An Introduction to Face Recognition

Boimetrics oEvolving Approaches to recognizing faces:Eigenface technology Local feature ananlsis oAdvantages/disadvantages oFuture
o

What is Face Recognition?

A set of two task:

Face Identification: Given a face image that belongs to a person in a database, tell whose image it is. Face Verification: Given a face image that might not belong to the database, verify whether it is from the person it is claimed to be in the database.

Importance of Face Recognition

First step in many Human Computer Interaction systems

Expression Recognition Cognitive State/Emotional State Recogntion

First step in many surveillance systems A step towards Automatic Target Recognition(ATR) or generic object detection/recognition Quick way to discover criminals Fake ids

Biometrics

Biometrics-digital analysis using cameras or scanners of biological characteristics such as facial structure , fingerprints and patterns to match profiles to databases of people

Different Approaches

Features:

Features from global appearance

Features from local regions

Principal Component Analysis(PCA)

Local Feature Analysis(LFA)

Similarity Measure

Neural Networks Template Matching

Face Detection: current state

State-of-the-art:

Front-view face detection can be done at >15 frames per second on 320x240 blackand-white images on a 700MHz PC with ~95% accuracy. Detection of faces is faster than detection of edges!

Side view face detection remains to be difficult.

The PCA Approach EigenfaceTechnology

Face Image captured Via cameraand processed using an algorithm based on principles component analysis (PCA) which translates characteristics of a face into a unique set of a numbers( templates) To identify a face ,the program compares its Eigenface characteristics,which are encoded into numbers called template,with those in the database,selecting the faces whose templtes match the target most closely, as shown

Knowledge-Based Methods

Top Top-down approach: Represent a face using a set of human-coded rules Example:

Use these rules to guide the search process

The center part of face has uniform intensity values The difference between the average intensity values of the center part and the upper part is significant A face often appears with two eyes that are symmetric to each other, a nose and a mouth

Knowledge-Based Method:

Level 1 (lowest resolution):

apply the rule the center part of the face has 4 cells with a basically uniform intensity to search for candidates

Level 2: search for eye and mouth features for validation

Knowledge-based Methods: Summary

Pros:

Easy to come up with simple rules Based on the coded rules, facial features in an input image are extracted first, and face candidates are identified Work well for face localization in uncluttered background
Difficult to translate human knowledge into rules precisely: detailed rules fail to detect faces and general rules may find many false positives Difficult to extend this approach to detect faces in different poses: implausible to enumerate all the possible cases

Cons:

Feature-Based Methods

Bottom-up approach: Detect facial features (eyes, nose, mouth, etc) first Facial features: edge, intensity, shape, texture, color, etc Aim to detect invariant features Group features into candidates and verify them

Feature-Based Methods: Summary

Pros: Features are invariant to pose and orientation change Cons: Difficult to locate facial features due to several corruption (illumination, noise, occlusion) Difficult to detect features in complex background

Local Feature Analysis

Local feature analysis considers individual features. These features are the building blocks from which all facial images can be constructed.

Local Feature Analysis

Local feature analysis selects features in each face that differ most from other faces such as, the nose ,eyebrows,mouth and the areas where the curvature of the bones changes.

Local Feature Analysis

For each selection, the computer constructs a face image and compares it with the target face to be identified. New patterns are created A facial image that matches with the target can be constructed.When a match is found, the computer looks in its databasefor a matching pattern of a real person

Performance Issues

From Eigenface Technology to local feature analysis, the problem faced were same: Images with complex backgrounds Poor lightning conditions Recogntion accuracy

Color-Based Face Detector

Pros:

Cons:

Easy to implement Effective and efficient in constrained environment Insensitive to pose, expression, rotation variation Sensitive to environment and lighting change Noisy detection results (body parts, skin-tone line tone line regions)

How the System Worked

Applications of Face Recognition

Multimedia Management Security Smart Cards Surveillance Others

Future Advancement

Biometric system integration services which combine face recogntion software with other biometrics such as voice, fingerprints ,etc components Aperson face will be the private ,secure and convenient password

Current Commercial Products

Visionics Corporation: Jersey City, NJ - peaks and valleys - 80 nodal points, 14-22 needed - golden triangle - faceprint

Viisage Technology: Littleton, MA - 128 archetypes on record - differences/similarities with models on record