Abstract-Over the last 20 years, several different techniques have been proposed for computer recognition of human faces. The purpose of this paper is to compare two simple but general strategies on a common database (frontal images of faces of 47 people: 26 males and 21 females, four images per person). We have developed and implemented two new algorithms; the first one is based on the computation of a set of geometrical features, such as nose width and length, mouth position, and chin shape, and the second one is based on almost-grey-level template matching. The results obtained on the testing sets (about 90 % correct recognition using geometrical features and perfect recognition using template matching) favor our implementation of the template-matching approach. Index Terms-Classification, face recognition, Karhunen-Loeve expansion, template matching.

We describe a method of recognizing handwritten digits by fitting generative models that are built from deformable B-splines with Gaussian "ink generators" spaced along the length of the spline. The splines are adjusted using a novel elastic matching procedure based on the Expectation Maximization (EM) algorithm that maximizes the likelihood of the model generating the data. This approach has many advantages. (1) After identifying the model most likely to have generated the data, the system not only produces a classification of the digit but also a rich description of the instantiation parameters which can yield information such as the writing style. (2) During the process of explaining the image, generative models can perform recognition driven segmentation. (3) The method involves a relatively small number of parameters and hence training is relatively easy and fast. (4) Unlike many other recognition schemes it does not rely on some form of pre-normalization of input images, but can ...

Several different techniques have been proposed for computer recognition of human faces. This paper presents the first results of an ongoing project to compare several recognition strategies on a common database. A set of algorithms has been developed to assess the feasibility of recognition using a vector of geometrical features, such as nose width and length, mouth position and chin shape. The performance of a Nearest Neighbor classifier, with a suitably defined metric, is reported as a function of the number of classes to be discriminated (people to be recognized) and of the number of examples per class. Finally, performance of classification with rejection is investigated.

This paper proposes to incorporate full covariance matrices into the radial basis function (RBF) networks and to use the Expectation-Maximization (EM) algorithm to estimate the basis function parameters. The resulting networks, referred to as elliptical basis function (EBF) networks, are evaluated through a series of text-independent speaker verification experiments involving 258 speakers from a phonetically balanced, continuous speech corpus (TIMIT). We propose a verification procedure using RBF and EBF networks as speaker models and show that the networks are readily applicable to verifying speakers using LP-derived cepstral coefficients as features. Experimental results show that small EBF networks with basis function parameters estimated by the EM algorithm outperform the large RBF networks trained in the conventional approach. The results also show that the equal error rate achieved by the EBF networks is about two-third of that achieved by the VQ-based speaker models. Keywords: ...

viii 1 Introduction 1 1.1 Handwritten Character Recognition : : : : : : : : : : : : : : : : : 1 1.2 Related Work : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 4 1.2.1 Feature Extraction : : : : : : : : : : : : : : : : : : : : : : 4 1.2.2 Handwriting Recognition : : : : : : : : : : : : : : : : : : : 6 1.3 Proposed Approach : : : : : : : : : : : : : : : : : : : : : : : : : : 9 1.4 Thesis Organization : : : : : : : : : : : : : : : : : : : : : : : : : : 12 2 Recognition and Representation of Numeral Patterns 13 2.1 Recognition Based on Human Logical Understanding : : : : : : : 13 2.1.1 Local Geometric Shape Features : : : : : : : : : : : : : : : 14 2.1.2 Learning of Different Contributions Among Local Shape Features : : : : : : : : : : : : : : : : : : : : : : : : : : : : 17 2.1.3 Learning of New Variants by Feature Generation : : : : : 17 2.2 Invariance Based on Biological Visual System : : : : : : : : : : : 18 2.2.1 Log-Polar Transformation : : : : : : : : : : : : : : : : :...

This thesis investigates feedforward neural networks in the context of classification tasks with respect to the detection of patterns that do not belong to the same categories of patterns used to train the network. This refers to the problem of the detection and/or rejection of spurious or novel patterns. In particular, the multilayer perceptron network (MLP) trained with the backpropagation algorithm is examined in this respect and different strategies for improving its performance in the detection of spurious patterns are considered. The problem is investigated from different points of view that vary from the modification of the multilayer perceptron network with different configurations that make it more intrinsically able to detect spurious information, to the introduction of novel auxiliary mechanisms which, when integrated with the MLP network, can provide an overall enhancement in the system's rejection capabilities. These different network configurations are examined with respe...

Up-propagation is an algorithm for inverting and learning neural network generative models. Sensory input is processed by inverting a model that generates patterns from hidden variables using top-down connections. The inversion process is iterative, utilizing a negative feedback loop that depends on an error signal propagated by bottom-up connections. The error signal is also used to learn the generative model from examples. The algorithm is benchmarked against principal component analysis in experiments on images of handwritten digits. In his doctrine of unconscious inference, Helmholtz argued that perceptions are formed by the interaction of bottom-up sensory data with top-down expectations. According to one interpretation of this doctrine, perception is a procedure of sequential hypothesis testing. We propose a new algorithm, called up-propagation, that realizes this interpretation in layered neural networks. It uses top-down connections to generate hypotheses, and bottom-up connect...

We describe an alternate approach to visual recognition of handwritten words, wherein an image is converted into a spatio-temporal signal by scanning it in one or more directions, and processed by a suitable connectionist network. The scheme offers several attractive features including shift-invariance, explication of local spatial geometry along the scan direction, a significant reduction in the number of free parameters, the ability to process arbitrarily long images along the scan direction, and a natural framework for dealing with the segmentation/recognition dilemma. Other salient features of the work include the use of a modular and structured approach for network construction and the integration of connectionist components with a procedural component to exploit the complementary strengths of both techniques. The system consists of two connectionist components and a procedural controller. One network concurrently makes recognition and segmentation hypotheses, and another...

INTRODUCTION Pattern Recognition (PR) addresses the problem of classifying objects, often represented as vectors or as strings of symbols, into categories. The difficulty is to synthesize, and then to efficiently compute, the classification function that maps objects to categories, given that objects in a category can have widely varying input representations. In most instances, the task is known to the designer through a set of example patterns whose categories are known, and through general, a priori knowledge about the task, such as: "the category of an object is not changed when the object is slightly translated or rotated in space". Historically, the field of PR started with the early efforts in Neural Networks (Perceptrons, Adalines...). While in the past, NNs have somewhat played the role of an outsider in PR, the recent progress in learning algorithms (and the availability of powerful hardware) have made them the method of choice for many PR applications

The purpose of this paper is to present a complete methodology based on a multidisciplinary approach, that goes from the extraction of features till the classification of a set of different portuguese granites. The set of tools to extract the features that characterise polished surfaces of the granites is mainly based on mathematical morphology. The classification methodology is based on a genetic algorithm capable of search the input feature space used by the nearest neighbour rule classifier. Results show that is adequate to perform feature reduction and simultaneous improve the recognition rate. Moreover, the present methodology represents a robust strategy to understand the proper nature of the images treated, and their discriminant features.