EE368 Face Detection Project Angi Chau, Ezinne Oji, Jeff Walters 28 May, 2003.

Slides:



Advertisements
Similar presentations
Image Segmentation Image segmentation (segmentace obrazu) –division or separation of the image into segments (connected regions) of similar properties.
Advertisements

Lecture 5 Template matching
EE 7730 Image Segmentation.
HMM-BASED PATTERN DETECTION. Outline  Markov Process  Hidden Markov Models Elements Basic Problems Evaluation Optimization Training Implementation 2-D.
Automatic Face Recognition Using Color Based Segmentation and Intelligent Energy Detection Michael Padilla and Zihong Fan Group 16 EE368, Spring
Smart Traveller with Visual Translator. What is Smart Traveller? Mobile Device which is convenience for a traveller to carry Mobile Device which is convenience.
Smart Traveller with Visual Translator for OCR and Face Recognition LYU0203 FYP.
Hazırlayan NEURAL NETWORKS Radial Basis Function Networks I PROF. DR. YUSUF OYSAL.
Face Processing System Presented by: Harvest Jang Group meeting Fall 2002.
Thresholding Thresholding is usually the first step in any segmentation approach We have talked about simple single value thresholding already Single value.
A Brief Survey on Face Recognition Systems Amir Omidvarnia March 2007.
Face Detection and Neural Networks Todd Wittman Math 8600: Image Analysis Prof. Jackie Shen December 2001.
Facial Recognition CSE 391 Kris Lord.
ICBV Course Final Project Arik Krol Aviad Pinkovezky.
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.
November 25, 2014Computer Vision Lecture 20: Object Recognition IV 1 Creating Data Representations The problem with some data representations is that the.
嵌入式視覺 Pattern Recognition for Embedded Vision Template matching Statistical / Structural Pattern Recognition Neural networks.
1 TEMPLATE MATCHING  The Goal: Given a set of reference patterns known as TEMPLATES, find to which one an unknown pattern matches best. That is, each.
Automated Face Detection Peter Brende David Black-Schaffer Veni Bourakov.
Joon Hyung Shim, Jinkyu Yang, and Inseong Kim
A Face processing system Based on Committee Machine: The Approach and Experimental Results Presented by: Harvest Jang 29 Jan 2003.
CS654: Digital Image Analysis
CSSE463: Image Recognition Day 11 Lab 4 (shape) tomorrow: feel free to start in advance Lab 4 (shape) tomorrow: feel free to start in advance Test Monday.
Computer Graphics and Image Processing (CIS-601).
COMP322/S2000/L171 Robot Vision System Major Phases in Robot Vision Systems: A. Data (image) acquisition –Illumination, i.e. lighting consideration –Lenses,
Eye regions localization Balázs Harangi – University of Debrecen Ciprian Pop – Technical University of Cluj-Napoca László Kovács – University of Debrecen.
Chap 7 Image Segmentation. Edge-Based Segmentation The edge information is used to determine boundaries of objects Pixel-based direct classification methods.
Kylie Gorman WEEK 1-2 REVIEW. CONVERTING AN IMAGE FROM RGB TO HSV AND DISPLAY CHANNELS.
Probability and Statistics in Vision. Probability Objects not all the sameObjects not all the same – Many possible shapes for people, cars, … – Skin has.
CSSE463: Image Recognition Day 11 Due: Due: Written assignment 1 tomorrow, 4:00 pm Written assignment 1 tomorrow, 4:00 pm Start thinking about term project.
Face Detection and Gender Recognition EE368 Project Report Michael Bax Chunlei Liu Ping Li 28 May 2003.
Visual Tracking by Cluster Analysis Arthur Pece Department of Computer Science University of Copenhagen
Face Detection Using Color Thresholding and Eigenimage Template Matching Diederik Marius Sumita Pennathur Klint Rose.
Thresholding Foundation:. Thresholding In A: light objects in dark background To extract the objects: –Select a T that separates the objects from the.
Laboratory of Image Processing Pier Luigi Mazzeo July 25, 2014.
EE368: Digital Image Processing Bernd Girod Leahy, p.1/15 Face Detection on Similar Color Images Scott Leahy EE368, Stanford University May 30, 2003.
SUMMERY 1. VOLUMETRIC FEATURES FOR EVENT DETECTION IN VIDEO correlate spatio-temporal shapes to video clips that have been automatically segmented we.
1 Review and Summary We have covered a LOT of material, spending more time and more detail on 2D image segmentation and analysis, but hopefully giving.
Color Image Segmentation Mentor : Dr. Rajeev Srivastava Students: Achit Kumar Ojha Aseem Kumar Akshay Tyagi.
1 Kernel Machines A relatively new learning methodology (1992) derived from statistical learning theory. Became famous when it gave accuracy comparable.
Face Detection – EE368 Group 10 May 30, Face Detection EE 368 Group 10 Waqar Mohsin Noman Ahmed Chung-Tse Mar.
Face Detection In Color Images Wenmiao Lu Shaohua Sun Group 3 EE368 Project.
Content Based Coding of Face Images
EE368 Final Project Spring 2003
IMAGE PROCESSING Tadas Rimavičius.
Introduction to Skin and Face Detection
Face Detection EE368 Final Project Group 14 Ping Hsin Lee
A Personal Tour of Machine Learning and Its Applications
Data Mining, Neural Network and Genetic Programming
CSSE463: Image Recognition Day 21
CSSE463: Image Recognition Day 11
Computer Vision Lecture 12: Image Segmentation II
Scott Tan Boonping Lau Chun Hui Weng
Group 1: Gary Chern Paul Gurney Jared Starman
Image Segmentation Techniques
Statistical Approach to a Color-based Face Detection Algorithm
CSSE463: Image Recognition Day 11
Fall 2012 Longin Jan Latecki
CSSE463: Image Recognition Day 23
Segmentation of Images By Color
Introduction to Pattern Recognition
Overview Accomplishments Automatic Queen selection Side by Side Tracks
Midterm Exam Closed book, notes, computer Similar to test 1 in format:
Tracking the Eyes using a Webcam
Midterm Exam Closed book, notes, computer Similar to test 1 in format:
CSSE463: Image Recognition Day 11
CSSE463: Image Recognition Day 11
Week 7 REU Nolan Warner.
Presentation transcript:

EE368 Face Detection Project Angi Chau, Ezinne Oji, Jeff Walters 28 May, 2003

High-Level System Design Face Color Detection Region of Interest Isolation Final Decison

Skin Color Detection: Neural Network TRAINING Stochastic Backpropagation Training patterns pre- whitened. Learning rate, , decreased with each training epoch. Train on equal number of skin and non-skin pixels. Training takes 10 minutes. RUNNING Extremely Efficient –All image pixels can be processed in under 1s. NETWORK TOPOLOGY AND COLORSPACE CHOICES Choose number of hidden units Pixel color can be expressed in multiple colorspaces –RGB Lab, XYZ, and HSV –RGB provided fewest false positives

Isolate Face Shapes: Convolving with Mask Resulting image from neural net had regions of interests that were not true faces. The unique oval-shape true faces was used. To isolate most probable regions of interest, the test image is convolved with an oval mask.

Narrowing Possible Face Locations Increases speed of detection algorithm. Test images showed that the faces were usually clustered. We risk eliminating true faces, but we reject more false positives.

Split Multi-Face Images: k-Means Clustering Regions may contain more than one face. Estimate number of faces using the Distance Transform –Use this estimate to initialize k. Feature vectors are (x,y) locations of each pixel in the region. Assign each pixel to one of k new regions.

Results on Training Images System runtime under 10s on average Simplest algorithm actually worked best! MissesRepeatsFalse Pos Image 1200 Image 2233 Image 3101 Image 4300 Image 5111 Image 6200 Image 7310

Problems Encountered Differences amongst colorspaces –e.g., Lab misidentifies red shirts as skin. –Final implementation used RGB neural net only. System parameters –Threshold for finding peaks during face color detection. –Aggressiveness of the k-means region breakup. –Finding the optimal set of parameters is a hard problem.

Failed Approaches Adaptive thresholding for face color detection. Morphological operations to clean up color segmentation results. Eigenfaces Template matching –Average face –Average eyes –Average “eye-frames” –Difficult to interpret correlation results.