Face Recognition Technology


Face recognition

Face Recognition Based on PCA

DCT-ANN Face Identification

Wavelet-ANN Face Recognition

Face Recognition Based on Polar Frequency Features

Face Recognition Based on FisherFaces

Face Recognition Based on Local Features

Face Recognition in Fourier Space

WebCam Face Identification

Face Recognition Based on Overlapping DCT

Face Recognition Based on Statistical Moments

Face Recognition Based on Nonlinear PCA

Face Recognition Based on Hierarchical Dimensionality Reduction

Fusion of Low-Computational Global and Local Features For Face Recognition

SVD-Based Face Recognition

Correlation Filters Face Verification

ICA Face Recognition

3D Face Recognition

Infrared Face Recognition

Octave Face Recognition

PHP Face Recognition

JAVA Face Recognition

LBP Face Recognition System

HMM Face Recognition System

NMF Face Recognition System

Face matching

Face Identification Based on CPD

GA MACE Face Verification

External resources

Advanced Source Code .Com

Neural Networks .It

Genetic Algorithms .It

Iris Recognition .It

Advanced Correlation Filters for Biometric Recognition

Download now Matlab source code
Requirements: Matlab, Matlab Image Processing Toolbox.

Correlation filters have been applied successfully to automatic target recognition (ATR) problems. The most basic correlation filter is the matched spatial filter (MSF), whose impulse response (in 2-D, point spread function) is the flipped version of the reference image. While the MSF performs well at detecting a reference image corrupted by additive white noise, it performs poorly when the reference image appears with distortions (e.g., rotations, scale changes). Thus one MSF will be needed to detect each appearance of an object. Clearly this is computationally unattractive for practical pattern recognition. Hester and Casasent addressed this challenge with the introduction of the synthetic discriminant function (SDF) filter. The SDF filter is a linear combination of MSFs where the combination weights are chosen so that the correlation outputs corresponding to the training images would yield pre-specified values at the origin. These pre-specified peak values are often referred to as peak constraints. The peak values corresponding to the authentics (also called the true class) are typically set to 1, and hence this SDF filter was known as the equal correlation peak (ECP) SDF filter. In principle, a single ECP SDF filter could replace many MSFs. Object recognition is performed by cross-correlating an input image with a synthesized template or filter and processing the resulting correlation output. The correlation output is searched for peaks, and the relative heights of these peaks are used to determine whether the object of interest is present or not. The locations of the peaks indicate the position of the objects.

Face verification is an important tool for authentication of an individual and it can be of significant value in security and e-commerce applications. We have developed an effective application of correlation filters for face verification. The performance of a specific type of correlation filter called the minimum average correlation energy (MACE) filter is evaluated using Facial Expression Database collected at the Advanced Multimedia Processing Lab at Carnegie Mellon University (CMU).

Index Terms: Matlab, source, code, face, identification, authentication, recognition, correlation, filters, filter, mace.

Release 1.0 Date 2010.08.10
Major features:

Face Recognition . It Luigi Rosa mobile +39 3207214179 luigi.rosa@tiscali.it