Correlation Pattern Recognition

Abstract

Correlation is a robust and general technique for pattern recognition and is used in many applications, such as automatic target recognition, biometric recognition and optical character recognition. The design, analysis and use of correlation pattern recognition algorithms requires background information, including linear systems theory, random variables and processes, matrix/vector methods, detection and estimation theory, digital signal processing and optical processing. This 2005 book provides a needed review of this diverse background material and develops the signal processing theory, the pattern recognition metrics, and the practical application know-how from basic premises. It shows both digital and optical implementations. It also contains technology presented by the team that developed it and includes case studies of significant interest, such as face and fingerprint recognition. Suitable for graduate students taking courses in pattern recognition theory, whilst reaching technical levels of interest to the professional practitioner.

Data Association Techniques for Non-Gaussian Measurements

“…By modeling light's behavior with mathematical functions, these functions can be performed on dedicated hardware platforms. One such function is that of optical correlation (Kumar, Mahalanobis, and Juday, 2005). The process is shown in Figure 15.…”

The Optimal ROS-Based Symmetric Phase-Only Filter for Fingerprint Verification

“…Furthermore, the matched filter output around its maximum is so broad that the peak cannot be easily located. The phase-only filter (POF) was proposed to solve such problems [4,5,6]. Consider two N 1 ×N 2 images, f(n 1 , n 2 ) and g(n 1 , n 2 ).…”

“…One way to remove noise for a SPOF is to set some frequencies of the filter to zero [6]. The set of frequencies in which the filter magnitude is non-zero is called the region of support (ROS).…”

“…It measures the noise sensitivity of the filters. To find an optimal ROS for SPOF, it is a natural way to find the region that maximizes the output SNR of the filter [6]. In order to obtain the expression of SNR, we switch back to 1D notation for simplicity.…”

Feature Correlation Filter for Face Recognition

“…Hence, to capture all possible image variations, a huge number of MFs are needed, which is definitely computational and storage impractical [4]. To solve these problems, more sophisticated correlation filter design techniques are proposed in various literatures [5][6] [7]. The advanced correlation filters construct a single filter or template from a set of training images and can be computed analytically and effectively using frequency domain techniques.…”