Neeraj Kumar, Alexander C. Berg, Peter N. Belumeur, and Shree K. Nayar Presented by Gregory Teodoro.

Slides:



Advertisements
Similar presentations
Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
Advertisements

Multi-Attribute Spaces: Calibration for Attribute Fusion and Similarity Search University of Oxford 5 th December 2012 Walter Scheirer, Neeraj Kumar, Peter.
Zhimin CaoThe Chinese University of Hong Kong Qi YinITCS, Tsinghua University Xiaoou TangShenzhen Institutes of Advanced Technology Chinese Academy of.
Foreground Focus: Finding Meaningful Features in Unlabeled Images Yong Jae Lee and Kristen Grauman University of Texas at Austin.
Decision Tree Approach in Data Mining
On-the-fly Specific Person Retrieval University of Oxford 24 th May 2012 Omkar M. Parkhi, Andrea Vedaldi and Andrew Zisserman.
3 Small Comments Alex Berg Stony Brook University I work on recognition: features – action recognition – alignment – detection – attributes – hierarchical.
1 Machine Learning: Lecture 10 Unsupervised Learning (Based on Chapter 9 of Nilsson, N., Introduction to Machine Learning, 1996)
1 Machine Learning: Lecture 7 Instance-Based Learning (IBL) (Based on Chapter 8 of Mitchell T.., Machine Learning, 1997)
Computer Vision Detecting the existence, pose and position of known objects within an image Michael Horne, Philip Sterne (Supervisor)
Adviser:Ming-Yuan Shieh Student:shun-te chuang SN:M
Tom-vs-Pete Classifiers and Identity- Preserving Alignment for Face Verification Thomas Berg Peter N. Belhumeur Columbia University 1.
Face Recognition and Biometric Systems
Content Based Image Clustering and Image Retrieval Using Multiple Instance Learning Using Multiple Instance Learning Xin Chen Advisor: Chengcui Zhang Department.
HCI Final Project Robust Real Time Face Detection Paul Viola, Michael Jones, Robust Real-Time Face Detetion, International Journal of Computer Vision,
Aki Hecht Seminar in Databases (236826) January 2009
 Image Search Engine Results now  Focus on GIS image registration  The Technique and its advantages  Internal working  Sample Results  Applicable.
Comparison and Combination of Ear and Face Images in Appearance-Based Biometrics IEEE Trans on PAMI, VOL. 25, NO.9, 2003 Kyong Chang, Kevin W. Bowyer,
Face Processing System Presented by: Harvest Jang Group meeting Fall 2002.
TEAM-1 JACKIE ABBAZIO SASHA PEREZ DENISE SILVA ROBERT TESORIERO Face Recognition Systems.
1/16 Final project: Web Page Classification By: Xiaodong Wang Yanhua Wang Haitang Wang University of Cincinnati.
FACE DETECTION AND RECOGNITION By: Paranjith Singh Lohiya Ravi Babu Lavu.
Facial Recognition CSE 391 Kris Lord.
Face Recognition Using Neural Networks Presented By: Hadis Mohseni Leila Taghavi Atefeh Mirsafian.
Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION.
A Generic Approach for Image Classification Based on Decision Tree Ensembles and Local Sub-windows Raphaël Marée, Pierre Geurts, Justus Piater, Louis Wehenkel.
AdvisorStudent Dr. Jia Li Shaojun Liu Dept. of Computer Science and Engineering, Oakland University 3D Shape Classification Using Conformal Mapping In.
Dimensionality Reduction: Principal Components Analysis Optional Reading: Smith, A Tutorial on Principal Components Analysis (linked to class webpage)
Slide Image Retrieval: A Preliminary Study Guo Min Liew and Min-Yen Kan National University of Singapore Web IR / NLP Group (WING)
Processing of large document collections Part 2 (Text categorization) Helena Ahonen-Myka Spring 2006.
“Hello! My name is... Buffy” Automatic Naming of Characters in TV Video Mark Everingham, Josef Sivic and Andrew Zisserman Arun Shyam.
Machine Learning CSE 681 CH2 - Supervised Learning.
K. Selçuk Candan, Maria Luisa Sapino Xiaolan Wang, Rosaria Rossini
Classifying Images with Visual/Textual Cues By Steven Kappes and Yan Cao.
Object Recognition in Images Slides originally created by Bernd Heisele.
Automatic Image Annotation by Using Concept-Sensitive Salient Objects for Image Content Representation Jianping Fan, Yuli Gao, Hangzai Luo, Guangyou Xu.
ECE738 Advanced Image Processing Face Detection IEEE Trans. PAMI, July 1997.
Face Recognition: An Introduction
Mining Binary Constraints in Feature Models: A Classification-based Approach Yi Li.
School of Engineering and Computer Science Victoria University of Wellington Copyright: Peter Andreae, VUW Image Recognition COMP # 18.
Adaptive Rigid Multi-region Selection for 3D face recognition K. Chang, K. Bowyer, P. Flynn Paper presentation Kin-chung (Ryan) Wong 2006/7/27.
2005/12/021 Fast Image Retrieval Using Low Frequency DCT Coefficients Dept. of Computer Engineering Tatung University Presenter: Yo-Ping Huang ( 黃有評 )
Gang WangDerek HoiemDavid Forsyth. INTRODUCTION APROACH (implement detail) EXPERIMENTS CONCLUSION.
Categorization by Learning and Combing Object Parts B. Heisele, T. Serre, M. Pontil, T. Vetter, T. Poggio. Presented by Manish Jethwa.
VIP: Finding Important People in Images Clint Solomon Mathialagan Andrew C. Gallagher Dhruv Batra CVPR
Support Vector Machines and Gene Function Prediction Brown et al PNAS. CS 466 Saurabh Sinha.
Face Image-Based Gender Recognition Using Complex-Valued Neural Network Instructor :Dr. Dong-Chul Kim Indrani Gorripati.
GENDER AND AGE RECOGNITION FOR VIDEO ANALYTICS SOLUTION PRESENTED BY: SUBHASH REDDY JOLAPURAM.
Face detection Behold a state-of-the-art face detector! (Courtesy Boris Babenko)Boris Babenko slides adapted from Svetlana Lazebnik.
1 Some Guidelines for Good Research Dr Leow Wee Kheng Dept. of Computer Science.
Classification Course web page: vision.cis.udel.edu/~cv May 14, 2003  Lecture 34.
MACHINE LEARNING 7. Dimensionality Reduction. Dimensionality of input Based on E Alpaydın 2004 Introduction to Machine Learning © The MIT Press (V1.1)
Software Quality Assurance and Testing Fazal Rehman Shamil.
Learning Photographic Global Tonal Adjustment with a Database of Input / Output Image Pairs.
Identifying “Best Bet” Web Search Results by Mining Past User Behavior Author: Eugene Agichtein, Zijian Zheng (Microsoft Research) Source: KDD2006 Reporter:
 Effective Multi-Label Active Learning for Text Classification Bishan yang, Juan-Tao Sun, Tengjiao Wang, Zheng Chen KDD’ 09 Supervisor: Koh Jia-Ling Presenter:
Linear Models & Clustering Presented by Kwak, Nam-ju 1.
Evaluation of Gender Classification Methods with Automatically Detected and Aligned Faces Speaker: Po-Kai Shen Advisor: Tsai-Rong Chang Date: 2010/6/14.
High resolution product by SVM. L’Aquila experience and prospects for the validation site R. Anniballe DIET- Sapienza University of Rome.
Deformation Modeling for Robust 3D Face Matching Xioguang Lu and Anil K. Jain Dept. of Computer Science & Engineering Michigan State University.
Deeply learned face representations are sparse, selective, and robust
PRESENTED BY Yang Jiao Timo Ahonen, Matti Pietikainen
Can Computer Algorithms Guess Your Age and Gender?
Hybrid Features based Gender Classification
Thesis Advisor : Prof C.V. Jawahar
State-of-the-art face recognition systems
Deep Face Recognition Omkar M. Parkhi Andrea Vedaldi Andrew Zisserman
Attributes and Simile Classifiers for Face Verification
Categorization by Learning and Combing Object Parts
Domingo Mery Department of Computer Science
Presentation transcript:

Neeraj Kumar, Alexander C. Berg, Peter N. Belumeur, and Shree K. Nayar Presented by Gregory Teodoro

 Attribute Classification ◦ Early research focused on gender and ethnicity.  Done on small datasets  Use of linear discriminate analysis for simple attributes such as glasses.  methods used to characterize or separate two or more classes of objects or events through differences.  “Face-prints” training was used in Support Vector Machines to determine gender.  Use of simple-pixel comparison operators.

 Why use Attribute Classification ◦ Faces has a well-established and consistent reference frame for image alignment ◦ Differentiating like objects is conceptually simple  In Paper Example : Comparing two cars of the same model could or could not be considered the same object; two same faces however are the same object. ◦ A shared pool of attributes applicable to all faces.  Gender, Race, Hair Color, Moustache, Eyewear, Curly, Bangs, Eyebrow Bushiness, and so on…

 Older methods used a Euclidean Distance between pairs of images using Component Analysis; later adding in linear discriminate analysis. ◦ Algorithms worked well, but only in controlled environments  Pose, angel, lighting and expression caused issues in recognizing the face. ◦ Does not work very well with “Labeled Faces in the Wild (LFW) benchmarks.  Other methods used 2D alignment strategies, and applied them to the LFW benchmark set, aligning all faces to each other or pairs considered to be similar. ◦ This was computationally expensive. ◦ Paper attempts to find a far better solution and algorithm that does not involve matching points.  Paper suggests a new method, using attribute and identity labels to describe an image

 Images were collected off the internet through a large number of photo-sharing sites, search engines, and the Mturk.  Downloaded images are ran through the OKAO Face Detector which extracts faces, pose angles, and locations of points of interest. ◦ Two corners of each eye and the mouth corners.  Points are used to align the face and in image transformation.  End result is the largest collection of “real-world” faces; faces collected in a non-controlled environment. ◦ The Columbia Face Database

 Images labeled using the Amazon Mechanic Turk (Mturk) service. ◦ A form of crowd-sourcing, each image is labeled manually by a group of three people; only labels where all three people agreed were used.  Total collection of 145,000 verified positive labels.  Content-Based Image Retrieval System ◦ Difference in goal from most CBIR systems  Most try to find objects similar to another object  This system tries to find an object fitting a text query.  In Paper Example : “Asian Man Smiling With Glasses”

 Attributes collected by this method are not binary. ◦ Thickness of eyebrows is not a “Have” or “Have not” situation. But rather a continuous attribute. “How thick.”  Visual attributes far more varied than names and specific attributes; providing more possible description overall. ◦ Black, Asian, Male, Female are specific named attributes. eyebrow bushiness, skin shine, and age are visual attributes.  FaceTracer is the subset of the Columbia Face Database, containing these attribute labels. There are 5,000 labels.  PubFig is the second dataset, of 58,797 images of 200 individuals in a variety of poses and environments.

 A set of sample images and their attributes.

 Attributes are thought of as a function a[i]; mapping the images I to real values a[i]. ◦ Positive values indicted strength of the ith attribute, and negative values indicate absence.  Second form attribute called “Similes” ◦ Example : A person has “eyes like Penelope Cruz’s”.  Forms a simile function S[cruz][eyes]  Learning attributes or simile classifiers are as simple as fitting a function to a set of prelabeled training data. ◦ Data must be then regularized; with bias towards more commonly observed features.

 Faces are aligned and transformed using an affine transformation ◦ Easy to do thanks to eyes, mouth, etc.  The face is then split into 10 regions, corresponding to feature areas, such as nose, mouth, eyebrows, forehead, and so on. ◦ Regions are defined manually, but only once. ◦ Division of the face this way takes advantage of the common geometry of human faces; while still allowing for differences.  Robust to small errors in alignment. ◦ Extracted values are normalized to lower the effect of lighting and generalize the images.

 A sample face discovered and split into regions of interest.

 A sample simile comparison, and more region details.

 Best features for classification chosen automatically from a number of features. ◦ These are used to train the final attribute and simile classifiers  Classifiers (C[i]) are built using a supervised learning approach. ◦ Trained against a set of labeled images for each attribute, in positive and negative. ◦ This is iterated throughout the dataset and the different classifiers. ◦ Classifiers chosen based on cross-validation accuracy performance.  Features continually added until accuracy for tests stops improving.  For performance, the lowest-scoring 70% of classification features are dropped to a minimum of 10 features.

 Results of Gender and Smiling Detection. (Above.) Results of Classifiers and their cross-validation values. (Right.)

 Are these two faces of the same person? ◦ Small changes in pose, expression, and lighting can cause false negatives.  Two images I[1] and I[2] show the same person. ◦ Verification Classifier V compares the attributes of C[I[1]] and C[I[2]], returning v(I[1],I[2])  These vectors are the result of concatenating the results of n attributes.  Assumptions made ◦ C[i] for I[1] and I[2] should be similar if they are the same, and different otherwise. ◦ Classifier Values are raw outputs of binary classifiers, thus the sign of the value return is important.

 Sample of face verification.

 Let a[i] and b[i] be the outputs of the ith trait classifier for each face. ◦ A large value must be creative that is positive or negative depending on if this is the same individual.  The absolute value of a[i] – b[i] nets us the similarity results, and the product a[i]b[i] gives us the sign. ◦ Thus…

 The concatenation of this for all n attributes/similes forms the input to the verification classifier. V.  Training V requires a combination of positive and negative examples. ◦ The classification function was trained using libsvm.

 Accuracy rating hovers around 85% on average, slightly below but comparable to the current state-of-the-art method. (86.83%)  When compared to human-based verification, versus machine-based verification; human- based wins out by a large margin. ◦ Algorithm when tested against the LFW had an accuracy of 78.65%, compared to average human accuracy which is 99.20%  Testing was done by pulling a subset of 20,000 images of 140 people from the LWF, and creating mutually disjointed sets of 14 individuals.

 Completely new direction of face verification and performances comparable to state-of- the-art algorithms already.  Further improvements can be made by using ◦ more attributes ◦ improving the training process ◦ combining attributes and simile classifiers with low level image cues.  Questions remaining on how to apply attributes to domains other than faces. (Cars, houses, animals, etc.)