Over the last 30 years, scale space representations have emerged as a fundamental tool for allowing systems to become increasingly robust against changes in camera viewpoint. Unfortunately, the implementation details that are required to properly construct a scale space representation are not published in the literature. Incorrectly implementing these details will lead to extremely poor system performance. In this paper, we address the practical considerations associated with scale space representations. Our focus is to make explicit how a scale space is constructed, thereby increasing the accessibility of this powerful representation to developers of computer vision systems.

Current approaches to script identification rely onhand-selected features and often require processing a significantpart of the document to achieve reliable identification.We present an approach that applies a large pool ofimage features to a small training sample and uses subsetfeature selection techniques to automatically select a subsetwith the most discriminating power. At run time we usea classifier coupled with an evidence accumulation engineto report a script label once a preset likelihood thresholdhas been reached. We apply the system to a diverse corpusof printed Russian and English documents that suffer fromcommon degradation problems. Our validation studyshows promising results both in terms of the script identificationaccuracy and the ability to identify script on thescale of individual words and text lines.

As object recognition algorithms focus more closely on appearance, the problem of how best to measure similarity between images becomes critical. Within the context of an existing object recognition system, we present an empirical comparison of 27 different error functions on a set of 20 example problems. Each error function measures the similarity between an observed and a predicted image. Our goal is to select an error best suited to guide an heuristic search algorithm through a space of possible scene configurations.

There is a long tradition of using heuristic search within the context of object recognition. However, most of these techniques rely solely on object geometry and are based on matching model features to data features. We present a novel approach for using search coupled with an error function based on graphical rendering. An empirical approach is used to evaluate five different search algorithms on a set of 20 example problems.

Color is a powerful cue for determining the pose of 3D objects viewed by a single camera. We present a method based on hue histograms for locating multiple objects with respect to a fixed camera. The algorithm is tested on controlled blocks-world scenes and an indoor office scene. On these examples, a pose refinement algorithm performs better when guided by color than when guided by more traditional edge information.

Most model-based object recognition algorithms attempt to match stored model features to features extracted from imagery. The better the match, the more likely it is that the object is present in the scene. Problems arise when objects are occluded because matches will be incomplete. It is rare for an object recognition algorithm to employ knowledge to explain the absence of occluded features. The work presented here illustrates an approach to object recognition which propagates evidence of occlusion from range to optical sensors and thereby explains missing features.

This paper presents a three-dimensional (3-D) model-based ATR algorithm that operates simultaneously on imagery from three heterogeneous, approximately boresight aligned sensors. An iterative search matches models to range and optical imagery by repeatedly predicting detectable features, measuring support for these features in the imagery, and adjusting the transformations relating the target to the sensors in order to improve the match. The result is a locally optimal and globally consistent set of 3-D transformations that precisely relate the best matching target features to combined range, IR, and color images. Results show the multisensor algorithm recovers 3-D target pose more accurately than does a traditional single-sensor algorithm. Errors in registration between images are also corrected during matching. The intended application is imaging from semiautonomous military scout vehicles.

The object recognition, system presented combines on-line feature prediction with an iterative multisensor matching algorithm. Matching begins with an initial object type and pose hypothesis. An iterative generate-and-test procedure then refines the pose as well as the sensor-to-sensor registration for separate range and electro optical sensors. During matching, object features predicted to be visible are updated to reflect changes in hypothesized object pose and sensor registration. The match found is locally optimal in terms of the complete space of possible matches and globally consistent in the sense of preserving the 3D constraints implied by sensor and object geometry. Results on real data are presented which demonstrate the algorithm correcting for up to 30/spl deg/ errors in initial orientation and 5 m errors in initial translation.