Abstract—This paper addresses the problem of retrieving images from large image databases. The method is based on local grayvalue invariants which are computed at automatically detected interest points. A voting algorithm and semilocal constraints make retrieval possible. Indexing allows for efficient retrieval from a database of more than 1,000 images. Experimental results show correct retrieval in the case of partial visibility, similarity transformations, extraneous features, and small perspective deformations. Index Terms—Image retrieval, image indexing, graylevel invariants, matching, interest points. 1

A computer vision system has been implemented that can recognize threedimensional objects from unknown viewpoints in single gray-scale images. Unlike most other approaches, the recognition is accomplished without any attempt to reconstruct depth information bottom-up from the visual input. Instead, three other mechanisms are used that can bridge the gap between the two-dimensional image and knowledge of three-dimensional objects. First, a process of perceptual organization is used to form groupings and structures in the image that are likely to be invariant over a wide range of viewpoints. Second, a probabilistic ranking method is used to reduce the size of the search space during model based matching. Finally, a process of spatial correspondence brings the projections of three-dimensional models into direct correspondence with the image by solving for unknown viewpoint and model parameters. A high level of robustness in the presence of occlusion and missing data can be achieved through full application of a viewpoint consistency constraint. It is argued that similar mechanisms and constraints form the basis for recognition in human vision. This paper has been published in Artificial Intelligence, 31, 3 (March 1987), pp. 355–395. 1 1

This paper presents a comparative study and survey of model-based object-recognition algorithms for robot vision. The goal of these algorithms is to recognize the identity, position, and orientation of randomly oriented industrial parts. In one form this is commonly referred to as the “bin-picking ” problem, in which the parts to be recognized are presented in a jumbled bin. The paper is organized according to 2-D, 2&D, and 3-D object representations, which are used as the basis for the recognition algorithms. Three

This paper discusses how local measurements of three-dimensional pool[ions and surface normals (recorded by a set of tactile sensors, or by threedimensional range sensors), may be used o identify and locate objects, from among a set, of known objects. The objects are modeled as po!yhedra having up to six degrees of freedom relative to the sensors. We show tiat inconsistent, hypotheses about pairings between sensed points and object, surfaces can be discarded efficiently by using local constraints on: distoances bet,ween faces, angles betwee, face normals, and angles (reiatAve to t. he surface normals) of vectors between sensed points. We show by simulation and by mathematical bounds that the number of hypotheses consisten; with these constraints is small. We also show how to recover the position and orient, at, ion of the object from the sense daiwa. The algorithm's performance on data obt,ained from a triangulation range sensor is illustrated.

Contents 1 Introduction 2 1.1 Notations and Definitions . . . . . . . . . . . . . . . . . . . . . . . . 3 2 Problem Formulations 4 2.1 Integer Programming Formulations . . . . . . . . . . . . . . . . . . . 5 2.2 Continuous Formulations . . . . . . . . . . . . . . . . . . . . . . . . 8 3 Computational Complexity 12 4 Bounds and Estimates 15 5 Exact Algorithms 19 5.1 Enumerative Algorithms . . . . . . . . . . . . . . . . . . . . . . . . . 19 5.2 Exact Algorithms for the Unweighted Case . . . . . . . . . . . . . . 21 5.3 Exact Algorithms for the Weighted Case . . . . . . . . . . . . . . . . 25 6 Heuristics 27 6.1 Sequential Greedy Heuristics . . . . . . . . . . . . . . . . . . . . . . 28 6.2 Local Search Heuristics . . . . . . . . . . . . . . . . . . . . . . . . . 29 6.3 Advanced Search Heuristics . . . . . . . . . . . . . . . . . . . . . . . 30 6.3.1 Simulated annealing . . . . . . . . . . . . . . . . . . . . . . . 30 6.3.2 Neural networks . . . . . . . . . . . . . . . . . . . . . . . .

Abstract | This paper addresses the problem of retrieving images from large image databases. The method is based on local greyvalue invariants which are computed at automatically detected interest points. Avoting algorithm and semi-local constraints make retrieval possible. Indexing allows for e cient retrieval from a database of more than 1000 images. Experimental results show correct retrieval in the case of partial visibility, similarity transformations, extraneous features, and small perspective deformations.

Abstract-In this paper we propose a method to solve the stereo cor-respondence problem. The method matches features and feature rela-tionships and can be paraphrased as follows. Linear edge segments are extracted from both the left and right images. Each such segment is characterized by its position and orientation in the image as well as its relationships with the nearby segments. A relational graph is thus built from each image. For each segment in one image a set of potential assignments in the other image is determined. These assignments are represented as nodes in a correspondence graph. Arcs in this graph rep-resent compatible assignments established on the basis of segment re-lationships. Stereo matching becomes equivalent to searching for sets of mutually compatible nodes in this graph. These sets are found by looking for maximal cliques. The maximal clique the best suited to rep-resent a stereo correspondence is selected using a benefit function. Fi-nally we show numerous results obtained with this method. Index Terms-Feature-based matching, feature grouping, geometric constraints, maximal cliques, stereo vision, subgraph isomorphism. T I.

Abstract-This paper introduces an analytical framework for studying some properties of model acquisition and recognition techniques based on indexing. The goal is to demonstrate that several problems previously associated with the approach can be attributed to the low dimensionality of invariants used. These include limited index selectivity, excessive accumulation of votes in the look-up table buckets, and excessive sensitivity to quantization parameters. Theoretical results demonstrate that using high-dimensional, highly descriptive global invariants produces better results in terms of accuracy, false positive suppression, and computation time. A practical example of high-dimensional global invariants is introduced and used to implement a 2-D shape acquisitionhecognition system. The acquisitiodrecognition system is based on a two-step table look-up mechanism. First, local curve descriptors are obtained by correlating image contour information at short range. Then, seven-dimensional global invariants are computed by correlating triplets of local curve descriptors at longer range. This experimental system is meant to illustrate the behavior of a high-dimensional indexing scheme. Indeed, its performance shows good agreement with the analytical model with respect to database size, fault tolerance, and recognition speed. Model acquisition time is linear to cubic in the number of object features. Object recognition time is constant to linear in the number of models in the database and linear to cubic in the number of features in the image. The system has been tested extensively, with more than 250 arbitrary shapes in the database. Unsupervised shape and subpart acquisition is demonstrated. I.

This paper presents a method for automatically registering multiple three dimensional (3D) data sets. Previous approaches required manual specification of initial pose estimates or relied on external pose measurement systems. In contrast, our method does not assume any knowledge of initial poses or even which data sets overlap. Our automatic registration algorithm begins by converting the input data into surface meshes, which are pair-wise registered using a surface matching engine. The resulting matches are tested for surface consistency, but some incorrect matches may be locally undetectable. A global optimization process searches a graph constructed from these potentially faulty pair-wise matches for a connected sub-graph containing only correct matches, employing a global consistency measure to detect incorrect, but locally consistent matches. From this sub-graph, the final poses of all views can be computed directly. We apply our algorithm to the problem of 3D digital reconstruction of real world objects and show results for a collection of automatically digitized objects.

This paper continues ou,' work' on vlsuM representations of three-dimensional surfaces [Brady and Yuille 1984b]. The theoretical component o our work is a study of classes of surface curves as a source of constraint on the surface on which they lie, and as a basis for describing it. We analyze bounding contours, sin face intersections, lines of cunature, and asymptotes. Our experimental work hives.igates whether the information suggested by our theoretical study can be computed reliably mid efficiently. We demonstrate algorithms that compute lines of curvature of a (Gaussian smoothed) surface; determine planar patches and umbi!ic regions; extract axes of surfaces of revolution and tube surfaces. We report preliminary results on adapting the curvature primM sketch algorithms of Asada and Brady [1984] to detect and describe surface intersections. () Massachusetts Institute of Technology, 1984 This report describes research done at the Artificial Intelligeice Laboratory of the Massachusetts Institute of Technology. Support for the ]aboratory's Artificial Intelligence reseat.oh is provided in par. by the Adwmced Research Projects Agency of the Department of Defense under Office of Naval Research contract N00014-80-C-0505, the Office of Nax'al Research under contract number N000t4-77-C-0389, ,and the System Development Foundation. This wcrk was done while Haruo Asada was a visiting scientist at MIT on leave from Toshiba Corporation, Japan, and while Jean Ponce was a visking s.ientist on leave from I.'RIA, Paris, Fro,nee. ' Pr't of (t6:7)