture 10 Discriminative models. Discriminative methods. Discriminative vs. generative. Discriminative methods.
Overview of section Lecture 0 Discriminative models Object detection with classifiers Boosting Gentle boosting Object model Object detection Nearest-Neighbor methods Multiclass object detection Context
More informationObject Recognition. Computer Vision. Slides from Lana Lazebnik, Fei-Fei Li, Rob Fergus, Antonio Torralba, and Jean Ponce
Object Recognition Computer Vision Slides from Lana Lazebnik, Fei-Fei Li, Rob Fergus, Antonio Torralba, and Jean Ponce How many visual object categories are there? Biederman 1987 ANIMALS PLANTS OBJECTS
More informationCourse Administration
Course Administration Project 2 results are online Project 3 is out today The first quiz is a week from today (don t panic!) Covers all material up to the quiz Emphasizes lecture material NOT project topics
More informationUsing the Forest to See the Trees: Context-based Object Recognition
Using the Forest to See the Trees: Context-based Object Recognition Bill Freeman Joint work with Antonio Torralba and Kevin Murphy Computer Science and Artificial Intelligence Laboratory MIT A computer
More informationPart-based and local feature models for generic object recognition
Part-based and local feature models for generic object recognition May 28 th, 2015 Yong Jae Lee UC Davis Announcements PS2 grades up on SmartSite PS2 stats: Mean: 80.15 Standard Dev: 22.77 Vote on piazza
More informationhttps://en.wikipedia.org/wiki/the_dress Recap: Viola-Jones sliding window detector Fast detection through two mechanisms Quickly eliminate unlikely windows Use features that are fast to compute Viola
More informationObject Category Detection: Sliding Windows
04/10/12 Object Category Detection: Sliding Windows Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem Today s class: Object Category Detection Overview of object category detection Statistical
More informationLocal Features and Bag of Words Models
10/14/11 Local Features and Bag of Words Models Computer Vision CS 143, Brown James Hays Slides from Svetlana Lazebnik, Derek Hoiem, Antonio Torralba, David Lowe, Fei Fei Li and others Computer Engineering
More informationObject detection as supervised classification
Object detection as supervised classification Tues Nov 10 Kristen Grauman UT Austin Today Supervised classification Window-based generic object detection basic pipeline boosting classifiers face detection
More informationDeformable Part Models
CS 1674: Intro to Computer Vision Deformable Part Models Prof. Adriana Kovashka University of Pittsburgh November 9, 2016 Today: Object category detection Window-based approaches: Last time: Viola-Jones
More informationAnalysis: TextonBoost and Semantic Texton Forests. Daniel Munoz Februrary 9, 2009
Analysis: TextonBoost and Semantic Texton Forests Daniel Munoz 16-721 Februrary 9, 2009 Papers [shotton-eccv-06] J. Shotton, J. Winn, C. Rother, A. Criminisi, TextonBoost: Joint Appearance, Shape and Context
More informationImage Analysis. Window-based face detection: The Viola-Jones algorithm. iphoto decides that this is a face. It can be trained to recognize pets!
Image Analysis 2 Face detection and recognition Window-based face detection: The Viola-Jones algorithm Christophoros Nikou cnikou@cs.uoi.gr Images taken from: D. Forsyth and J. Ponce. Computer Vision:
More informationPreviously. Part-based and local feature models for generic object recognition. Bag-of-words model 4/20/2011
Previously Part-based and local feature models for generic object recognition Wed, April 20 UT-Austin Discriminative classifiers Boosting Nearest neighbors Support vector machines Useful for object recognition
More informationLecture 16: Object recognition: Part-based generative models
Lecture 16: Object recognition: Part-based generative models Professor Stanford Vision Lab 1 What we will learn today? Introduction Constellation model Weakly supervised training One-shot learning (Problem
More informationVisual Object Recognition
Perceptual and Sensory Augmented Computing Visual Object Recognition Tutorial Visual Object Recognition Bastian Leibe Computer Vision Laboratory ETH Zurich Chicago, 14.07.2008 & Kristen Grauman Department
More informationCS 231A Computer Vision (Fall 2011) Problem Set 4
CS 231A Computer Vision (Fall 2011) Problem Set 4 Due: Nov. 30 th, 2011 (9:30am) 1 Part-based models for Object Recognition (50 points) One approach to object recognition is to use a deformable part-based
More informationSupervised learning. y = f(x) function
Supervised learning y = f(x) output prediction function Image feature Training: given a training set of labeled examples {(x 1,y 1 ),, (x N,y N )}, estimate the prediction function f by minimizing the
More informationRecognition of Animal Skin Texture Attributes in the Wild. Amey Dharwadker (aap2174) Kai Zhang (kz2213)
Recognition of Animal Skin Texture Attributes in the Wild Amey Dharwadker (aap2174) Kai Zhang (kz2213) Motivation Patterns and textures are have an important role in object description and understanding
More informationObject Category Detection: Sliding Windows
03/18/10 Object Category Detection: Sliding Windows Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem Goal: Detect all instances of objects Influential Works in Detection Sung-Poggio
More informationDetecting and Segmenting Humans in Crowded Scenes
Detecting and Segmenting Humans in Crowded Scenes Mikel D. Rodriguez University of Central Florida 4000 Central Florida Blvd Orlando, Florida, 32816 mikel@cs.ucf.edu Mubarak Shah University of Central
More informationMachine Learning Crash Course
Machine Learning Crash Course Photo: CMU Machine Learning Department protests G20 Computer Vision James Hays Slides: Isabelle Guyon, Erik Sudderth, Mark Johnson, Derek Hoiem The machine learning framework
More informationUnderstanding Faces. Detection, Recognition, and. Transformation of Faces 12/5/17
Understanding Faces Detection, Recognition, and 12/5/17 Transformation of Faces Lucas by Chuck Close Chuck Close, self portrait Some slides from Amin Sadeghi, Lana Lazebnik, Silvio Savarese, Fei-Fei Li
More informationLarge-Scale Traffic Sign Recognition based on Local Features and Color Segmentation
Large-Scale Traffic Sign Recognition based on Local Features and Color Segmentation M. Blauth, E. Kraft, F. Hirschenberger, M. Böhm Fraunhofer Institute for Industrial Mathematics, Fraunhofer-Platz 1,
More informationFace/Flesh Detection and Face Recognition
Face/Flesh Detection and Face Recognition Linda Shapiro EE/CSE 576 1 What s Coming 1. Review of Bakic flesh detector 2. Fleck and Forsyth flesh detector 3. Details of Rowley face detector 4. The Viola
More informationVisuelle Perzeption für Mensch- Maschine Schnittstellen
Visuelle Perzeption für Mensch- Maschine Schnittstellen Vorlesung, WS 2009 Prof. Dr. Rainer Stiefelhagen Dr. Edgar Seemann Institut für Anthropomatik Universität Karlsruhe (TH) http://cvhci.ira.uka.de
More informationObject Detection Design challenges
Object Detection Design challenges How to efficiently search for likely objects Even simple models require searching hundreds of thousands of positions and scales Feature design and scoring How should
More informationPeople detection in complex scene using a cascade of Boosted classifiers based on Haar-like-features
People detection in complex scene using a cascade of Boosted classifiers based on Haar-like-features M. Siala 1, N. Khlifa 1, F. Bremond 2, K. Hamrouni 1 1. Research Unit in Signal Processing, Image Processing
More informationCategory-level localization
Category-level localization Cordelia Schmid Recognition Classification Object present/absent in an image Often presence of a significant amount of background clutter Localization / Detection Localize object
More informationLecture 18: Human Motion Recognition
Lecture 18: Human Motion Recognition Professor Fei Fei Li Stanford Vision Lab 1 What we will learn today? Introduction Motion classification using template matching Motion classification i using spatio
More informationHuman Detection and Tracking for Video Surveillance: A Cognitive Science Approach
Human Detection and Tracking for Video Surveillance: A Cognitive Science Approach Vandit Gajjar gajjar.vandit.381@ldce.ac.in Ayesha Gurnani gurnani.ayesha.52@ldce.ac.in Yash Khandhediya khandhediya.yash.364@ldce.ac.in
More informationSelection of Scale-Invariant Parts for Object Class Recognition
Selection of Scale-Invariant Parts for Object Class Recognition Gy. Dorkó and C. Schmid INRIA Rhône-Alpes, GRAVIR-CNRS 655, av. de l Europe, 3833 Montbonnot, France fdorko,schmidg@inrialpes.fr Abstract
More informationA novel template matching method for human detection
University of Wollongong Research Online Faculty of Informatics - Papers (Archive) Faculty of Engineering and Information Sciences 2009 A novel template matching method for human detection Duc Thanh Nguyen
More informationRecognition problems. Face Recognition and Detection. Readings. What is recognition?
Face Recognition and Detection Recognition problems The Margaret Thatcher Illusion, by Peter Thompson Computer Vision CSE576, Spring 2008 Richard Szeliski CSE 576, Spring 2008 Face Recognition and Detection
More informationHigh Level Computer Vision
High Level Computer Vision Part-Based Models for Object Class Recognition Part 2 Bernt Schiele - schiele@mpi-inf.mpg.de Mario Fritz - mfritz@mpi-inf.mpg.de http://www.d2.mpi-inf.mpg.de/cv Please Note No
More informationLocal cues and global constraints in image understanding
Local cues and global constraints in image understanding Olga Barinova Lomonosov Moscow State University *Many slides adopted from the courses of Anton Konushin Image understanding «To see means to know
More informationObject Category Detection. Slides mostly from Derek Hoiem
Object Category Detection Slides mostly from Derek Hoiem Today s class: Object Category Detection Overview of object category detection Statistical template matching with sliding window Part-based Models
More informationSkin and Face Detection
Skin and Face Detection Linda Shapiro EE/CSE 576 1 What s Coming 1. Review of Bakic flesh detector 2. Fleck and Forsyth flesh detector 3. Details of Rowley face detector 4. Review of the basic AdaBoost
More informationFinding people in repeated shots of the same scene
1 Finding people in repeated shots of the same scene Josef Sivic 1 C. Lawrence Zitnick Richard Szeliski 1 University of Oxford Microsoft Research Abstract The goal of this work is to find all occurrences
More informationOriented Filters for Object Recognition: an empirical study
Oriented Filters for Object Recognition: an empirical study Jerry Jun Yokono Tomaso Poggio Center for Biological and Computational Learning, M.I.T. E5-0, 45 Carleton St., Cambridge, MA 04, USA Sony Corporation,
More informationObject and Class Recognition I:
Object and Class Recognition I: Object Recognition Lectures 10 Sources ICCV 2005 short courses Li Fei-Fei (UIUC), Rob Fergus (Oxford-MIT), Antonio Torralba (MIT) http://people.csail.mit.edu/torralba/iccv2005
More informationBeyond bags of features: Adding spatial information. Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba
Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba Adding spatial information Forming vocabularies from pairs of nearby features doublets
More informationEvaluation and comparison of interest points/regions
Introduction Evaluation and comparison of interest points/regions Quantitative evaluation of interest point/region detectors points / regions at the same relative location and area Repeatability rate :
More informationContext. CS 554 Computer Vision Pinar Duygulu Bilkent University. (Source:Antonio Torralba, James Hays)
Context CS 554 Computer Vision Pinar Duygulu Bilkent University (Source:Antonio Torralba, James Hays) A computer vision goal Recognize many different objects under many viewing conditions in unconstrained
More informationFace Recognition for Mobile Devices
Face Recognition for Mobile Devices Aditya Pabbaraju (adisrinu@umich.edu), Srujankumar Puchakayala (psrujan@umich.edu) INTRODUCTION Face recognition is an application used for identifying a person from
More informationBoosting Object Detection Performance in Crowded Surveillance Videos
Boosting Object Detection Performance in Crowded Surveillance Videos Rogerio Feris, Ankur Datta, Sharath Pankanti IBM T. J. Watson Research Center, New York Contact: Rogerio Feris (rsferis@us.ibm.com)
More informationEfficient Kernels for Identifying Unbounded-Order Spatial Features
Efficient Kernels for Identifying Unbounded-Order Spatial Features Yimeng Zhang Carnegie Mellon University yimengz@andrew.cmu.edu Tsuhan Chen Cornell University tsuhan@ece.cornell.edu Abstract Higher order
More informationEnsemble Methods, Decision Trees
CS 1675: Intro to Machine Learning Ensemble Methods, Decision Trees Prof. Adriana Kovashka University of Pittsburgh November 13, 2018 Plan for This Lecture Ensemble methods: introduction Boosting Algorithm
More informationHuman detection using local shape and nonredundant
University of Wollongong Research Online Faculty of Informatics - Papers (Archive) Faculty of Engineering and Information Sciences 2010 Human detection using local shape and nonredundant binary patterns
More informationSegmentation. Bottom up Segmentation Semantic Segmentation
Segmentation Bottom up Segmentation Semantic Segmentation Semantic Labeling of Street Scenes Ground Truth Labels 11 classes, almost all occur simultaneously, large changes in viewpoint, scale sky, road,
More informationDetecting Pedestrians Using Patterns of Motion and Appearance (Viola & Jones) - Aditya Pabbaraju
Detecting Pedestrians Using Patterns of Motion and Appearance (Viola & Jones) - Aditya Pabbaraju Background We are adept at classifying actions. Easily categorize even with noisy and small images Want
More informationIntroduction to object recognition. Slides adapted from Fei-Fei Li, Rob Fergus, Antonio Torralba, and others
Introduction to object recognition Slides adapted from Fei-Fei Li, Rob Fergus, Antonio Torralba, and others Overview Basic recognition tasks A statistical learning approach Traditional or shallow recognition
More informationLearning to Recognize Faces in Realistic Conditions
000 001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050
More informationA Survey of Various Face Detection Methods
A Survey of Various Face Detection Methods 1 Deepali G. Ganakwar, 2 Dr.Vipulsangram K. Kadam 1 Research Student, 2 Professor 1 Department of Engineering and technology 1 Dr. Babasaheb Ambedkar Marathwada
More informationCapturing People in Surveillance Video
Capturing People in Surveillance Video Rogerio Feris, Ying-Li Tian, and Arun Hampapur IBM T.J. Watson Research Center PO BOX 704, Yorktown Heights, NY 10598 {rsferis,yltian,arunh}@us.ibm.com Abstract This
More informationA Hybrid Face Detection System using combination of Appearance-based and Feature-based methods
IJCSNS International Journal of Computer Science and Network Security, VOL.9 No.5, May 2009 181 A Hybrid Face Detection System using combination of Appearance-based and Feature-based methods Zahra Sadri
More informationLearning Visual Semantics: Models, Massive Computation, and Innovative Applications
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications Part II: Visual Features and Representations Liangliang Cao, IBM Watson Research Center Evolvement of Visual Features
More informationTracking Using Online Feature Selection and a Local Generative Model
Tracking Using Online Feature Selection and a Local Generative Model Thomas Woodley Bjorn Stenger Roberto Cipolla Dept. of Engineering University of Cambridge {tew32 cipolla}@eng.cam.ac.uk Computer Vision
More informationFace Objects Detection in still images using Viola-Jones Algorithm through MATLAB TOOLS
Face Objects Detection in still images using Viola-Jones Algorithm through MATLAB TOOLS Dr. Mridul Kumar Mathur 1, Priyanka Bhati 2 Asst. Professor (Selection Grade), Dept. of Computer Science, LMCST,
More informationPart-Based Models for Object Class Recognition Part 2
High Level Computer Vision Part-Based Models for Object Class Recognition Part 2 Bernt Schiele - schiele@mpi-inf.mpg.de Mario Fritz - mfritz@mpi-inf.mpg.de https://www.mpi-inf.mpg.de/hlcv Class of Object
More informationPart-Based Models for Object Class Recognition Part 2
High Level Computer Vision Part-Based Models for Object Class Recognition Part 2 Bernt Schiele - schiele@mpi-inf.mpg.de Mario Fritz - mfritz@mpi-inf.mpg.de https://www.mpi-inf.mpg.de/hlcv Class of Object
More informationSubject-Oriented Image Classification based on Face Detection and Recognition
000 001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050
More informationDetection of Multiple, Partially Occluded Humans in a Single Image by Bayesian Combination of Edgelet Part Detectors
Detection of Multiple, Partially Occluded Humans in a Single Image by Bayesian Combination of Edgelet Part Detectors Bo Wu Ram Nevatia University of Southern California Institute for Robotics and Intelligent
More informationLast week. Multi-Frame Structure from Motion: Multi-View Stereo. Unknown camera viewpoints
Last week Multi-Frame Structure from Motion: Multi-View Stereo Unknown camera viewpoints Last week PCA Today Recognition Today Recognition Recognition problems What is it? Object detection Who is it? Recognizing
More informationModern Object Detection. Most slides from Ali Farhadi
Modern Object Detection Most slides from Ali Farhadi Comparison of Classifiers assuming x in {0 1} Learning Objective Training Inference Naïve Bayes maximize j i logp + logp ( x y ; θ ) ( y ; θ ) i ij
More informationIs 2D Information Enough For Viewpoint Estimation? Amir Ghodrati, Marco Pedersoli, Tinne Tuytelaars BMVC 2014
Is 2D Information Enough For Viewpoint Estimation? Amir Ghodrati, Marco Pedersoli, Tinne Tuytelaars BMVC 2014 Problem Definition Viewpoint estimation: Given an image, predicting viewpoint for object of
More informationActive learning for visual object recognition
Active learning for visual object recognition Written by Yotam Abramson and Yoav Freund Presented by Ben Laxton Outline Motivation and procedure How this works: adaboost and feature details Why this works:
More informationHuman Activity Recognition Using a Dynamic Texture Based Method
Human Activity Recognition Using a Dynamic Texture Based Method Vili Kellokumpu, Guoying Zhao and Matti Pietikäinen Machine Vision Group University of Oulu, P.O. Box 4500, Finland {kello,gyzhao,mkp}@ee.oulu.fi
More informationRGBD Face Detection with Kinect Sensor. ZhongJie Bi
RGBD Face Detection with Kinect Sensor ZhongJie Bi Outline The Existing State-of-the-art Face Detector Problems with this Face Detector Proposed solution to the problems Result and ongoing tasks The Existing
More informationCS 231A Computer Vision (Fall 2012) Problem Set 4
CS 231A Computer Vision (Fall 2012) Problem Set 4 Master Set Due: Nov. 29 th, 2012 (23:59pm) 1 Part-based models for Object Recognition (50 points) One approach to object recognition is to use a deformable
More informationCS6670: Computer Vision
CS6670: Computer Vision Noah Snavely Lecture 16: Bag-of-words models Object Bag of words Announcements Project 3: Eigenfaces due Wednesday, November 11 at 11:59pm solo project Final project presentations:
More informationA Cascade of Feed-Forward Classifiers for Fast Pedestrian Detection
A Cascade of eed-orward Classifiers for ast Pedestrian Detection Yu-ing Chen,2 and Chu-Song Chen,3 Institute of Information Science, Academia Sinica, aipei, aiwan 2 Dept. of Computer Science and Information
More informationVideo Google faces. Josef Sivic, Mark Everingham, Andrew Zisserman. Visual Geometry Group University of Oxford
Video Google faces Josef Sivic, Mark Everingham, Andrew Zisserman Visual Geometry Group University of Oxford The objective Retrieve all shots in a video, e.g. a feature length film, containing a particular
More informationHuman Detection. A state-of-the-art survey. Mohammad Dorgham. University of Hamburg
Human Detection A state-of-the-art survey Mohammad Dorgham University of Hamburg Presentation outline Motivation Applications Overview of approaches (categorized) Approaches details References Motivation
More informationSpatial Latent Dirichlet Allocation
Spatial Latent Dirichlet Allocation Xiaogang Wang and Eric Grimson Computer Science and Computer Science and Artificial Intelligence Lab Massachusetts Tnstitute of Technology, Cambridge, MA, 02139, USA
More informationLocal Image Features
Local Image Features Ali Borji UWM Many slides from James Hayes, Derek Hoiem and Grauman&Leibe 2008 AAAI Tutorial Overview of Keypoint Matching 1. Find a set of distinctive key- points A 1 A 2 A 3 B 3
More informationCOSC160: Detection and Classification. Jeremy Bolton, PhD Assistant Teaching Professor
COSC160: Detection and Classification Jeremy Bolton, PhD Assistant Teaching Professor Outline I. Problem I. Strategies II. Features for training III. Using spatial information? IV. Reducing dimensionality
More informationLecture 4 Face Detection and Classification. Lin ZHANG, PhD School of Software Engineering Tongji University Spring 2018
Lecture 4 Face Detection and Classification Lin ZHANG, PhD School of Software Engineering Tongji University Spring 2018 Any faces contained in the image? Who are they? Outline Overview Face detection Introduction
More informationDetection of a Single Hand Shape in the Foreground of Still Images
CS229 Project Final Report Detection of a Single Hand Shape in the Foreground of Still Images Toan Tran (dtoan@stanford.edu) 1. Introduction This paper is about an image detection system that can detect
More informationPart-based models. Lecture 10
Part-based models Lecture 10 Overview Representation Location Appearance Generative interpretation Learning Distance transforms Other approaches using parts Felzenszwalb, Girshick, McAllester, Ramanan
More informationMining Discriminative Adjectives and Prepositions for Natural Scene Recognition
Mining Discriminative Adjectives and Prepositions for Natural Scene Recognition Bangpeng Yao 1, Juan Carlos Niebles 2,3, Li Fei-Fei 1 1 Department of Computer Science, Princeton University, NJ 08540, USA
More informationCS5670: Intro to Computer Vision
CS5670: Intro to Computer Vision Noah Snavely Introduction to Recognition mountain tree banner building street lamp people vendor Announcements Final exam, in-class, last day of lecture (5/9/2018, 12:30
More informationObject Detection by 3D Aspectlets and Occlusion Reasoning
Object Detection by 3D Aspectlets and Occlusion Reasoning Yu Xiang University of Michigan Silvio Savarese Stanford University In the 4th International IEEE Workshop on 3D Representation and Recognition
More informationVisual words. Map high-dimensional descriptors to tokens/words by quantizing the feature space.
Visual words Map high-dimensional descriptors to tokens/words by quantizing the feature space. Quantize via clustering; cluster centers are the visual words Word #2 Descriptor feature space Assign word
More informationContexts and 3D Scenes
Contexts and 3D Scenes Computer Vision Jia-Bin Huang, Virginia Tech Many slides from D. Hoiem Administrative stuffs Final project presentation Nov 30 th 3:30 PM 4:45 PM Grading Three senior graders (30%)
More informationFace Detection by Means of Skin Detection
Face Detection by Means of Skin Detection Vitoantonio Bevilacqua 1,2, Giuseppe Filograno 1, and Giuseppe Mastronardi 1,2 1 Department of Electrical and Electronics, Polytechnic of Bari, Via Orabona, 4-7125
More information