A central problem in object recognition is to determine the transformation that relates the model to the image, given some partial correspondence between the two. This is useful in determining whether an object is present in an image, and if so, determining where the object is. We present a novel method of solving this problem that uses region information. In our approach the model is divided into volumes, and the image is divided into regions. Given a match between subsets of volumes and regions (without any explicit correspondence between different pieces of the regions) the alignment transformation is computed. The method applies to planar objects under similarity, affine, and projective transformations and to projections of 3-D objects undergoing affine and projective transformations. 1 Introduction A fundamental problem in recognition is pose estimation. Given a correspondence between some portions of an object model and some portions of an image, determine the transformation th...

. Many recognition procedures rely on the consistency of a subset of data features with an hypothesis, as the sufficient evidence to the presence of the corresponding object. The performance of such procedures are analyzed using a probabilistic model and provide expressions for the sufficient size of such data subsets, that, if consistent, guarantee the validity of the hypotheses with arbitrarily prespecified confidence. The analysis focuses on 2D objects and on the affine transformation class, and is based, for the first time, on an integrated model, which takes into account the shape of the objects involved, the accuracy of the data collected, the clutter present in the scene, the class of the transformations involved, the accuracy of the localization, and the confidence required in the hypotheses. Most of these factors can be quantified cumulatively by one parameter, denoted "effective similarity", which largely determines the sufficient subset size. 1 Introduction Model-Based obje...

Robust recognition systems require a careful understanding of the effects of error in sensed features. Error in these image features results in uncertainty in the possible image location of each additional model feature. We present an accurate, analytic approximation for this uncertainty when model poses are based on matching three image and model points. This result applies to objects that are fully threedimensional, where past results considered only twodimensional objects. Further, we introduce a linear programming algorithm to compute this uncertainty when poses are based on any number of initial matches. 1 Introduction Object recognition systems frequently hypothesize a known object's pose based on matching a small number of the object's features to features in the image (e.g., [7, 14, 17, 10]). To confirm the hypothesis, they commonly use the pose to look for additional matches. A fundamental question in building robust recognition systems is how noise in the matched image feat...

Model-Based object recognition is a fundamentnal task of Computer Vision. In this paper we consider the performance of the popular geometric hashing (GH) algorithm for model based recognition and, in a probabilistic setting, examine the influence of some design decisions and derive several tradeoffs between two measures of performance: reliability and time complexity. We also propose a variation of the GH algorithm, which alleviates some of its inherent problems and demonstrate its enhanced performance in experiments. 1. Introduction The geometric hashing algorithm [9] is a fast implementation of the alignment approach to recognition, which tests all model bases together and alleviate the needs for explicitly aligning the model and for counting the number of image points consistent with it. The GH algorithm relies of the invariance property of affine coordinates relative to the affine transformation: consider a set of planar points, and specify three non-collinear points p 0 ; p 1 and...