A snake is an energy-minimizing spline guided by external constraint forces and influenced by image forces that pull it toward features such as lines and edges. Snakes are active contour models: they lock onto nearby edges, localizing them accurately. Scale-space continuation can be used to enlarge the cap-ture region surrounding a feature. Snakes provide a unified account of a number of visual problems, in-cluding detection of edges, lines, and subjective contours; motion tracking; and stereo matching. We have used snakes successfully for interactive interpretation, in which user-imposed constraint forces guide the snake near features of interest.

Abstract|We present an object recognition system based

We study how to measure the degree of similarity between two image contours. We propose an approach for comparing contours that takes into account deformations in object shape, the articulation of parts, and variations in the shape and size of portions of objects. Our method uses dynamic programming to compute the minimum cost of bringing one shape into the other via local deformations. Using this as a starting point, we investigate the properties that such a cost function should have to model human performance and to perform usefully in a computer vision system. We suggest novel conditions on this cost function that help capture the part-based nature of objects without requiring any explicit decomposition of shapes into their parts. We then suggest several possible cost functions based on different physical models of contours, and describe experiments with these costs. 1 Introduction Detecting similarity is a key tool in interpretating images. In this paper we develop a measure of s...

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 ...

Hand-printed digits can be modeled as splines that are governed by about 8 control points. For each known digit, the control points have preferred "home" locations, and deformations of the digit are generated by moving the control points away from their home locations. Images of digits can be produced by placing Gaussian ink generators uniformly along the spline. Real images can be recognized by nding the digit model most likely to have generated the data. For each digit model we use an elastic matching algorithm to minimize an energy function that includes both the deformation energy of the digit model and the log probability that the model would generate the inked pixels in the image. The model with the lowest total energy wins. If a uniform noise process is included in the model of image generation, some of the inked pixels can be rejected as noise as a digit model is tting a poorly segmented image. The digit models learn by modifying the home locations of the control points.

Despite the success of many pattern recognition systems in constrained domains, problems that involve noisy input and many classes remain difficult. A promising direction is to use several classifiers simultaneously, such that they can complement each other in correctness. This thesis is concerned with decision combination in a multiple classifier system that is critical to its success. A multiple classifier system consists of a set of classifiers and a decision combination function. It is a preferred solution to a complex recognition problem because it allows simultaneous use of feature descriptors of many types, corresponding measures of similarity, and many classification procedures. It also allows dynamic selection, so that classifiers adapted to inputs of a particular type may be applied only when those inputs are encountered. Decisions by the classifiers are represented as rankings of the class set that are derivable from the results of feature matching. Rank scores contain more ...

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.

Abstract. We propose a general method for finding pointwise correspondence between 2-D shapes based on the concept of order structure and using geometric hashing. The problem of finding correspondence and the problem of establishing shape equivalence can be considered as one and the same problem. Given shape equivalence, we can in general find pointwise correspondence and the existence of a unambiguous correspondence mapping can be used as a rule for deciding shape equivalence. As a measure of shape equivalence we will use the concept of order structure which in principle can be defined for arbitrary geometric configurations such as points lines and curves. The order structure equivalence of subsets of points and tangent directions of a shape is will be used to establish pointwise correspondence. The finding of correspondence between different views of the same object and different instances of the same object category can be used as a foundation for establishment and recognition of visual categories. 1

A biologically motivated compute intensive approach to computer vision is developed and applied to the problem of face recognition. The approach is based on the use of twodimensional Gabor functions that fit the receptive fields of simple cells in the primary visual cortex of mammals. A descriptor set that is robust against translations is extracted by a global reduction operation and used for a search in an image database. The method was applied on a database of 205 face images of 30 persons and a recognition rate of 94% was achieved.

We describe a new approach to the visual recognition of cursive handwriting. An effort is made to attain humanlike performance by using a method based on pictorial alignment and on a model of the process of handwriting. The alignment approach permits recognition of character instances that appear embedded in connected strings. A system embodying this approach has been implemented and tested on five different word sets. The performance was stable both across words and across writers. The system exhibited a substantial ability to interpret cursive connected strings without recourse to lexical knowledge.