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

A hybrid time and space integrating processor is shown to provide more than one operation per analog to digital conversion. A preferred performance measure, operations per second per component, is used to compare bit-sliced digital and high accuracy optical processors using the digital multiplication-by-analog-convolution algorithm. Optical system performance is shown to increase nearly quadratically with the speed of its components, while digital systems increase only linearly.

High accuracy optical processors: a new performance comparison.

We consider a feature selection method to detect skin tumors on chicken carcasses using hyperspectral (HS) reflectance data. Detection of chicken tumors is difficult because the tumors vary in size and shape; some tumors are small, early-stage tumor spots. We make use of the fact that a chicken skin tumor consists of a lesion region surrounded by a region of thickened skin and that the spectral responses of the lesion and the thickened-skin regions of tumors are considerably different and train our feature selection algorithm to separately detect lesion regions and thickened-skin regions; we then fuse the two HS detection results to reduce false alarms. To the best of our knowledge, these techniques are new. Our forward selection and modified branch and bound algorithm is used to select a small number of lambda spectral features that are useful for discrimination. Initial results show that our method offers promise for a good tumor detection rate and a low false alarm rate.

Fusion algorithm for poultry skin tumor detection using hyperspectral data

We describe a high-speed acousto-optic Hough-transform mapping modulator. This mapping modulator generates any θ slice of the straight line Hough-transform and one-dimensional slices of generalized Hough transforms (e.g., for circles and ellipses). We derive the mapping functions for the acousto-optic modulator for both circle and ellipse Hough transforms and show simulations of generalized Hough transforms using both functions. We also describe how the mapping modulators can compute Hough transforms for nonanalytically describable inputs.

High-speed acousto-optic mapping modulator for the generalized Hough transform.

An efficient 3-D object-centered knowledge base is described. The ability to on-line generate a 2-D image projection or range image for any object/viewer orientation from this knowledge base is addressed. Applications of this knowledge base in associative processors and symbolic correlators are then discussed. Initial test results are presented for a multiple degree of freedom object recognition problem. These include new techniques to achieve object orientation information and two new associative memory matrix formulations.

Model-based knowledge-based optical processors

A hierarchical classifier using a new SVRDM (support vector representation and discrimination machine) is proposed for automatic target recognition. An accuracy and distance-based method is used to design a hierarchical classifier. Our SVRDM hierarchical classifier has the ability to reject unseen non-object classes and clutter inputs. Uses of both iconic and spatial frequency domain features are considered. Initial recognition and rejection test results on infrared (IR) data are excellent.

David P. Casasent

Papers

High accuracy optical processors: a new performance comparison.

Fusion algorithm for poultry skin tumor detection using hyperspectral data

High-speed acousto-optic mapping modulator for the generalized Hough transform.

Model-based knowledge-based optical processors

Automatic target recognition using new support vector machine