A face recognition system must recognize a face from a novel image despite the variations between images of the same face. A common approach to overcoming image variations because of changes in the illumination conditions is to use image representations that are relatively insensitive to these variations. Examples of such representations are edge maps, image intensity derivatives, and images convolved with 2D Gabor-like filters. Here we present an empirical study that evaluates the sensitivity of these representations to changes in illumination, as well as viewpoint and facial expression. Our findings indicated that none of the representations considered is sufficient by itself to overcome image variations because of a change in the direction of illumination. Similar results were obtained for changes due to viewpoint and expression. Image representations that emphasized the horizontal features were found to be less sensitive to changes in the direction of illumination. However, systems...

. The appearance of an object is composed of local structure. This local structure can be described and characterized by a vector of local features measured by local operators such as Gaussian derivatives or Gabor filters. This article presents a technique where appearances of objects are represented by the joint statistics of such local neighborhood operators. As such, this represents a new class of appearance based techniques for computer vision. Based on joint statistics, the paper develops techniques for the identification of multiple objects at arbitrary positions and orientations in a cluttered scene. Experiments show that these techniques can identify over 100 objects in the presence of major occlusions. Most remarkably, the techniques have low complexity and therefore run in real-time. 1. Introduction The paper proposes a framework for the statistical representation of the appearance of arbitrary 3D objects. This representation consists of a probability density function or jo...

Shape indexing is a way of making rapid associations between features detected in an image and object models that could have produced them. When model databases are large, the use of high-dimensional features is critical, due to the improved level of discrimination they can provide. Unfortunately, finding the nearest neighbour to a query point rapidly becomes inefficient as the dimensionality of the feature space increases. Past indexing methods have used hash tables for hypothesis recovery, but only in low-dimensional situations. In this paper, we show that a new variant of the k-d tree search algorithm makes indexing in higherdimensional spaces practical. This Best Bin First, or BBF, search is an approximate algorithm which finds the nearest neighbour for a large fraction of the queries, and a very close neighbour in the remaining cases. The technique has been integrated into a fully developed recognition system, which is able to detect complex objects in real, cluttered scenes in just a few seconds.

The classical way of attempting to solve the face (or object) recognition problem is by using large and representative datasets. In many applications though, only one sample per class is available to the system. In this contribution, we describe a probabilistic approach that is able to compensate for imprecisely localized, partially occluded and expression variant faces even when only one single training sample per class is available to the system. To solve the localization problem, we find the subspace (within the feature space, e.g. eigenspace) that represents this error for each of the training images. To resolve the occlusion problem, each face is divided into k local regions which are analyzed in isolation. In contrast with other approaches, where a simple voting space is used, we present a probabilistic method that analyzes how "good" a local match is. To make the recognition system less sensitive to the differences between the facial expression displayed on the training and the testing images, we weight the results obtained on each local area on the bases of how much of this local area is affected by the expression displayed on the current test image.

. This paper examines statistical approaches to model-based object recognition. Evidence is presented indicating that, in some domains, normal (Gaussian) distributions are more accurate than uniform distributions for modeling feature fluctuations. This motivates the development of new maximum-likelihood and MAP recognition formulations which are based on normal feature models. These formulations lead to an expression for the posterior probability of the pose and correspondences given an image. Several avenues are explored for specifying a recognition hypothesis. In the first approach, correspondences are included as a part of the hypotheses. Search for solutions may be ordered as a combinatorial search in correspondence space, or as a search over pose space, where the same criterion can equivalently be viewed as a robust variant of chamfer matching. In the second approach, correspondences are not viewed as being a part of the hypotheses. This leads to a criterion that is a smooth funct...

this article, please send e-mail to: tpami@computer.org, and reference IEEECS Log Number 107780

Invariance under a group of 3D transformations seems a desirable component of an efficient 3D shape representation. We propose representations which are invariant under weak perspective to either rigid or affine 3D transformations, and we show how they can be computed efficiently from a sequence of images with a linear and incremental algorithm. We show simulated results with perspective projection and noise, and the results of model acquisition from a real sequence of images. The use of linear computation, together with the integration through time of invariant representations, offers improved robustness and stability. Using these invariant representations, we derive model-based projective invariant functions of general 3D objects. We discuss the use of the model-based invariants with existing recognition strategies: alignment without transformation, and constant time indexing from 2D images of general 3D objects.

Hierarchical image structures are abundant in computer vision and have been used to encode part structure, scale spaces, and a variety of multiresolution features. In this paper, we describe a framework for indexing such representations that embeds the topological structure of a directed acyclic graph (DAG) into a low-dimensional vector space. Based on a novel spectral characterization of a DAG, this topological signature allows us to efficiently retrieve a promising set of candidates from a database of models using a simple nearest-neighbor search. We establish the insensitivity of the signature to minor perturbation of graph structure due to noise, occlusion, or node split/merge. To accommodate large-scale occlusion, the DAG rooted at each nonleaf node of the query "votes" for model objects that share that "part," effectively accumulating local evidence in a model DAG's topological subspaces. We demonstrate the approach with a series of indexing experiments in the domain of view-based 3D object recognition using shock graphs.

AbstractÐWe present a method of indexing three-dimensional objects from single two-dimensional images. Unlike most other methods to solve this problem, ours does not rely on invariant features. This allows a richer set of shape information to be used in the recognition process. We also suggest the kd-tree as an alternative indexing data structure to the standard hash table. This makes hypothesis recovery more efficient in high-dimensional spaces, which are necessary to achieve specificity in large model databases. Search efficiency is maintained in these regimes by the use of Best-Bin First search, a modified kd-tree search algorithm which locates approximate nearest-neighbors. Neighbors recovered from the index are used to generate probability estimates, local within the feature space, which are then used to rank hypotheses for verification. On average, the ranking process greatly reduces the number of verifications required. Our approach is general in that it can be applied to any real-valued feature vector. In addition, it is straightforward to add to our index information from real images regarding the true probability distributions of the feature groupings used for indexing. In this paper, we provide experiments with both synthetic and real images, as well as details of the practical implementation of our system, which has been applied in the domain of telerobotics. Index TermsÐModel-based object recognition; indexing; kd-tree algorithm; nearest-neighbors algorithm. 1

Abstract—We present five performance measures to evaluate grouping modules in the context of constrained search and indexing based object recognition. Using these measures, we demonstrate a sound experimental framework, based on statistical ANOVA tests, to compare and contrast three edge based organization modules, namely, those of Etemadi et al., Jacobs, and Sarkar-Boyer in the domain of aerial objects using 50 images. With adapted parameters, the Jacobs module performs overall the best for constraint based recognition. For fixed parameters, the Sarkar-Boyer module is the best in terms of recognition accuracy and indexing speedup. Etemadi et al.’s module performs equally well with fixed and adapted parameters while the Jacobs module is most sensitive to fixed and adapted parameter choices. The overall performance ranking of the modules is Jacobs, Sarkar-Boyer, and Etemadi et al. Index Terms—Perceptual organization, performance evaluation, analysis of variance, ANOVA, experimental vision, intermediate level computer vision, feature grouping, performance characterization. 1