Face Detection using the Spectral Histogram representation By: Christopher Waring, Xiuwen Liu Department of Computer Science Florida State University Presented.

Slides:



Advertisements
Similar presentations
Applications of one-class classification
Advertisements

Bayesian Belief Propagation
Statistical Learning of Multi-View Face Detection
CSCE643: Computer Vision Bayesian Tracking & Particle Filtering Jinxiang Chai Some slides from Stephen Roth.
QR Code Recognition Based On Image Processing
Object Detection Using Semi- Naïve Bayes to Model Sparse Structure Henry Schneiderman Robotics Institute Carnegie Mellon University.
Detecting Faces in Images: A Survey
Computer Vision for Human-Computer InteractionResearch Group, Universität Karlsruhe (TH) cv:hci Dr. Edgar Seemann 1 Computer Vision: Histograms of Oriented.
Recognition by finding patterns
Performance Evaluation Measures for Face Detection Algorithms Prag Sharma, Richard B. Reilly DSP Research Group, Department of Electronic and Electrical.
AdaBoost & Its Applications
Face detection Many slides adapted from P. Viola.
1 Rotation Invariant Face Detection Using Neural Network Lecturers: Mehdi Dehghani - Mahdy Bashary Supervisor: Dr. Bagheri Shouraki Spring 2007.
The Viola/Jones Face Detector (2001)
Lecture 5 Template matching
Patch Descriptors CSE P 576 Larry Zitnick
1 Learning to Detect Objects in Images via a Sparse, Part-Based Representation S. Agarwal, A. Awan and D. Roth IEEE Transactions on Pattern Analysis and.
吳家宇 吳明翰 Face Detection Based on Template Matching and 2DPCA Algorithm 2009/01/14.
Face detection and recognition Many slides adapted from K. Grauman and D. Lowe.
Primal Sketch Integrating Structure and Texture Ying Nian Wu UCLA Department of Statistics Keck Meeting April 28, 2006 Guo, Zhu, Wu (ICCV, 2003; GMBV,
Classifiers for Recognition Reading: Chapter 22 (skip 22.3) Slide credits for this chapter: Frank Dellaert, Forsyth & Ponce, Paul Viola, Christopher Rasmussen.
Classification and application in Remote Sensing.
Robust Real-Time Object Detection Paul Viola & Michael Jones.
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,
Smart Traveller with Visual Translator for OCR and Face Recognition LYU0203 FYP.
Face Processing System Presented by: Harvest Jang Group meeting Fall 2002.
Object Detection Using the Statistics of Parts Henry Schneiderman Takeo Kanade Presented by : Sameer Shirdhonkar December 11, 2003.
Understanding Faces Computational Photography
Foundations of Computer Vision Rapid object / face detection using a Boosted Cascade of Simple features Presented by Christos Stoilas Rapid object / face.
Face Detection CSE 576. Face detection State-of-the-art face detection demo (Courtesy Boris Babenko)Boris Babenko.
FACE DETECTION AND RECOGNITION By: Paranjith Singh Lohiya Ravi Babu Lavu.
Face Recognition Using Neural Networks Presented By: Hadis Mohseni Leila Taghavi Atefeh Mirsafian.
Overview Introduction to local features
Tal Mor  Create an automatic system that given an image of a room and a color, will color the room walls  Maintaining the original texture.
Multiclass object recognition
Mutual Information-based Stereo Matching Combined with SIFT Descriptor in Log-chromaticity Color Space Yong Seok Heo, Kyoung Mu Lee, and Sang Uk Lee.
EADS DS / SDC LTIS Page 1 7 th CNES/DLR Workshop on Information Extraction and Scene Understanding for Meter Resolution Image – 29/03/07 - Oberpfaffenhofen.
Overview Harris interest points Comparing interest points (SSD, ZNCC, SIFT) Scale & affine invariant interest points Evaluation and comparison of different.
Rotation Invariant Neural-Network Based Face Detection
Lecture 29: Face Detection Revisited CS4670 / 5670: Computer Vision Noah Snavely.
Face detection Slides adapted Grauman & Liebe’s tutorial
Visual Object Recognition
Object Recognition in Images Slides originally created by Bernd Heisele.
CS654: Digital Image Analysis Lecture 25: Hough Transform Slide credits: Guillermo Sapiro, Mubarak Shah, Derek Hoiem.
Face Detection Using Large Margin Classifiers Ming-Hsuan Yang Dan Roth Narendra Ahuja Presented by Kiang “Sean” Zhou Beckman Institute University of Illinois.
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.
Timo Ahonen, Abdenour Hadid, and Matti Pietikainen
PRESENTATION REU IN COMPUTER VISION 2014 AMARI LEWIS CRCV UNIVERSITY OF CENTRAL FLORIDA.
Face Detection Using Neural Network By Kamaljeet Verma ( ) Akshay Ukey ( )
CS332 Visual Processing Department of Computer Science Wellesley College High-Level Vision Face Recognition I.
Computer Vision Lecture 7 Classifiers. Computer Vision, Lecture 6 Oleh Tretiak © 2005Slide 1 This Lecture Bayesian decision theory (22.1, 22.2) –General.
CSCI 631 – Foundations of Computer Vision March 15, 2016 Ashwini Imran Image Stitching.
WLD: A Robust Local Image Descriptor Jie Chen, Shiguang Shan, Chu He, Guoying Zhao, Matti Pietikäinen, Xilin Chen, Wen Gao 报告人:蒲薇榄.
AdaBoost Algorithm and its Application on Object Detection Fayin Li.
Cascade for Fast Detection
Summary of “Efficient Deep Learning for Stereo Matching”
Face Detection EE368 Final Project Group 14 Ping Hsin Lee
Scale Invariant Feature Transform (SIFT)
Announcements Final is Thursday, March 20, 10:30-12:20pm
Lit part of blue dress and shadowed part of white dress are the same color
Recognition using Nearest Neighbor (or kNN)
Paper Presentation: Shape and Matching
Feature description and matching
Outline Multilinear Analysis
A Tutorial on HOG Human Detection
Outline S. C. Zhu, X. Liu, and Y. Wu, “Exploring Texture Ensembles by Efficient Markov Chain Monte Carlo”, IEEE Transactions On Pattern Analysis And Machine.
Learning to Detect Faces Rapidly and Robustly
Image and Video Processing
Feature descriptors and matching
Presented by Xu Miao April 20, 2005
Presentation transcript:

Face Detection using the Spectral Histogram representation By: Christopher Waring, Xiuwen Liu Department of Computer Science Florida State University Presented by: Tal Blum

Sources The presentation is based on a few resources by the authors: –Exploration of the Spectral Histogram for Face Detection – M.Sc thesis by Christopher Waring (2002) –Spectral Histogram Based Face Detection – IEEE (2003) –Rotation Invariant Face Detection Using Spectral Histograms & SVM – CVPR submission –Independent Spectral Representation of images for Recognition – Optical Society of America (2003)

Overview Spectral Histogram –Overview of Gibbs Sampling + Simulated annealing Method for Lighting Normalization Data used 3 Algorithms –SH + Neural Networks –SH + SVM –Rotation Invariant SH +SVM Experimental Results Conclusions & Discussions

Two Approaches to Object Detection Curse of dimensionality –Features should be: (Vasconcelos) Independent have low Bayes Error 2 main Approaches in Object Detection: –Complicated Features with many interactions Require many data points Use syntactic variations that mimic the real variations Estimation Error might be high Assuming Model or Parameter structure –Small set of features or small number of values This is the case for Spectral Histograms The Bayes Error might be high (Vasconcelos) Estimation Error is low

Why Spectral Histograms? Translation Invariant –Therefore insensitive to incorrect alignment. (surprisingly) seem to be able to separate Objects from Non-Objects well. Good performance with a very small feature set. Good performance with a large rotation invariance. Don’t rely at all on any global spatial information Combining of variant and invariant features Will play a more Important role

What is Spectral Histogram

Types of Filters 3 types of filters: –Gradient Filters –Gabor Filters –Laplasian of Gaussians Filters The exact composition of the filters is different for each algorithm.

Gibbs Sampling+ Simulated Annealing We want to sample from We can use the induced Gibbs Distribution Algorithm: Repeat –Randomly pick a location –Change the pixel value according to q Until for every filter

Face Synthesis using Gibbs Sampling + Simulated Annealing A measure of the quality of the Representation

Comparison - PCA vs. Spectral Histogram Original ImageReconstructed Images

Reconstruction vs. Sampling Reconstructionsampling

Spectral Histograms of several images

Lighting correction They use a 21x21 sized images Minimal brightness plane of 3x3 is computed from each 7x7 block A 21x21 correction plane is computed by bi-linear interpolation Histogram Normalization is applied

Lighting correction

Detection & Post Processing Detection is don on 3 scaled Gaussian pyramid, each scale down sampled by1.1 detections within 3 pixels are merged A detection is marked as final if it is found at at least two concurrent levels A detection counts as correct if at least half of the face lies within the detection window

Adaptive Threshold

Algorithm I using a Neural Network Neural Network was used as a classifier –Training with back propagation Data Processing –1500 Face images & 8000 Non-Face images –Bootstrapping was used to limit the # non faces (Sung Poggio) leaving 800 Non-Faces Use 8 filters with 80 bins in each

Alg. I - Filter Selection 7 LoG filters with 4 Difference of gradient: Dx Dy Dxx Dyy 70 Gabor filters with: – T = 2,4,6,8,10,12,14 – = 0,40,80,120,160,200,280,320 Selected Filters (8 out of 81) 4 LoG filters with: 3 Difference of Gradiant: Dx Dxx & Dyy 1 Gabor filter with T=2 and

Spectral Histograms of several images

Algorithm I – Results on CMU test set I MethodDetection Rate False Detections Waring & Liu 93.8%94 Yang, Ahuja & Kreigman 93.6%74 Yang, Ahuja & Kreigman 92.3%82 Yang Roth & Ahuja 94.2%84 Rowley, Baluja & Kanade 92.5%862 Schneiderman 93.0%88 Colmenarz & Huang 98.0%12758

Algorithm I – Results on CMU test set II MethodDetection Rate False Detections Waring & Liu 89.4%29 Sung & Poggio Rowley, Baluja & Kanade 90.3%42 Yang, Ahuja & Kreigman 91.5%1 Yang, Ahuja & Kreigman 89.4%3 Schneiderman 91.2%12 Yang Roth & Ahuja 93.6%3

Algorithm II using a SVM SVM instead of a Neural Network They use more filters –34 filters (instead of 7) –359 bins (instead of 80) 4500 randomly rotated Face images & 8000 Non-Face images from before

Algorithm II (SVM) Filters The filters were hand picked Filters: –The Intensity filter –4 Difference of Gradient filters Dx,Dy,Dxx &Dyy –5 LoG filgers –24 gabor filters with Local & Global Constraints Using Histograms as features

Spectral Histograms of several images

Algorithm II (SVM) Results

Old Results

Algorithm III using SVM + rotation invariant features Same features as in Alg. II The Features enable 180 degrees of rotation invariance Rotate the image 180 degrees and switch Histograms achieving 360 degrees invariance

Rotating 180 degrees

Combining the two classifiers

Results Upright test sets

Results Rotated test sets

Rotation Invariation Results

More pictures

Conclusions A system which is rotation & translation invariant Achieves very high accuracy for frontal faces and rotated frontal faces The system is not real time, but is possible to implement convolution in hardware Uses limited amount of data Accuracy as a function of efficiency

Conclusions (2) Faces are identifiable through local spatial dependencies where the global ones can be globally modeled as histograms The problem with spatial methods is the estimation of the parameters The SH representation is independent of classifier choice SVM outperforms Neural Networks The Problems and the Errors of this system are considerably different than of other systems

Conclusions (3) Localization in Space and Scale is not as good as other methods Translation Invariant features can enable a coarser sampling the image Use adaptive thresholding Use several scales to improve performance SH can be used for sampling of objects