Minimum average correlation energy filters

Heterogeneous Stitching of X-ray Images According to Homographic Evaluation

The C-arm X-ray system is a common intraoperative imaging modality used to observe the state of a fractured bone in orthopedic surgery. Using C-arm, the bone fragments are aligned during surgery, and their lengths and angles with respect to the entire bone are measured to verify the fracture reduction. Since the field-of-view of the C-arm is too narrow to visualize the entire bone, a panoramic X-ray image is utilized to enlarge it by stitching multiple images. To achieve X-ray image stitching with feature detection, the extraction of accurate and densely matched features within the overlap region between images is imperative. However, since the features are highly affected by the properties and sizes of the overlap regions in consecutive X-ray images, the accuracy and density of matched features cannot be guaranteed. To solve this problem, a heterogeneous stitching of X-ray images was proposed. This heterogeneous stitching was completed according to the overlap region based on homographic evaluation. To acquire sufficiently matched features within the limited overlap region, integrated feature detection was used to estimate a homography. The homography was then evaluated to confirm its accuracy. When the estimated homography was incorrect, local regions around the matched feature were derived from integrated feature detection and substituted to re-estimate the homography. Successful X-ray image stitching of the C-arm was achieved by estimating the optimal homography for each image. Based on phantom and ex-vivo experiments using the proposed method, we confirmed a panoramic X-ray image construction that was robust compared to the conventional methods.

Efficient Correlation Tracking via Center-Biased Spatial Regularization

Correlation filters (CFs) have been applied to visual tracking with success providing excellent performance in terms of accuracy and efficiency. The underlying periodic assumption of the training samples results in their great efficiency when using the fast Fourier transform (FFT), yet it also brings unwanted boundary effects. To address this issue, the recently proposed spatially-regularized discriminative CF (SRDCF) method introduces a Gaussian weight function to regularize the learning filter, yielding favorable performances in accuracy but high computational complexity because the objective of the SRDCF cannot achieve a closed solution via the FFT. Motivated by SRDCF, we present an efficient and effective CF-based tracker using center-biased constraint weights (CBCWs), which improve simultaneously speed and accuracy. Specifically, we first construct a CBCW function by exploiting the symmetry of the Fourier transform. The values of the constraint weights are real in both time and frequency domains, so that the optimization can be directly solved in the frequency domain without any data transformation, thereby greatly reducing its computational complexity. Moreover, according to the average peak-tocorrelation energy value of the CF response, we propose an efficient and effective filter update strategy to handle occlusions during tracking. Extensive experiments on the OTB-2013, OTB- 2015, and VOT2016 benchmarks demonstrate that the proposed tracker significantly outperforms the baseline SRDCF in terms of accuracy and efficiency. Moreover, the proposed method performs favorably against 16 other representative state-of-the-art methods regarding robustness and success rate.

One lens optical correlation: application to face recognition

Despite its extensive use, the traditional 4f Vander Lugt Correlator optical setup can be further simplified. We propose a lightweight correlation scheme where the decision is taken in the Fourier plane. For this purpose, the Fourier plane is adapted and used as a decision plane. Then, the offline phase and the decision metric are re-examined in order to keep a reasonable recognition rate. The benefits of the proposed approach are numerous: (1) it overcomes the constraints related to the use of a second lens; (2) the optical correlation setup is simplified; (3) the multiplication with the correlation filter can be done digitally, which offers a higher adaptability according to the application. Moreover, the digital counterpart of the correlation scheme is lightened since with the proposed scheme we get rid of the inverse Fourier transform (IFT) calculation (i.e., decision directly in the Fourier domain without resorting to IFT). To assess the performance of the proposed approach, an insight into digital hardware resources saving is provided. The proposed method involves nearly 100 times fewer arithmetic operators. Moreover, from experimental results in the context of face verification-based correlation, we demonstrate that the proposed scheme provides comparable or better accuracy than the traditional method. One interesting feature of the proposed scheme is that it could greatly outperform the traditional scheme for face identification application in terms of sensitivity to face orientation. The proposed method is found to be digital/optical implementation-friendly, which facilitates its integration on a very broad range of scenarios.

Latent Constrained Correlation Filter

Correlation filters are special classifiers designed for shift-invariant object recognition, which are robust to pattern distortions. The recent literature shows that combining a set of sub-filters trained based on a single or a small group of images obtains the best performance. The idea is equivalent to estimating variable distribution based on the data sampling (bagging), which can be interpreted as finding solutions (variable distribution approximation) directly from sampled data space. However, this methodology fails to account for the variations existed in the data. In this paper, we introduce an intermediate step-solution sampling-after the data sampling step to form a subspace, in which an optimal solution can be estimated. More specifically, we propose a new method, named latent constrained correlation filters (LCCF), by mapping the correlation filters to a given latent subspace, and develop a new learning framework in the latent subspace that embeds distribution-related constraints into the original problem. To solve the optimization problem, we introduce a subspace-based alternating direction method of multipliers, which is proven to converge at the saddle point. Our approach is successfully applied to three different tasks, including eye localization, car detection, and object tracking. Extensive experiments demonstrate that LCCF outperforms the state-of-the-art methods.¹¹ .

Weak Classifier for Density Estimation in Eye Localization and Tracking

In this paper, we propose a fast weak classifier that can detect and track eyes in video sequences. The approach relies on a least-squares detector based on the inner product detector (IPD) that can stimate a probability density distribution for a feature's location-which fits naturally with a Bayesian estimation cycle, such as a Kalman or particle filter. As a least-squares sliding window detector, it possesses tolerance to small variations in the desired pattern while maintaining good generalization capabilities and computational efficiency. We propose two approaches to integrating the IPD with a particle filter tracker. We use the BioID, FERET, LFPW, and COFW public datasets as well as five manually annotated high-definition video sequences to quantitatively evaluate the algorithms' performance. The video data set contains four subjects, different types of backgrounds, blurring due to fast motion, and occlusions. All code and data are available.

Photorefractive two-beam coupling joint transform correlator: modeling and performance evaluation

The photorefractive two-beam coupling joint transform correlator combines two features. The first is embedded semi-adaptive optimality, which weighs the correlation against clutter and noise in the input, and the second is the intrinsic dynamic range compression nonlinearity, which improves several metrics simultaneously without metric trade-off. Although the two beam coupling correlator was invented many years ago, its outstanding performance was recognized on only relatively simple images. There was no study about the performance of this correlator on complicated images and using different figures of merit. In this paper, the study is extended to more complicated images. For the first time, to our knowledge, we demonstrate simultaneous improvement in metrics performance without metric trade-off. The performance was evaluated compared to the classical joint transform correlator. A typical experimental result to validate the simulation results was also shown in this work. The best performing operation parameters were identified to guide the experimental work and for future comparison with other well-known optimal correlation filters.

Spartans: Single-Sample Periocular-Based Alignment-Robust Recognition Technique Applied to Non-Frontal Scenarios

In this paper, we investigate a single-sample periocular-based alignment-robust face recognition technique that is pose-tolerant under unconstrained face matching scenarios. Our Spartans framework starts by utilizing one single sample per subject class, and generate new face images under a wide range of 3D rotations using the 3D generic elastic model which is both accurate and computationally economic. Then, we focus on the periocular region where the most stable and discriminant features on human faces are retained, and marginalize out the regions beyond the periocular region since they are more susceptible to expression variations and occlusions. A novel facial descriptor, high-dimensional Walsh local binary patterns, is uniformly sampled on facial images with robustness toward alignment. During the learning stage, subject-dependent advanced correlation filters are learned for pose-tolerant non-linear subspace modeling in kernel feature space followed by a coupled max-pooling mechanism which further improve the performance. Given any unconstrained unseen face image, the Spartans can produce a highly discriminative matching score, thus achieving high verification rate. We have evaluated our method on the challenging Labeled Faces in the Wild database and solidly outperformed the state-of-the-art algorithms under four evaluation protocols with a high accuracy of 89.69%, a top score among image-restricted and unsupervised protocols. The advancement of Spartans is also proven in the Face Recognition Grand Challenge and Multi-PIE databases. In addition, our learning method based on advanced correlation filters is much more effective, in terms of learning subject-dependent pose-tolerant subspaces, compared with many well-established subspace methods in both linear and non-linear cases.

Cancelable face verification using optical encryption and authentication

In a cancelable biometric system, each instance of enrollment is distorted by a transform function, and the output should not be retransformed to the original data. This paper presents a new cancelable face verification system in the encrypted domain. Encrypted facial images are generated by a double random phase encoding (DRPE) algorithm using two keys (RPM1 and RPM2). To make the system noninvertible, a photon counting (PC) method is utilized, which requires a photon distribution mask for information reduction. Verification of sparse images that are not recognizable by direct visual inspection is performed by unconstrained minimum average correlation energy filter. In the proposed method, encryption keys (RPM1, RPM2, and PDM) are used in the sender side, and the receiver needs only encrypted images and correlation filters. In this manner, the system preserves privacy if correlation filters are obtained by an adversary. Performance of PC-DRPE verification system is evaluated under illumination variation, pose changes, and facial expression. Experimental results show that utilizing encrypted images not only increases security concerns but also enhances verification performance. This improvement can be attributed to the fact that, in the proposed system, the face verification problem is converted to key verification tasks.

Zero-Aliasing Correlation Filters for Object Recognition

Correlation filters (CFs) are a class of classifiers that are attractive for object localization and tracking applications. Traditionally, CFs have been designed in the frequency domain using the discrete Fourier transform (DFT), where correlation is efficiently implemented. However, existing CF designs do not account for the fact that the multiplication of two DFTs in the frequency domain corresponds to a circular correlation in the time/spatial domain. Because this was previously unaccounted for, prior CF designs are not truly optimal, as their optimization criteria do not accurately quantify their optimization intention. In this paper, we introduce new zero-aliasing constraints that completely eliminate this aliasing problem by ensuring that the optimization criterion for a given CF corresponds to a linear correlation rather than a circular correlation. This means that previous CF designs can be significantly improved by this reformulation. We demonstrate the benefits of this new CF design approach with several important CFs. We present experimental results on diverse data sets and present solutions to the computational challenges associated with computing these CFs. Code for the CFs described in this paper and their respective zero-aliasing versions is available at http://vishnu.boddeti.net/projects/correlation-filters.html.

High-Speed Tracking with Kernelized Correlation Filters

The core component of most modern trackers is a discriminative classifier, tasked with distinguishing between the target and the surrounding environment. To cope with natural image changes, this classifier is typically trained with translated and scaled sample patches. Such sets of samples are riddled with redundancies-any overlapping pixels are constrained to be the same. Based on this simple observation, we propose an analytic model for datasets of thousands of translated patches. By showing that the resulting data matrix is circulant, we can diagonalize it with the discrete Fourier transform, reducing both storage and computation by several orders of magnitude. Interestingly, for linear regression our formulation is equivalent to a correlation filter, used by some of the fastest competitive trackers. For kernel regression, however, we derive a new kernelized correlation filter (KCF), that unlike other kernel algorithms has the exact same complexity as its linear counterpart. Building on it, we also propose a fast multi-channel extension of linear correlation filters, via a linear kernel, which we call dual correlation filter (DCF). Both KCF and DCF outperform top-ranking trackers such as Struck or TLD on a 50 videos benchmark, despite running at hundreds of frames-per-second, and being implemented in a few lines of code (Algorithm 1). To encourage further developments, our tracking framework was made open-source.

Fourier filter augmented with trainer histograms

This paper describes a computationally efficient method for boosting the performance of correlation filters. The correlation filter is augmented with an array of histograms and the associated affinity numbers, obtained from the training image set utilized in construction of the filter. In the operational phase, histograms of sensor images are examined only at the image neighborhoods where the correlation filter provides initial indications of a target occurrence. The presence of a target is affirmed at image locations that pass both the peak cross correlation and histogram tests. Results of numerous experiments demonstrate that reinforcement of the spatial correlation filter with the trainer histograms leads to more robust Fourier filters for target detection and classification.

Sparse Feature Extraction for Pose-Tolerant Face Recognition

Automatic face recognition performance has been steadily improving over years of research, however it remains significantly affected by a number of factors such as illumination, pose, expression, resolution and other factors that can impact matching scores. The focus of this paper is the pose problem which remains largely overlooked in most real-world applications. Specifically, we focus on one-to-one matching scenarios where a query face image of a random pose is matched against a set of gallery images. We propose a method that relies on two fundamental components: (a) A 3D modeling step to geometrically correct the viewpoint of the face. For this purpose, we extend a recent technique for efficient synthesis of 3D face models called 3D Generic Elastic Model. (b) A sparse feature extraction step using subspace modeling and ℓ1-minimization to induce pose-tolerance in coefficient space. This in return enables the synthesis of an equivalent frontal-looking face, which can be used towards recognition. We show significant performance improvements in verification rates compared to commercial matchers, and also demonstrate the resilience of the proposed method with respect to degrading input quality. We find that the proposed technique is able to match non-frontal images to other non-frontal images of varying angles.

Subspace-based discrete transform encoded local binary patterns representations for robust periocular matching on NIST's face recognition grand challenge

In this paper, we employ several subspace representations (principal component analysis, unsupervised discriminant projection, kernel class-dependence feature analysis, and kernel discriminant analysis) on our proposd discrete transform encoded local binary patterns (DT-LBP) to match periocular region on a large data set such as NIST's face recognition grand challenge (FRGC) ver2 database. We strictly follow FRGC Experiment 4 protocol, which involves 1-to-1 matching of 8014 uncontrolled probe periocular images to 16 028 controlled target periocular images (~128 million pairwise face match comparisons). The performance of the periocular region is compared with that of full face with different illumination preprocessing schemes. The verification results on periocular region show that subspace representation on DT-LBP outperforms LBP significantly and gains a giant leap from traditional subspace representation on raw pixel intensity. Additionally, our proposed approach using only the periocular region is almost as good as full face with only 2.5% reduction in verification rate at 0.1% false accept rate, yet we gain tolerance to expression, occlusion, and capability of matching partial faces in crowds. In addition, we have compared the best standalone DT-LBP descriptor with eight other state-of-the-art descriptors for facial recognition and achieved the best performance. The two general frameworks are our major contribution: 1) a general framework that employs various generative and discriminative subspace modeling techniques for DT-LBP representation and 2) a general framework that encodes discrete transforms with local binary patterns for the creation of robust descriptors.

Trends in correlation-based pattern recognition and tracking in forward-looking infrared imagery

In this paper, we review the recent trends and advancements on correlation-based pattern recognition and tracking in forward-looking infrared (FLIR) imagery. In particular, we discuss matched filter-based correlation techniques for target detection and tracking which are widely used for various real time applications. We analyze and present test results involving recently reported matched filters such as the maximum average correlation height (MACH) filter and its variants, and distance classifier correlation filter (DCCF) and its variants. Test results are presented for both single/multiple target detection and tracking using various real-life FLIR image sequences.

Development of automated image stitching system for radiographic images

Standard X-ray images using conventional screen-film technique have a limited field of view that is insufficient to show the full bone structure of large hands on a single frame. To produce images containing the whole hand structure, digitized images from the X-ray films can be assembled using image stitching. This paper presents a new medical image stitching method that utilizes minimum average correlation energy filters to identify and merge pairs of hand X-ray medical images. The effectiveness of the proposed method is demonstrated in the experiments involving two databases which contain a total of 40 pairs of overlapping and non-overlapping hand images. The experimental results are compared with that of the normalized cross-correlation (NCC) method. It is found that the proposed method outperforms the NCC method in classifying and merging the overlapping and non-overlapping medical images. The efficacy of the proposed method is further indicated by its average execution time, which is about five times shorter than that of the other method.

A framework for binding and retrieving class-specific information to and from image patterns using correlation filters

We describe a template-based framework to bind class-specific information to a set of image patterns and retrieve that information by matching the template to a query pattern of the same class. This is done by mapping the class-specific information to a set of spatial translations which are applied to the set of image patterns from which a template is designed, taking advantage of the properties of correlation filters. The bound information is retrieved during matching with an authentic query by estimating the spatial translations applied to the images that were used to design the template. In this paper, we focus on the problem of binding information to biometric signatures as an application of our framework. Our framework is flexible enough to allow spreading the information to be bound over multiple pattern classes which, in the context of biometric key-binding, enables multiclass and multimodal biometric key-binding. We demonstrate the effectiveness of the proposed scheme via extensive numerical results on multiple biometric databases.

Asymmetric correlation: a noise robust similarity measure for template matching

We present an efficient and noise robust template matching method based on asymmetric correlation (ASC). The ASC similarity function is invariant to affine illumination changes and robust to extreme noise. It correlates the given non-normalized template with a normalized version of each image window in the frequency domain. We show that this asymmetric normalization is more robust to noise than other cross correlation variants, such as the correlation coefficient. Direct computation of ASC is very slow, as a DFT needs to be calculated for each image window independently. To make the template matching efficient, we develop a much faster algorithm, which carries out a prediction step in linear time and then computes DFTs for only a few promising candidate windows. We extend the proposed template matching scheme to deal with partial occlusion and spatially varying light change. Experimental results demonstrate the robustness of the proposed ASC similarity measure compared to state-of-the-art template matching methods.

Distortion tolerant correlation filter design

This paper introduces a computationally efficient algorithm for synthesis of a distortion tolerant correlation filter and associated threshold, denoted collectively as the enhanced matched filter (EMF). Application areas of EMF include imagery based automatic target detection and recognition and biometrics. The EMF is synthesized from a set of training images characterizing the target of interest within the expected distortion range. A distinguishing feature of EMF is the ascribed threshold, which is a byproduct of the filter computation process and does not rely on nontarget trainers. The EMF performance is compared to that of the synthetic discriminant function using realistic test scenarios.

Maximum Margin Correlation Filter: a new approach for localization and classification

Support vector machine (SVM) classifiers are popular in many computer vision tasks. In most of them, the SVM classifier assumes that the object to be classified is centered in the query image, which might not always be valid, e.g., when locating and classifying a particular class of vehicles in a large scene. In this paper, we introduce a new classifier called Maximum Margin Correlation Filter (MMCF), which, while exhibiting the good generalization capabilities of SVM classifiers, is also capable of localizing objects of interest, thereby avoiding the need for image centering as is usually required in SVM classifiers. In other words, MMCF can simultaneously localize and classify objects of interest. We test the efficacy of the proposed classifier on three different tasks: vehicle recognition, eye localization, and face classification. We demonstrate that MMCF outperforms SVM classifiers as well as well known correlation filters.

Optical correlator based target detection, recognition, classification, and tracking

A dedicated automatic target recognition and tracking optical correlator (OC) system using advanced processing technology has been developed. Rapidly cycling data-cubes with size, shape, and orientation are employed with software algorithms to isolate correlation peaks and enable tracking of targets in maritime environments with future track prediction. The method has been found superior to employing maximum average correlation height filters for which the correlation peak intensity drops off in proportion to the number of training images. The physical dimensions of the OC system may be reduced to as small as 2 in. × 2 in. × 3 in. (51 mm × 51 mm × 76 mm) by modifying and minimizing the OC components.

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.

Robust classification method of tumor subtype by using correlation filters

Tumor classification based on gene expression profiles, which is of great benefit to the accurate diagnosis and personalized treatment for different types of tumor, has drawn a great attention in recent years. This paper proposes a novel tumor classification method based on correlation filters to identify the overall pattern of tumor subtype hidden in differentially expressed genes. Concretely, two correlation filters, i.e., Minimum Average Correlation Energy (MACE) and Optimal Tradeoff Synthetic Discriminant Function (OTSDF), are introduced to determine whether a test sample matches the templates synthesized for each subclass. The experiments on six publicly available datasets indicate that the proposed method is robust to noise, and can more effectively avoid the effects of dimensionality curse. Compared with many model-based methods, the correlation filter based method can achieve better performance when balanced training sets are exploited to synthesize the templates. Particularly, the proposed method can detect the similarity of overall pattern while ignoring small mismatches between test sample and the synthesized template. And it performs well even if only few training samples are available. More importantly, the experimental results can be visually represented, which is helpful for the further analysis of results.

A Regularized Correntropy Framework for Robust Pattern Recognition

This letter proposes a new multiple linear regression model using regularized correntropy for robust pattern recognition. First, we motivate the use of correntropy to improve the robustness of the classical mean square error (MSE) criterion that is sensitive to outliers. Then an l1 regularization scheme is imposed on the correntropy to learn robust and sparse representations. Based on the half-quadratic optimization technique, we propose a novel algorithm to solve the nonlinear optimization problem. Second, we develop a new correntropy-based classifier based on the learned regularization scheme for robust object recognition. Extensive experiments over several applications confirm that the correntropy-based l1 regularization can improve recognition accuracy and receiver operator characteristic curves under noise corruption and occlusion.

Neural network model for rotation invariant recognition of object shapes

A multichannel, multilayer feed forward neural network model is proposed for rotation invariant recognition of objects. In the M channel network, each channel consists of a one dimensional slice of the two dimensional (2D) Fourier transform (FT) of the input pattern that connects fully to the weight matrix. Each slice is taken at different angles from the 2D FT of the object. From each channel, only one neuron can fire in the presence of the training object. The output layer sums up the response of the hidden layer neuron and confirms the presence of the object. Rotation invariant recognition from 0 degrees to 360 degrees is obtained even in the case of degraded images.

Optical Computing: A 60-Year Adventure

Optical computing is a very interesting 60-year old field of research. This paper gives a brief historical review of the life of optical computing from the early days until today. Optical computing generated a lot of enthusiasm in the sixties with major breakthroughs opening a large number of perspectives. The period between 1980 and 2000 could be called the golden age with numerous new technologies and innovating optical processors designed and constructed for real applications. Today the field of optical computing is not ready to die, it has evolved and its results benefit to new research topics such as nanooptics, biophotonics, or communication systems.

Adaptive phase-input joint transform correlator

An adaptive phase-input joint transform correlator for pattern recognition is presented. The input of the system is two phase-only images: input scene and reference. The reference image is generated with a new iterative algorithm using phase-only synthetic discriminant functions. The algorithm takes into account calibration lookup tables of all optoelectronics elements used in optodigital experiments. The designed adaptive phase-input joint transform correlator is able to reliably detect a target and its distorted versions embedded into a cluttered background. Computer simulations are provided and compared with those of various existing joint transform correlators in terms of discrimination capability, tolerance to input additive noise, and to small geometric image distortions. Experimental optodigital results are also provided and discussed.

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.

An associative memory readout for ESNs with applications to dynamical pattern recognition

The use of echo state networks (ESN) to find patterns in time (dynamical pattern recognition) has been limited. This paper argues that ESNs are particularly well suited for dynamical pattern recognition and proposes a linear associative memory (LAM) as a novel readout for ESNs. From the class of LAMs, the minimum average correlation energy (MACE) filter is adopted because of its high rejection characteristics that allow its use as a detector in the automatic pattern recognition literature. In the ESN application, the MACE interprets the states of the ESN as a two-dimensional "image", one dimension being time and the other the processing element index (space). An optimal template image for each class, which associates ESN states with the class label, can be analytically computed using training data. During testing, ESN states are correlated with each template image and the class label of the template with the highest correlation is assigned to the input pattern. The ESN-MACE combination leads to a nonlinear template matcher with robust noise performance as needed in non-Gaussian, nonlinear digital communication channels. A real-world data experiment for chemical sensing with an electronic nose is included to demonstrate the validity of this approach. Moreover, the proposed readout can also be used with liquid state machines eliminating the need to convert spike trains into continuous signals by binning or low-pass filtering.

A bayesian approach to deformed pattern matching of iris images

We describe a general probabilistic framework for matching patterns that experience in-plane nonlinear deformations, such as iris patterns. Given a pair of images, we derive a maximum a posteriori probability (MAP) estimate of the parameters of the relative deformation between them. Our estimation process accomplishes two things simultaneously: It normalizes for pattern warping and it returns a distortion-tolerant similarity metric which can be used for matching two nonlinearly deformed image patterns. The prior probability of the deformation parameters is specific to the pattern-type and, therefore, should result in more accurate matching than an arbitrary general distribution. We show that the proposed method is very well suited for handling iris biometrics, applying it to two databases of iris images which contain real instances of warped patterns. We demonstrate a significant improvement in matching accuracy using the proposed deformed Bayesian matching methodology. We also show that the additional computation required to estimate the deformation is relatively inexpensive, making it suitable for real-time applications.

Deformable shape finding with models based on kernel methods

In this paper, a new kernel-based deformable model is proposed for detecting deformable shapes. To incorporate valuable information for shape detection, such as edge orientations into the shape representation, a novel scheme based on kernel methods has been utilized. The variation model of a deformable shape is established by a set of training samples of the shape represented in a kernel feature space. The proposed deformable model consists of two parts: a set of basis vectors describing the sample subspace, including the shape representations of the training samples, and a feasibility constraint generated by the one-class support vector machine to describe the feasible region of the training samples in the sample subspace. The aim of the proposed feasibility constraint is to avoid finding some invalid shapes. By using the proposed deformable model, an efficient algorithm without initial solutions is developed for shape detection. The proposed approach was tested against real images. Experimental results show the effectiveness of the proposed deformable model and prove the feasibility of the proposed approach.

Pattern recognition with an adaptive joint transform correlator

An adaptive joint transform correlator for real-time pattern recognition is presented. A reference image for the correlator is generated with a new iterative algorithm. The training algorithm is based on synthetic discriminant functions. The obtained reference image contains the information needed to reliably discriminate a target against known false objects and a cluttered background. Calibration lookup tables of all optoelectronics elements used are included in the design of the adaptive joint transform correlator. Two methods for the implementation of the proposed joint transform correlator in an optodigital setup are considered. Experimental results are provided and compared with those of computer simulations.

Correlation filters with controlled scale response

Correlation filtering methods are becoming increasingly popular for image recognition and location. The recent introduction of optimal tradeoff circular harmonic function filters allowed the user to specify the response of a correlation filter to in-plane rotation distortion. In this paper we introduce a new correlation filter design that can provide a user-specified response to in-plane scale distortion. The design is based on the Mellin radial harmonic (MRH) transform and incorporates multiple harmonics into the correlation filter for improved discrimination capability. Additionally, the filter design minimizes the average correlation energy in order to achieve sharp correlation peaks, and thus we refer to these filters as minimum average correlation energy Mellin radial harmonic (MACE-MRH) filters. We present underlying theory, a MACE-MRH filter design method, and numerical simulation results.