This paper presents a method for extracting distinctive invariant features from images, which can be used to perform reliable matching between different images of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a a substantial range of affine distortion, addition of noise, change in 3D viewpoint, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through leastsquares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.

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

We describe two new color indexing techniques. The first one is a more robust version of the commonly used color histogram indexing. In the index we store the cumulative color histograms. The L 1 -, L 2 -, or L1 -distance between two cumulative color histograms can be used to define a similarity measure of these two color distributions. We show that while this method produces only slightly better results than color histogram methods, it is more robust with respect to the quantization parameter of the histograms. The second technique is an example of a new approach to color indexing. Instead of storing the complete color distributions, the index contains only their dominant features. We implement this approach by storing the first three moments of each color channel of an image in the index, i.e., for a HSV image we store only 9 floating point numbers per image. The similarity function which is used for the retrieval is a weighted sum of the absolute differences between corresponding mo...

. 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 present a real-time face tracker in this paper. The system has achieved a rate of 30+ frames/second using an HP-9000 workstation with a framegrabber and a Canon VC-C1 camera. It can track a person’s face while the person moves freely (e.g., walks, jumps, sits down and stands up) in a room. Three types of models have been employed in developing the system. First, we present a stochastic model to characterize skin-color distributions of human faces. The information provided by the model is sufficient for tracking a human face in various poses and views. This model is adaptable to different people and different lighting conditions in real-time. Second, a motion model is used to estimate image motion and to predict search window. Third, a camera model is used to predict and to compensate for camera motion. The system can be applied to tele-conferencing and many HCI applications including lip-reading and gaze tracking. The principle in developing this system can be extended to other tracking problems such as tracking the human hand. 1

Color histograms are used to compare images in many applications. Their advantages are efficiency, and insensitivity to small changes in camera viewpoint. However, color histograms lack spatial information, so images with very di#erent appearances can have similar histograms. For example, a picture of fall foliage might contain a large number of scattered red pixels

Abstract—This paper is concerned with the derivation of a progression of shadow-free image representations. First, we show that adopting certain assumptions about lights and cameras leads to a 1D, gray-scale image representation which is illuminant invariant at each image pixel. We show that as a consequence, images represented in this form are shadow-free. We then extend this 1D representation to an equivalent 2D, chromaticity representation. We show that in this 2D representation, it is possible to relight all the image pixels in the same way, effectively deriving a 2D image representation which is additionally shadow-free. Finally, we show how to recover a 3D, full color shadow-free image representation by first (with the help of the 2D representation) identifying shadow edges. We then remove shadow edges from the edge-map of the original image by edge in-painting and we propose a method to reintegrate this thresholded edge map, thus deriving the sought-after 3D shadow-free image. Index Terms—Shadow removal, illuminant invariance, reintegration. 1

Abstract. This paper studies a statistical skin-color model and its adaptation. It is revealed that (1) human skin colors cluster in a small region in a color space; (2) the variance of a skin color cluster can be reduced by intensity normalization, and (3) under a certain lighting condition, a skin-color distribution can be characterized by amultivariate normal distribution in the normalized color space. We then propose an adaptive model to characterize human skin-color distributions for tracking human faces under di erent lighting conditions. The parameters of the model are adapted based on the maximum likelihood criterion. The model has been successfully applied to a real-time face tracker and other applications. 1

Abstract—We aim at combining color and shape invariants for indexing and retrieving images. To this end, color models are proposed independent of the object geometry, object pose, and illumination. From these color models, color invariant edges are derived from which shape invariant features are computed. Computational methods are described to combine the color and shape invariants into a unified high-dimensional invariant feature set for discriminatory object retrieval. Experiments have been conducted on a database consisting of 500 images taken from multicolored man-made objects in real world scenes. From the theoretical and experimental results it is concluded that object retrieval based on composite color and shape invariant features provides excellent retrieval accuracy. Object retrieval based on color invariants provides very high retrieval accuracy whereas object retrieval based entirely on shape invariants yields poor discriminative power. Furthermore, the image retrieval scheme is highly robust to partial occlusion, object clutter and a change in the object’s pose. Finally, the image retrieval scheme is integrated into the PicToSeek system on-line at

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.