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

Presents a theoretically very simple, yet efficient, multiresolution approach to gray-scale and rotation invariant texture classification based on local binary patterns and nonparametric discrimination of sample and prototype distributions. The method is based on recognizing that certain local binary patterns, termed "uniform," are fundamental properties of local image texture and their occurrence histogram is proven to be a very powerful texture feature. We derive a generalized gray-scale and rotation invariant operator presentation that allows for detecting the "uniform" patterns for any quantization of the angular space and for any spatial resolution and presents a method for combining multiple operators for multiresolution analysis. The proposed approach is very robust in terms of gray-scale variations since the operator is, by definition, invariant against any monotonic transformation of the gray scale. Another advantage is computational simplicity as the operator can be realized with a few operations in a small neighborhood and a lookup table. Experimental results demonstrate that good discrimination can be achieved with the occurrence statistics of simple rotation invariant local binary patterns.

/pdf/multiresolution-gray-scale-and-rotation-invariant-texture-1b1y2fta4g.pdf

Multiresolution gray-scale and rotation invariant texture classification with local binary patterns

http://library.utia.cas.cz/prace/20030125.pdf

Image registration methods: a survey

Presents a review of 200 references in content-based image retrieval. The paper starts with discussing the working conditions of content-based retrieval: patterns of use, types of pictures, the role of semantics, and the sensory gap. Subsequent sections discuss computational steps for image retrieval systems. Step one of the review is image processing for retrieval sorted by color, texture, and local geometry. Features for retrieval are discussed next, sorted by: accumulative and global features, salient points, object and shape features, signs, and structural combinations thereof. Similarity of pictures and objects in pictures is reviewed for each of the feature types, in close connection to the types and means of feedback the user of the systems is capable of giving by interaction. We briefly discuss aspects of system engineering: databases, system architecture, and evaluation. In the concluding section, we present our view on: the driving force of the field, the heritage from computer vision, the influence on computer vision, the role of similarity and of interaction, the need for databases, the problem of evaluation, and the role of the semantic gap.

/pdf/content-based-image-retrieval-at-the-end-of-the-early-years-q45iy9ejai.pdf

Content-based image retrieval at the end of the early years

In this paper the authors present a new approach for the nonrigid registration of contrast-enhanced breast MRI. A hierarchical transformation model of the motion of the breast has been developed. The global motion of the breast is modeled by an affine transformation while the local breast motion is described by a free-form deformation (FFD) based on B-splines. Normalized mutual information is used as a voxel-based similarity measure which is insensitive to intensity changes as a result of the contrast enhancement. Registration is achieved by minimizing a cost function, which represents a combination of the cost associated with the smoothness of the transformation and the cost associated with the image similarity. The algorithm has been applied to the fully automated registration of three-dimensional (3-D) breast MRI in volunteers and patients. In particular, the authors have compared the results of the proposed nonrigid registration algorithm to those obtained using rigid and affine registration techniques. The results clearly indicate that the nonrigid registration algorithm is much better able to recover the motion and deformation of the breast than rigid or affine registration algorithms.

/pdf/nonrigid-registration-using-free-form-deformations-2olitefstb.pdf

Nonrigid registration using free-form deformations: application to breast MR images

The problem of rotation-, scale-, and translation-invariant recognition of images is discussed. A set of rotation-invariant features are introduced. They are the magnitudes of a set of orthogonal complex moments of the image known as Zernike moments. Scale and translation invariance are obtained by first normalizing the image with respect to these parameters using its regular geometrical moments. A systematic reconstruction-based method for deciding the highest-order Zernike moments required in a classification problem is developed. The quality of the reconstructed image is examined through its comparison to the original one. The orthogonality property of the Zernike moments, which simplifies the process of image reconstruction, make the suggest feature selection approach practical. Features of each order can also be weighted according to their contribution to the reconstruction process. The superiority of Zernike moment features over regular moments and moment invariants was experimentally verified. >

Invariant image recognition by Zernike moments

A neural network (NN) based approach for classification of images represented by translation-, scale-, and rotation-invariant features is presented. The utilized network is a multilayer perceptron (MLP) classifier with one hidden layer. Back-propagation learning is used for its training. Two types of features are used: moment invariants derived from geometrical moments of the image, and features based on Zernlike moments, which are the mapping of the image onto a set of complex orthogonal polynomials. The performance of the MLP is compared to the Bayes, nearest-neighbor, and minimum-mean-distance statistical classifiers. Through extensive experimentation with noiseless as well as noisy binary images of all English characters (26 classes), the following conclusions are reached: (1) the MLP outperforms the other three classifiers, especially when noise is present; (2) the nearest-neighbor classifier performs about the same as the NN for the noiseless case; (3) the NN can do well even with a very small number of training samples; (4) the NN has a good degree of fault tolerance; and (5) the Zernlike-moment-based features possess strong class separability power and are more powerful than moment invariants. >

Classification of invariant image representations using a neural network

This paper presents a new model-based approach for texture classification which is rotation invariant, i.e., the recognition accuracy is not affected if the orientation of the test texture is different from the orientation of the training samples. The method uses three statistical features, two of which are obtained from a new parametric model of the image called a ``circular symmetric autoregressive model.'' Two of the proposed features have physical interpretation in terms of the roughness and directionality of the texture. The results of several classification experiments on differently oriented samples of natural textures including both microtextures and macrotextures are presented.

A Model-Based Method for Rotation Invariant Texture Classification

Many image matching schemes are based on mapping coordinate locations, such as the locations of landmarks, in one image to corresponding locations in a second image. A new approach to this mapping (coordinate transformation), called the elastic body spline (EBS), is described. The spline is based on a physical model of a homogeneous, isotropic three-dimensional (3-D) elastic body. The model can approximate the way that some physical objects deform. The EBS as well as the affine transformation, the thin plate spline and the volume spline are used to match 3-D magnetic resonance images (MRI's) of the breast that are used in the diagnosis and evaluation of breast cancer. These coordinate transformations are evaluated with different types of deformations and different numbers of corresponding (paired) coordinate locations. In all but one of the cases considered, using the EBS yields more similar images than the other methods.

A physics-based coordinate transformation for 3-D image matching

This paper describes the third generation of an hourly short-term load forecasting system known as ANNSTLF (Artificial Neural Network Short-Term Load Forecaster). This forecaster has received wide acceptance by the electric utility industry and is being used by 35 utilities across the US and Canada. The third generation architecture is substantially changed from the previous generation. It includes only two ANN forecasters, one predicts the base load and the other forecasts the change in load. The final forecast is computed by adaptive combination of these two forecasts. The effect of humidity and wind speed are considered through a linear transformation of temperature. A novel weighted interpolation scheme is developed for forecasting of holiday loads, giving improved accuracy. The holiday peak load is first estimated and then the ANNSTLF forecast is re-shaped with the new peak forecast. The performance on data from ten different utilities is reported and compared to the previous generation.

Alireza Khotanzad

Papers

Invariant image recognition by Zernike moments

Classification of invariant image representations using a neural network

A Model-Based Method for Rotation Invariant Texture Classification

A physics-based coordinate transformation for 3-D image matching

ANNSTLF-Artificial Neural Network Short-Term Load Forecaster- generation three