SVMs for (x) Recognition (From Moghaddam / Yang’s “Gender Classification with SVMs”) Brian Whitman.

Slides:



Advertisements
Similar presentations
Statistical Machine Learning- The Basic Approach and Current Research Challenges Shai Ben-David CS497 February, 2007.
Advertisements

Introduction to Support Vector Machines (SVM)
Lecture 9 Support Vector Machines
Zhimin CaoThe Chinese University of Hong Kong Qi YinITCS, Tsinghua University Xiaoou TangShenzhen Institutes of Advanced Technology Chinese Academy of.
Image classification Given the bag-of-features representations of images from different classes, how do we learn a model for distinguishing them?
SVM - Support Vector Machines A new classification method for both linear and nonlinear data It uses a nonlinear mapping to transform the original training.
Detecting Faces in Images: A Survey
On-the-fly Specific Person Retrieval University of Oxford 24 th May 2012 Omkar M. Parkhi, Andrea Vedaldi and Andrew Zisserman.
Face detection Behold a state-of-the-art face detector! (Courtesy Boris Babenko)Boris Babenko.
Machine learning continued Image source:
Computer Vision for Human-Computer InteractionResearch Group, Universität Karlsruhe (TH) cv:hci Dr. Edgar Seemann 1 Computer Vision: Histograms of Oriented.
LPP-HOG: A New Local Image Descriptor for Fast Human Detection Andy Qing Jun Wang and Ru Bo Zhang IEEE International Symposium.
Real-Time Human Pose Recognition in Parts from Single Depth Images Presented by: Mohammad A. Gowayyed.
AdaBoost & Its Applications
Face detection Many slides adapted from P. Viola.
Neural Computation Final Project -Earthquake Prediction , Spring Alon Talmor Ido Yariv.
The Viola/Jones Face Detector (2001)
Image classification Given the bag-of-features representations of images from different classes, how do we learn a model for distinguishing them?
TRADING OFF PREDICTION ACCURACY AND POWER CONSUMPTION FOR CONTEXT- AWARE WEARABLE COMPUTING Presented By: Jeff Khoshgozaran.
Artificial Intelligence Statistical learning methods Chapter 20, AIMA (only ANNs & SVMs)
Robust Real-time Object Detection by Paul Viola and Michael Jones ICCV 2001 Workshop on Statistical and Computation Theories of Vision Presentation by.
Ensemble Tracking Shai Avidan IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE February 2007.
Face detection and recognition Many slides adapted from K. Grauman and D. Lowe.
Face Recognition with Harr Transforms and SVMs EE645 Final Project May 11, 2005 J Stautzenberger.
Support Vector Machines Kernel Machines
The Implicit Mapping into Feature Space. In order to learn non-linear relations with a linear machine, we need to select a set of non- linear features.
SVM (Support Vector Machines) Base on statistical learning theory choose the kernel before the learning process.
Pattern Recognition. Introduction. Definitions.. Recognition process. Recognition process relates input signal to the stored concepts about the object.
Advisor: Prof. Tony Jebara
Facial Feature Detection
Multiclass object recognition
Age and Gender Classification using Modulation Cepstrum Jitendra Ajmera (presented by Christian Müller) Speaker Odyssey 2008.
This week: overview on pattern recognition (related to machine learning)
CSSE463: Image Recognition Day 27 This week This week Last night: k-means lab due. Last night: k-means lab due. Today: Classification by “boosting” Today:
An Example of Course Project Face Identification.
Detecting Pedestrians Using Patterns of Motion and Appearance Paul Viola Microsoft Research Irfan Ullah Dept. of Info. and Comm. Engr. Myongji University.
Support Vector Machines Mei-Chen Yeh 04/20/2010. The Classification Problem Label instances, usually represented by feature vectors, into one of the predefined.
Support Vector Machines Reading: Ben-Hur and Weston, “A User’s Guide to Support Vector Machines” (linked from class web page)
Classifiers Given a feature representation for images, how do we learn a model for distinguishing features from different classes? Zebra Non-zebra Decision.
Object Recognition in Images Slides originally created by Bernd Heisele.
Spam Detection Ethan Grefe December 13, 2013.
Face Detection Using Large Margin Classifiers Ming-Hsuan Yang Dan Roth Narendra Ahuja Presented by Kiang “Sean” Zhou Beckman Institute University of Illinois.
Real-Time Detection, Alignment and Recognition of Human Faces Rogerio Schmidt Feris Changbo Hu Matthew Turk Pattern Recognition Project June 12, 2003.
Advanced Analytics on Hadoop Spring 2014 WPI, Mohamed Eltabakh 1.
Ohad Hageby IDC Support Vector Machines & Kernel Machines IP Seminar 2008 IDC Herzliya.
CS 1699: Intro to Computer Vision Support Vector Machines Prof. Adriana Kovashka University of Pittsburgh October 29, 2015.
The Viola/Jones Face Detector A “paradigmatic” method for real-time object detection Training is slow, but detection is very fast Key ideas Integral images.
Classification (slides adapted from Rob Schapire) Eran Segal Weizmann Institute.
CSSE463: Image Recognition Day 14 Lab due Weds, 3:25. Lab due Weds, 3:25. My solutions assume that you don't threshold the shapes.ppt image. My solutions.
University of Texas at Austin Machine Learning Group Department of Computer Sciences University of Texas at Austin Support Vector Machines.
ACADS-SVMConclusions Introduction CMU-MMAC Unsupervised and weakly-supervised discovery of events in video (and audio) Fernando De la Torre.
Face Image-Based Gender Recognition Using Complex-Valued Neural Network Instructor :Dr. Dong-Chul Kim Indrani Gorripati.
Speaker Change Detection using Support Vector Machines V.Kartik, D.Srikrishna Satish and C.Chandra Sekhar Speech and Vision Laboratory Department of Computer.
Weka. Weka A Java-based machine vlearning tool Implements numerous classifiers and other ML algorithms Uses a common.
Computer Vision Spring ,-685 Instructor: S. Narasimhan WH 5409 T-R 10:30am – 11:50am Lecture #23.
Notes on HW 1 grading I gave full credit as long as you gave a description, confusion matrix, and working code Many people’s descriptions were quite short.
9.913 Pattern Recognition for Vision Class9 - Object Detection and Recognition Bernd Heisele.
6.S093 Visual Recognition through Machine Learning Competition Image by kirkh.deviantart.com Joseph Lim and Aditya Khosla Acknowledgment: Many slides from.
CSSE463: Image Recognition Day 14 Lab due Weds. Lab due Weds. These solutions assume that you don't threshold the shapes.ppt image: Shape1: elongation.
Face detection Many slides adapted from P. Viola.
Learning by Loss Minimization. Machine learning: Learn a Function from Examples Function: Examples: – Supervised: – Unsupervised: – Semisuprvised:
1 Kernel Machines A relatively new learning methodology (1992) derived from statistical learning theory. Became famous when it gave accuracy comparable.
Support Vector Machines Part 2. Recap of SVM algorithm Given training set S = {(x 1, y 1 ), (x 2, y 2 ),..., (x m, y m ) | (x i, y i )   n  {+1, -1}
Performance of Computer Vision
Brian Whitman Paris Smaragdis MIT Media Lab
Brief Review of Recognition + Context
The following slides are taken from:
Face Detection Gender Recognition 1 1 (19) 1 (1)
Support vector machine-based text detection in digital video
Supervised machine learning: creating a model
Presentation transcript:

SVMs for (x) Recognition (From Moghaddam / Yang’s “Gender Classification with SVMs”) Brian Whitman

“Commodity Intelligence” ‘Wow factor’ important Collaborative filtering ‘Simple’ tasks sometimes the most useful An SVM embedded evaluator… Cameras with ‘common sense’

Why SVM for feature detection? Quick evaluation model Machines (SVs) are easily stored and small

Experiment: Gender ID Using MITFaces dataset ~7500 faces with varying genders, races, ages, expressions, ‘extras’ All aligned 160x160 with left eye at 80,80 Face content is usually only 80x40

MITFaces examples

Representation? Simple pixel values Why?

Sample size Maintain ‘ground rule’ of ML Dimensions < Examples*2 At 3200 dims (80x40), this is hard Training parameters (maximum lagrangians, kernel width) help We use 80x40 and 40x20 in our examples

Training stage Choose 3200 random adult faces for training and 3200 random faces for testing Extract 80x40 ‘face window’ from each face and treat the 3200 doubles (0..1) as a training example Train SVM on pixel values of the train set (dual p4 xeon linux 2ghz minutes)

Testing Stage Take the other 3200 face vectors and present them to the learned SVM If class > 0, male, < 0, female. Confidence: some linear combination of # of support vectors and magnitude of result Had no problem doing this at 10hz on a PIII800 with tons running

In-class face gender results 80x40; C=100, aux=100 93% of faces classified correctly 95% male 90% female 40x20; C=100, aux=10 97% 98% male 95% female

Next step: Realtime Media Lab is where webcams go to die Webcam at 160x120, ‘face region’ to 80x40, downsampled to 40x20. Webcam gets frames at 10hz, we greyscale it and present it to the previously trained SVM Results… mixed

Realtime examples (If the demo crashes)

‘Creepybot’ With better control over alignment Monitors Windows clipboard Same architecture as the Creepycam

Creepybot Examples (If the demo crashes)

Other parameters MITFaces has a great data label set Train an SVM for appearance of each descriptor: Race Age Gender Expression Moustache

Per-class results (40x20, etc…) “Adult or not” Overall: 94% (Not adult: 403/516) (78%) (Adult): 2605/2684) (97%)

Per-class results… “Smiling or not” Overall: 88% (Not smiling: 1354/1520) (89%) (Smiling: 1450 / 1672) (87%)

Per-class results “Serious or not” Overall: 88% (Not serious: 1517/1712) (89%) (Serious: 1311/1484) (88%)

Could we do better? Representation is lacking But results are surprisingly good For realtime, need auto-alignment / rescaling, or a better representation Could this lead to an invasion of cheap intelligent cameras, each with tacky switches for feature detection and marketing?