Biometric verification with correlation filters

Using biometrics for subject verification can significantly improve security over that of approaches based on passwords and personal identification numbers, both of which people tend to lose or forget. In biometric verification the system tries to match an input biometric (such as a fingerprint, face image, or iris image) to a stored biometric template. Thus correlation filter techniques are attractive candidates for the matching precision needed in biometric verification. In particular, advanced correlation filters, such as synthetic discriminant function filters, can offer very good matching performance in the presence of variability in these biometric images (e.g., facial expressions, illumination changes, etc.). We investigate the performance of advanced correlation filters for face, fingerprint, and iris biometric verification.     

Modified filter synthetic discriminant functions for improved optical correlator performance

By the filter modulation operator N, the modified filter synthetic discriminant function permits advantageous preprocessing of individual training-set images that are used in a linear combination to construct the filter synthetic discriminant function, which applies a modulation operator M to the synthetic discriminant function. A relaxation algorithm is used to satisfy the equal correlation peaks rule in the correlator output plane. As the filter modulation operators M and N can be given any functional form, the modified filter synthetic discriminant function design proposed is sufficiently general to be described as a unified filter modulation synthetic discriminant function design.     

Distortion-invariant filter for nonoverlapping noise

A new heuristic filter based on the optimum filter for disjoint noise developed by Javidi and Wang [J. Opt. Soc. Am. A 11, 2604 (1995)] is presented. In this new filter a number of optimum filters built from single training images are combined linearly by use of the synthetic discriminant function (SDF) approach into a distortion-invariant filter for disjoint noise. Like the traditional SDF approach, this summation technique makes it possible to control the height of the correlation peak easily, for example, if a uniform filter response is needed. The filter is compared with the distortion-invariant version of the optimum filter on images with low contrast and high levels of nonoverlapping clutter. The new filter shows good results, demonstrating that it is, with very simple heuristic methods, possible to improve the performance of distortion-invariant filters for nonoverlapping noise.     

Implementation of arbitrary real-valued correlation filters for the shadow-casting incoherent correlator

We describe an incoherent correlator, based on the shadow-casting principle, that is able to implement any real-valued linear correlation filter. The correlation filter and the input image are displayed on commercial liquid-crystal television (LCTV) panels. Although it cannot handle high-resolution images, the incoherent correlator is lensless, compact, low cost, and uses a white-light source. A bipolar technique is devised to represent any linear filter, computed from a single reference image or composite, in the correlator. We demonstrate experimentally the efficiency of the design in the case of optimal trade-off (OT) filters and optimal trade-off synthetic discriminant function (OT-SDF) filters.     

Gray-level computer-generated hologram filters for multiple-object correlation

Synthesis of gray-level computer-generated holograms allows for an increase of the information storage capability that is usually achieved with conventional binary filters. This is mainly because more degrees of freedom are available. We propose to profit from this feature by synthesizing complex filters formed by many superimposed holograms, each with a different carrier frequency. We apply these gray-level filters to perform multichannel correlation and in this way enhance the capability of optical correlators to process the information in parallel and simultaneously. First, we analyze the behavior of some performance criteria on the impulse response and on the correlation as a function of the number of holograms that are multiplexed. Then we show the results of two experiments: In the first a composed phase-only filter is used in a multiple-object recognition process. In the second a composed synthetic discriminant function filter is used to implement an object classification by means of a binary code.     

Constrained quadratic correlation filters for target detection

A method for designing and implementing quadratic correlation filters (QCFs) for shift-invariant target detection in imagery is presented. The QCFs are quadratic classifiers that operate directly on the image data without feature extraction or segmentation. In this sense the QCFs retain the main advantages of conventional linear correlation filters while offering significant improvements in other respects. Not only is more processing required for detection of peaks in the outputs of multiple linear filters but choosing the most suitable among them is an error-prone task. All channels in a QCF work together to optimize the same performance metric and to produce a combined output that leads to considerable simplification of the postprocessing scheme. The QCFs that are developed involve hard constraints on the output of the filter. Inasmuch as this design methodology is indicative of the synthetic discriminant function (SDF) approach for linear filters, the filters that we develop here are referred to as quadratic SDFs (QSDFs). Two methods for designing QSDFs are presented, an efficient architecture for achieving them is discussed, and results from the Moving and Stationary Target Acquisition and Recognition synthetic aperture radar data set are presented.     

Performance assessment of the modified-hybrid optical neural network filter

We present in detail the recorded results of the modified-hybrid optical neural network (M-HONN) filter during a full series of tests to examine its robustness and overall performance for object recognition tasks. We test the M-HONN filter for its detectability and peak sharpness with within-class distortion of the input object, its discrimination ability between an in-class and out-of-class object, and its performance with cluttered images of the true-class object. The M-HONN filter is found to exhibit good detectability, an ability to maintain its correlation-peak sharpness throughout the recorded tests, good discrimination ability, and an ability to detect the true-class object within cluttered input images. Additionally we observe the M-HONN filter's performance within the tests in comparison with the constrained-hybrid optical neural network filter for the first three series of tests and the synthetic discriminant function-maximum average correlation height filter for the fourth set of tests.     

Synthetic discriminant function filter employing nonlinear space-domain preprocessing on bandpass-filtered images

Previously [Appl. Opt. 36, p. 9212 (1997)] we examined the performance of the linear and nonlinear preprocessed difference-of-Gaussians filter, and it was shown that this operation results in greater tolerance to in-class variations while maintaining excellent discrimination ability. The introduction of nonlinearity was shown to provide greater robustness to the filter's response to noise and background clutter in the input scene. We incorporate this new operation into the synthesis of a modified synthetic discriminant function filter. The filter is shown to produce sharp peaks, excellent discrimination without the need to include out-of-class objects, and good invariance to out-of-plane rotation over a distortion range of up to 90 degrees . Additionally, the introduction of nonlinearity is shown to provide greater robustness of the filter response to background clutter in the input scene.     

Hybrid digital-optical correlation employing a chirp-encoded simulated-annealing-based rotation-invariant and distortion-tolerant filter

The simulated annealing (SA) algorithm based on entropy optimization is a technique of synthesizing distortion-invariant matched filters capable of discriminating very similar images. The synthesis of rotation-invariant filters using modified SA-based filter equations and their tolerance to distortions are studied. The filters are trained with true class images rotated in-plane at 3 degrees intervals between 0 degrees and 360 degrees . A total of seven filters are required over the whole range for both CCD or thermal images. Optical correlation in a hybrid digital-optical correlator results in an unwanted zero-order dc along with two first-order (+/-1) correlation peaks. A chirp function multiplied with the filter separates out the three peaks to three different planes, and only one peak in focus is captured in a camera. The performance of the modified SA-based filter has been studied in comparison to the conventional SA filter as well as with other filters.     

Rotationally invariant pattern recognition by use of linear and nonlinear cascaded filters

We discuss the merits of using single-layer (linear and nonlinear) and multiple-layer (nonlinear) filters for rotationally invariant and noise-tolerant pattern recognition. The capability of each approach is considered with reference to a two-class, rotation-invariant, character recognition problem. The minimum average correlation energy (MACE) filter is a linear filter that is generally accepted to be optimal for detecting signals that are free from noise. Here it is found that an optimized MACE filter cannot differentiate between the characters E and F in a rotation-invariant manner. We have found, however, that this task is possible when a single optimized linear filter is used to achieve the required response when a nonlinear threshold function is included after the filter. We show that this structure can be cascaded to form a multiple-layer, cascaded filter and that the capability of such a system is enhanced by its increased noise tolerance in the character recognition problem. Finally, we show the capability of a two-layer cascade as a means to detect different species of bacteria in images obtained from a phase-contrast microscope.     

Nonlinear cascaded correlation processes to improve the performances of automatic spatial-frequency-selective filters in pattern recognition

A recognition process consisting of two cascaded correlation stages with a sigmoid nonlinearity applied in the first correlation plane is investigated. The filters are computed to give prespecified central correlation amplitudes in the second correlation plane when inputs are reference images. It is also desired that the second correlation amplitudes with the training images should minimize the cost function of the automatic spatial-frequency selection algorithm to reduce distortion sensitivity and to improve the performance of the filters. Filter computation methods are given, and it is shown why two such correlation processes may improve the correlation performance. Numerical simulations are described and compared with the one-stage correlation system that works with the automatic spatial-frequency selection filter.     

Spectral optimized asymmetric segmented phase-only correlation filter

We suggest a new type of optimized composite filter, i.e., the asymmetric segmented phase-only filter (ASPOF), for improving the effectiveness of a VanderLugt correlator (VLC) when used for face identification. Basically, it consists in merging several reference images after application of a specific spectral optimization method. After segmentation of the spectral filter plane to several areas, each area is assigned to a single winner reference according to a new optimized criterion. The point of the paper is to show that this method offers a significant performance improvement on standard composite filters for face identification. We first briefly revisit composite filters [adapted, phase-only, inverse, compromise optimal, segmented, minimum average correlation energy, optimal trade-off maximum average correlation, and amplitude-modulated phase-only (AMPOF)], which are tools of choice for face recognition based on correlation techniques, and compare their performances with those of the ASPOF. We illustrate some of the drawbacks of current filters for several binary and grayscale image identifications. Next, we describe the optimization steps and introduce the ASPOF that can overcome these technical issues to improve the quality and the reliability of the correlation-based decision. We derive performance measures, i.e., PCE values and receiver operating characteristic curves, to confirm consistency of the results. We numerically find that this filter increases the recognition rate and decreases the false alarm rate. The results show that the discrimination of the ASPOF is comparable to that of the AMPOF, but the ASPOF is more robust than the trade-off maximum average correlation height against rotation and various types of noise sources. Our method has several features that make it amenable to experimental implementation using a VLC.     

Generalization of the Jared and Ennis method of complex transmittance objects for the generation of synthetic discriminant function filters

We present a simple method of constructing synthetic discriminant function filters optimized to take into account the modulation of liquid-crystal devices. This relaxation algorithm, a generalization of the Jared and Ennis method, is an iterative method that includes arbitrary modulations for both scene and filter, extending the problem to the complex plane. Simulated and experimental results obtained in a VanderLugt correlator are presented for a two-class recognition problem. The optimal number of images needed to describe an object in a filter generated in this way is discussed, and the influence of the spatial light modulation resolution on the correlation is studied.     

High-speed pattern-recognition systems using parallel-access optical disks

We discuss the use of parallel-access optical disks for high-speed pattern-recognition systems. Three practical configurations that make use of the unique properties of optical disks are discussed. A practical incoherent disk-based correlator is described, and its performance illustrated by use of both matched filters and computer-generated minimum average correlation energy filters.     

Illumination-tolerant face verification of low-bit-rate JPEG2000 wavelet images with advanced correlation filters for handheld devices

Face recognition on mobile devices, such as personal digital assistants and cell phones, is a big challenge owing to the limited computational resources available to run verifications on the devices themselves. One approach is to transmit the captured face images by use of the cell-phone connection and to run the verification on a remote station. However, owing to limitations in communication bandwidth, it may be necessary to transmit a compressed version of the image. We propose using the image compression standard JPEG2000, which is a wavelet-based compression engine used to compress the face images to low bit rates suitable for transmission over low-bandwidth communication channels. At the receiver end, the face images are reconstructed with a JPEG2000 decoder and are fed into the verification engine. We explore how advanced correlation filters, such as the minimum average correlation energy filter [Appl. Opt. 26, 3633 (1987)] and its variants, perform by using face images captured under different illumination conditions and encoded with different bit rates under the JPEG2000 wavelet-encoding standard. We evaluate the performance of these filters by using illumination variations from the Carnegie Mellon University's Pose, Illumination, and Expression (PIE) face database. We also demonstrate the tolerance of these filters to noisy versions of images with illumination variations.     

Wavelet packet correlation methods in biometrics

We introduce wavelet packet correlation filter classifiers. Correlation filters are traditionally designed in the image domain by minimization of some criterion function of the image training set. Instead, we perform classification in wavelet spaces that have training set representations that provide better solutions to the optimization problem in the filter design. We propose a pruning algorithm to find these wavelet spaces by using a correlation energy cost function, and we describe a match score fusion algorithm for applying the filters trained across the packet tree. The proposed classification algorithm is suitable for any object-recognition task. We present results by implementing a biometric recognition system that uses the NIST 24 fingerprint database, and show that applying correlation filters in the wavelet domain results in considerable improvement of the standard correlation filter algorithm.     

Wavelet-modified maximum average correlation height filter for rotation invariance that uses chirp encoding in a hybrid digital-optical correlator

We discuss and implement a wavelet-modified maximum average correlation height (MACH) filter for 0 degrees -360 degrees in-plane rotations in a hybrid digital-optical correlator. Use of a wavelet transform improves the performance of the MACH filter by reducing the number of filters that are required to identify a target rotated at any angle between 0 degrees and 360 degrees in-plane rotations and enhances the autocorrelation peak intensity significantly. The output of a hybrid digital-optical correlator contains two autocorrelation peaks and a strong dc. Using a chirp function with the wavelet-modified MACH filter, the correlation signals are focused in three different planes. Thus placing a peak-capturing CCD camera at a particular plane, only one autocorrelation peak is recorded, discarding the strong dc and other autocorrelation peaks. A signal-to-noise ratio has been calculated as a metric of goodness of the proposed wavelet-modified MACH filter.     

Computer-generated multiple-object discriminant correlation filters: design by simulated annealing

The computer generation of multiple-object discriminant correlation filters is studied. The quantization of filter functions influences the correlation response. This may cause misdetection or incorrect classification of patterns and is especially serious in the case of multiple-object discriminant filters. We propose synthesizing the matched-filter functions by the simulated-annealing algorithm. The recording of Lohmann-type computer-generated holograms is considered. By this method the filter functions can be encoded with a reduction in the quantization levels of amplitude and phase. Acomputer simulation is performed, and the expected correlation responses are obtained.     

Real-time defect detection of steel wire rods using wavelet filters optimized by univariate dynamic encoding algorithm for searches

We propose a new defect detection algorithm for scale-covered steel wire rods. The algorithm incorporates an adaptive wavelet filter that is designed on the basis of lattice parameterization of orthogonal wavelet bases. This approach offers the opportunity to design orthogonal wavelet filters via optimization methods. To improve the performance and the flexibility of wavelet design, we propose the use of the undecimated discrete wavelet transform, and separate design of column and row wavelet filters but with a common cost function. The coefficients of the wavelet filters are optimized by the so-called univariate dynamic encoding algorithm for searches (uDEAS), which searches the minimum value of a cost function designed to maximize the energy difference between defects and background noise. Moreover, for improved detection accuracy, we propose an enhanced double-threshold method. Experimental results for steel wire rod surface images obtained from actual steel production lines show that the proposed algorithm is effective.     

Multireference binary phase-only filter optimized by regions of support

A new formulation of a multiplex filter for filtering-based optical processors, based on the VanderLugt architecture, is presented. The multireference binary phase-only filter (MBPOF), optimized by regions of support (ROS), constitutes a formal rewriting of some multiplex or composite filters including optimization functions, such as the distribution function and the selection function. The first function optimizes the multiplexing of references into the multireference filter. The second function defines the ROS of an object's Fourier spectrum and can be independently used to optimize the conventional binary phase-only filter. Both functions result from a segmentation of the Fourier plane. The MBPOF with ROS can be optically implemented in a filtering-based optical processor owing to a binary-phase spatial light modulator. Simulation and optical results are given for different examples of the BPOF and the MBPOF, both with ROS optimizing different criteria of performance, such as peak-to-correlation energy, discrimination capability, and distortion sensitivity.