. 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...

We suggest the use of the color correlogram as a generic indexing tool to tackle various computer vision problems. Correlograms were shown to be very effective for contentbased image retrieval [4]. We adapt the correlogram to handle the problems of image subregion querying, object localization, object tracking, and cut detection. Experimental results suggest that the color correlogram is much more effective than the histogram for these applications, with insignificant additional computational, storage, or processing cost. We also provide a technique to cut down the storage requirement of correlograms so that it is the same as that of histograms, with only negligible performance penalty compared to the original correlogram. 1

Several color object irecognition methods that are based on image retrieva1 algorithms attempt to discount changes of illuminlztion in order to increase performance when test image illumination conditions differ from those that obtained when the image database was created. Here we extend the seminal method of Swain and Ballard to discount changing illumination. The new method is based on the first stage of the simplest color indexing medhod, which uses angular invariants between color image and edge image channels. That method Jirst normalizes image channels, and then effectively discards much of the remaining information. Here we adopt the color-normalization stage as an adequate color constancy step. Further, we replace 30 color histograms by 20 chromaticity histograms. Treating these as images, we implement the method in a compressed histogram-image domain using a combination of wavelet compression and Discrete Cosine Transform (DCT to fully exploit the technique of low-pass filtering / or eficiency. Results are very.encouraging, wath substantially better performance than other methods tested. The method is also fast, in that the indexing process is entirely carried out in the compressed domain and uses a feature vector of only 36 or 72 values.

Object recognition systems aiming to work in real world settings should use multiple cues in order to achieve robustness. We present a new cue integration scheme which extends the idea of cue accumulation to discriminative classifiers. We derive and test the scheme for Support Vector Machines (SVMs), but we also show that it is easily extendible to any large margin classifier. Interestingly, in the case of one-class SVMs, the scheme can be interpreted as a new class of Mercer kernels for multiple cues. Experimental comparison with a probabilistic accumulation scheme is favorable to our method. Comparison with voting scheme shows that our method may suffer as the number of object classes increases. Based on these results, we propose a recognition algorithm consisting of a decision tree where decisions at each node are taken using our accumulation scheme. Results obtained using this new algorithm compare very favorably to accumulation (both probabilistic and discriminative) and voting scheme. 1

Abstract not found

Images or videos may be imaged under different illuminants than models in an image or video proxy database. Changing illumination color in particular may confound recognition algorithms based on color histograms or video segmentation routines based on these. Here we show that a very simple method of discounting illumination changes is adequate for both image retrieval and video segmentation tasks. We develop a feature vector of only 36 values that can also be em used for both these objectives as well as for retrieval of video proxy images from a database. The new image metric is based on a color-channel-normalization step, followed by reduction of dimensionality by going to a chromaticity space. Treating chromaticity histograms as images, we perform an effective low-pass filtering of the histogram by first reducing its resolution via a wavelet-based compression and then by a DCT transformation followed by zonal coding. We show that the color constancy step -- color band normalization -- can...

Several color object recognition methods that are based on image retrieval algorithms attempt to discount changes of illumination in order to increase performance when test image illumination conditions differ from those that obtained when the image database was created. Here we investigate under what general conditions illumination change can be described using a simple linear transform among RGB channels, for a multi--colored object, and adduce a different underlying principle than that usually suggested. The resulting new method, the Linear Color algorithm, is more accurately illuminant--invariant than previous methods. An implementation of the method uses a combination of wavelet compression and DCT transform to fully exploit the technique of low--pass filtering for efficiency. Results are very encouraging, with substantially better performance than other methods tested. The method is also fast, in that the indexing process is entirely carried out in the compressed domain and uses a feature vector of only 63 integers. 1

This paper presents a general method to retrieve images from large databases using images as queries. The method is based on local characteristics which are robust to the group of similarity transformations in the image. Images can be retrieved even if they are translated, rotated or scaled. Due to the locality of the characterization, images can be retrieved even if only a small part of the image is given as well as in the presence of occlusions. A voting algorithm, following the idea of a Hough transform, and semi-local constraints allow us to develop a new method which is robust to noise, to scene clutter and small perspective deformations. Experiments show an efficient recognition for different types of images. The approach has been validated on an image database containing 1020 images, some of them being very similar by structure, texture or shape. 1 Introduction Image retrieval is an important problem for accessing large image databases. We address the problem of retrie...

We introduce a new algorithm for identifying objects in cluttered images, based on approximate subgraph matching. This algorithm is robust under mode rate variations in the camera viewpoints. In other words, it is expected to recognize an object (whose mod e# is de rive d from a t e# plate image# in ase#J) h image# e ve n whe n the came ras of the te mplate and se#zz h image# are substantially di#e re# t. The algorithm re# re#IJ ts the obje#z( in the te#z late andse#(' himage# by we#)z te# adjace ncy graphs. The n the proble m of re cognizing the te mplate obje ct in the se#I' h image is re# uc e# to the proble# of approximat e#1 matching the te mplate graph as a subgraph of the se#(# h image graph. The matching proce dure is some what inse nsitive to minor graph variations, thus leading to a recognition algorithm which is robust with resoect to camera variations.

This thesis presents a method to efficiently recognize 3D objects from single, 2D images by the use of a novel, probabilistic indexing technique. Indexing is a two-stage process that includes an offline training stage and a runtime lookup stage. During training, feature vectors representing object appearance are acquired from several points of view about each object and stored in the index. At runtime, for each image feature vector detected, a small set of the closest model vectors is recovered from the index and used to form match hypotheses. This set of nearest neighbours provides interpolation between the nearby training views of the objects, and is used to compute probability estimates that proposed matches are correct. The overall recognition process becomes extremely efficient when hypotheses are verified in order of their probabilities. Contributions of this thesis include the use of an indexing data structure (the kd-tree) and search algorithm (Best-Bin First search) which, un...