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.

/pdf/neural-networks-for-pattern-recognition-34puigiau1.pdf

Neural networks for pattern recognition

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.

High-Speed Tracking with Kernelized Correlation Filters

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.

Neural network-based face detection

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

/pdf/handbook-of-fingerprint-recognition-16mh887j24.pdf

Handbook of Fingerprint Recognition

http://romisatriawahono.net/lecture/rm/survey/machine%20learning/Chandrashekar%20-%20Feature%20Selection%20Methods%20-%202014.pdf

A survey on feature selection methods

Kalman filtering represents formidable computational linear algebra requirements for each new input measurement vector. The air-to-air missile guidance problem is addressed for which an extended Kalman filter (EKF) is required because the measurements are nonlinear in Cartesian coordinates. An explicit formulation is used. At the outset, we discretize the system dynamics and measurement model and incorporate a discrete-time EKF. A factorized L D LT algorithm is used to propagate the covariance matrices between sample times. A simulation analysis of the number of data bits required in the computations is provided. Comparison with other EKF algorithms shows that this method requires only 18 bit accuracy (compared to 32-40 bits for other methods). Quantitative position, velocity and acceleration estimates obtained for a highly maneuverable target are presented. A high-accuracy floating point optical processor is presented that is capable of computing the full EKF to allow a new measurement update each msec.

A Factorized Extended Kalman Filter

The structure, principles of operation, specifications, and numerous examples of the use of the optically addressed potassium dideuterium phosphate (photo DKDP) light valve in optical data processing are reviewed.

Photo DKDP Light Valve: A Review

A correlator is described that combines optical and electronic processing. The optical section is the first Fourier transform taking stage of a joint transform correlator; its output is electronically processed by a modified spectrum analyzer. Increased flexibility and various processing operations beyond those normally possible in an optical system result.

Equalizing and coherence measure correlators

Optical linear algebra processors that involve solutions of linear algebraic equations have significant potential in adaptive and inference machines. We present an algorithm that includes constraints on the accuracy of the processor and improves the accuracy of the results obtained from such analog processors. The constraint algorithm matches the problem to the accuracy of the processor. Calculation of the adaptive weights in a phased array radar is used as a case study. Simulation results prove the benefits advertised. The desensitization of the calculated weights to computational errors in the processor is quantified. Ridge regression isused to determine the parameter needed in the algorithm.

Reduced sensitivity algorithm for optical processors using constraints and ridge regression.

An optical matched spatial filtering system is described that is capable of correlating nonvertical imagery with no loss in the peak intensity and SNR of the output correlation. From the coordinates of the correlation peak, the tilt angle of one camera (or angle of approach of the object being photographed) and the scale of the image (distance from the object) can be determined. Experimental demonstrations of the principle (combined geometrical and optical transformations) on actual imagery are included.

David P. Casasent

Papers

A Factorized Extended Kalman Filter

Photo DKDP Light Valve: A Review

Equalizing and coherence measure correlators

Reduced sensitivity algorithm for optical processors using constraints and ridge regression.

Optical pattern recognition on nonvertical imagery.