IEEE Transactions on Pattern Analysis and Machine Intelligence

In order for a robot to operate autonomously in its environment, it must be able to perceive its environment and take actions based on these perceptions. Recognizing the functionalities of objects is an important component of this ability. In this paper, we look into a new area of functionality recognition: determining the function of an object from its motion. Given a sequence of images of a know... View full abstract»

To successfully apply character recognition technology most of the forms currently hand-keyed will need to be redesigned. This paper presents results from a comprehensive study of three versions of a redesigned tax form. Analyses show that using separately spaced character boxes provides superior machine readability over fields containing combs and adjoining character boxes. It is shown that chara... View full abstract»

Presents cost estimates for finding the k-nearest neighbors to a test pattern according to a Minkowski p-metric, as a function of the size of the buckets in partitioning searching algorithms. The asymptotic expected number of operations to find the nearest neighbor is presented as a function of the average number of patterns per bucket n and is shown to contain a global minimum View full abstract»

In this paper, we propose a new scheme for off-line recognition of totally unconstrained handwritten numerals using a simple multilayer cluster neural network trained with the backpropagation algorithm and show that the use of genetic algorithms avoids the problem of finding local minima in training the multilayer cluster neural network with gradient descent technique, and improves the recognition... View full abstract»

An approach to the analysis and representation of facial dynamics for recognition of facial expressions from image sequences is presented. The algorithms utilize optical flow computation to identify the direction of rigid and nonrigid motions that are caused by human facial expressions. A mid-level symbolic representation motivated by psychological considerations is developed. Recognition of six f... View full abstract»

This paper investigates real-time bidirectional search (RTBS) algorithms, where two problem solvers, starting from the initial and goal states, physically move toward each other. To evaluate the RTBS performance, two kinds of algorithms are proposed and are compared to real-time unidirectional search. One is called centralized RTBS where a supervisor always selects the best action from all possibl... View full abstract»

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 algorithm that maximizes the likelihood of the model generating the data. This approach h... View full abstract»

Geman and Reynolds (ibid., vol.14, 1992) present an approach to linear image restoration which provides for recovery of horizontal and vertical gray-level discontinuities from blurred and noisy observations. We extend their model and parameter selection method to include diagonal discontinuities. A hazard of this modeling approach is identified and addressed. We also comment on the truncated Gibbs... View full abstract»

Marzal and Vidal (1993) considered the problem of computing the normalized edit distance between two strings, and reported experimental results which demonstrated the use of the measure to recognize hand-written characters. Their paper formulated the theoretical properties of the measure and developed two algorithms to compute it. In this short communication the authors demonstrate how this measur... View full abstract»

Online dynamic signature verification systems were designed and tested. A database of more than 10,000 signatures in (x(t), y(t))-form was acquired using a graphics tablet. We extracted a 42-parameter feature set at first, and advanced to a set of 49 normalized features that tolerate inconsistencies in genuine signatures while retaining the power to discriminate against forgeries. We studied algor... View full abstract»

Current methods for regularizing displacement fields in deformation-fitting problems are sensitive to rotation. We propose a rotation-insensitive regularization functional which is the true strain energy for a rubber-like material. The deformation-fitting problem is solved iteratively using successive approximations of the body's rotation, which may be non-uniform View full abstract»

Nearest neighbour classification expects the class conditional probabilities to be locally constant, and suffers from bias in high dimensions. We propose a locally adaptive form of nearest neighbour classification to try to ameliorate this curse of dimensionality. We use a local linear discriminant analysis to estimate an effective metric for computing neighbourhoods. We determine the local decisi... View full abstract»