David P. Casasent

Bio: David P. Casasent is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Optical correlator & Image processing. The author has an hindex of 44, co-authored 693 publications receiving 10367 citations. Previous affiliations of David P. Casasent include Carnegie Learning & Center for Excellence in Education.

Minimum average correlation energy filters

Abstract: The synthesis of a new category of spatial filters that produces sharp output correlation peaks with controlled peak values is considered. The sharp nature of the correlation peak is the major feature emphasized, since it facilitates target detection. Since these filters minimize the average correlation plane energy as the first step in filter synthesis, we refer to them as minimum average correlation energy filters. Experimental laboratory results from optical implementation of the filters are also presented and discussed.

Position, rotation, and scale invariant optical correlation

Abstract: A new optical transformation that combines geometrical coordinate transformations with the conventional optical Fourier transform is described. The resultant transformations are invariant to both scale and rotational changes in the input object or function. Extensions of these operations to optical pattern recognition and initial experimental demonstrations are also presented.

Multivariant technique for multiclass pattern recognition.

Abstract: A technique for multiclass optical pattern recognition of different perspective views of an object is described. Each multiclass representation of an object is described as an orthonormal basis function expansion, and a single averaged matched spatial filter is then produced from a weighted linear combination of these functions. The technique is demonstrated for a terminal missile guidance application using IR tank imagery.

Unified synthetic discriminant function computational formulation.

Abstract: A most attractive approach to distortion-invariant pattern recognition uses a synthetic discriminant function (SDF) as the matched spatial filter in a correlator. In this paper, we (1) provide a general basis function and hyperspace description of SDFs, (2) advance a derivation showing the generality of the correlation matrix observation space that we use in our filter synthesis, and (3) detail a unified SDF filter synthesis technique for five different types of pattern recognition problem.

Application Of The Liquid Crystal Light Valve To Real-Time Optical Data Processing

Abstract: This paper reviews the hybrid field-effect liquid crystal light valve (LCLV) and its application to real-time coherent optical data processing. The light valve is basically a high resolution optical-to-optical image converter. The device embodies a CdS photoconductor, a CdTe light-absorbing layer, a dielectric mirror, and a biphenyl liquid crystal layer sandwiched between indium-tin-oxide transparent electrodes deposited on optical quality glass flats. The input image is directed onto the photo-conductor to reduce the impedance of the photoconductor, thereby switching the ac voltage that is impressed across the electrodes onto the liquid crystal to activate the device. The ac operation ensures long operating life for the device. The liquid crystal is operated in a hybrid field-effect mode. It utilizes the twisted nematic effect to create a dark off-state (voltage off the liquid crystal) and optical birefringence to create the bright on-state. The liquid crystal modulates the phase of the coherent readout light. By an additional analyzer an intensity modulation is created.

Neural networks for pattern recognition

Abstract: From the Publisher: This is the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition. After introducing the basic concepts, the book examines techniques for modelling probability density functions and the properties and merits of the multi-layer perceptron and radial basis function network models. Also covered are various forms of error functions, principal algorithms for error function minimalization, learning and generalization in neural networks, and Bayesian techniques and their applications. Designed as a text, with over 100 exercises, this fully up-to-date work will benefit anyone involved in the fields of neural computation and pattern recognition.

High-Speed Tracking with Kernelized Correlation Filters

Abstract: 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.

Neural network-based face detection

Abstract: We present a neural network-based upright frontal face detection system. A retinally connected neural network examines small windows of an image and decides whether each window contains a face. The system arbitrates between multiple networks to improve performance over a single network. We present a straightforward procedure for aligning positive face examples for training. To collect negative examples, we use a bootstrap algorithm, which adds false detections into the training set as training progresses. This eliminates the difficult task of manually selecting nonface training examples, which must be chosen to span the entire space of nonface images. Simple heuristics, such as using the fact that faces rarely overlap in images, can further improve the accuracy. Comparisons with several other state-of-the-art face detection systems are presented, showing that our system has comparable performance in terms of detection and false-positive rates.

Handbook of Fingerprint Recognition

Abstract: A major new professional reference work on fingerprint security systems and technology from leading international researchers in the field Handbook provides authoritative and comprehensive coverage of all major topics, concepts, and methods for fingerprint security systems This unique reference work is an absolutely essential resource for all biometric security professionals, researchers, and systems administrators