Principal Component Analysis using Eigenfaces for face recognition & Viola-Jones method for face detection

WHY SELECT 'PCA based Eigenfaces' method? PCA based Eigenface method is at the most primary level and simplest of efficient face recognition algorithms --- and is therefore a great place for beginners to start learning face recognition! PCA based Eigenfaces method for recognition is as supported by EmguCV library as is Viola-Jones method for detection is So, implementing it in ASP.NET is SIMPLE: Plug-n-Play

IS 'PCA BASED EIGENFACES' METHOD 100% EFFICIENT??? NO, and i mean NO face RECOGNITION algorithm is YET 100% efficient ! yes, it could reach 100% efficiency but NOT ALWAYS! So, NO EXISTING face recognition algorithm is 100% foolproof. PCA based Eigenfaces method is NOT 100% efficient! in fact, on the average, it goes up to 70% to 75% efficiency honestly.

Is this a face or not?

Sketch of a Pattern Recognition Architecture

Image (window)

Feature Extraction

Classification
Feature Vector

Object Identity

Face Detection Algorithm

Lighting Compensation Color Space Transformation

Skin Color Detection

Input Image

Variance-based Segmentation Connected Component & Grouping

Face Localization

Eye/ Mouth Detection Face Boundary Detection Verifying/ Weighting Eyes-Mouth Triangles
Facial Feature Detection

Output Image

Overview :

Viola-Jones Face Detection Algorithm

Viola Jones technique overview Features Integral Images Feature Extraction Weak Classifiers Boosting and classifier evaluation Cascade of boosted classifiers Example Results

Full details available in paper by Viola and Jones, International Journal of Computer Vision, 2004 Some of the following slides were adapted from a presentation by Nathan Faggian

Viola Jones Technique Overview

Three major contributions/phases of the algorithm : Feature extraction Classification using boosting Multi-scale detection algorithm Feature extraction and feature evaluation.
Rectangular features are used, with a new image representation their calculation is very fast.

Classifier training and feature selection using a slight variation of a method called AdaBoost. A combination of simple classifiers is very effective

Features
Four basic types.
They are easy to calculate. The white areas are subtracted from the black ones. A special representation of the sample called the integral image makes feature extraction faster.

Feature Extraction
Features are extracted from sub windows of a sample image.
The base size for a sub window is 24 by 24 pixels. Each of the four feature types are scaled and shifted across all possible combinations

In a 24 pixel by 24 pixel sub window there are ~160,000 possible features to be calculated.

Practical implementation
Details discussed in Viola-Jones paper Training time = weeks (with 5k faces and 9.5k nonfaces)

Final detector has 38 layers in the cascade, 6060 features

700 Mhz processor:
Can process a 384 x 288 image in 0.067 seconds (in 2003 when paper was written)

Comparison of classification accuracy

Recognition with Eigenfaces

Algorithm
1. Process the image database (set of images with labels)
Run PCAcompute eigenfaces Calculate the K coefficients for each image

2. Given a new image (to be recognized) x, calculate K coefficients 3. Detect if x is a face 4. If it is a face, who is it?

Find closest labeled face in database

nearest-neighbor in K-dimensional space