A general technique for the recovery of significant image features is presented. The technique is basedon the mean shift algorithm, a simple nonparametric procedure for estimating density gradients. Drawbacks of the current methods (including robust clustering) are avoided. Featurespace of any naturecan beprocessed, and as an example, color image segmentation is discussed. The segmentation is completely autonomous, only its class is chosen by the user. Thus, the same program can produce a high quality edge image, or provide, by extracting all the significant colors, a preprocessor for content-based query systems. A 512 x 512 color image is analyzed in less than 10 seconds on a standard workstation. Gray level images are handled as color images having only the lightness coordinate.

Image segmentation is very essential and critical to image processing and pattern recognition. This survey provides a summary of color image segmentation techniques available now. Basically, color segmentation approaches are based on monochrome segmentation approaches operating in di erent color spaces. Therefore, we rst discuss the major segmentation approaches for segmenting monochrome images: histogram thresholding, characteristic feature clustering, edge detection, region-based methods, fuzzy techniques, neural networks, etc. � then review some major color representation methods and their advantages/disadvantages� nally summarize the color image segmentation techniques using di erent color representations. The usage of color models for image segmentation is also discussed. Some novel approaches such as fuzzy method and physics based method are investigated as well.

Colour cues were used to obtain robust detection and tracking of people in relatively unconstrained dynamic scenes. Gaussian mixture models were used to estimate probability densities of colour for skin, clothing and background. These models were used to detect, track and segment people, faces and hands. A technique for dynamically updating the models to accommodate changes in apparent colour due to varying lighting conditions was used. Two applications are highlighted: (1) actor segmentation for virtual studios, and (2) focus of attention for face and gesture recognition systems. A system implemented on a 200MHz PC tracks multiple objects in real-time. 1

Skin color has proven to be a useful and robust cue for face detection, localization and tracking. Image content filtering, content-aware video compression and image color balancing applications can also benefit from automatic detection of skin in images. Numerous techniques for skin color modelling and recognition have been proposed during several past years. A few papers comparing different approaches have been published [Zarit et al. 1999], [Terrillon et al. 2000], [Brand and Mason 2000]. However, a comprehensive survey on the topic is still missing. We try to fill this vacuum by reviewing most widely used methods and techniques and collecting their numerical evaluation results.

. We use colour mixture models for real-time colour-based object localisation, tracking and segmentation in dynamic scenes. Within such a framework, we address the issues of model order selection, modelling scene background and model adaptation in time. Experimental results are given to demonstrate our approach in different scale and lighting conditions. 1 Introduction Colour has been used in machine vision for tasks such as segmentation [1, 2], tracking [3] and recognition [4, 5]. Colour offers many advantages over geometric information in dynamic vision such as robustness under partial occlusion, rotation in depth, scale changes and resolution changes. Furthermore, using colour enables real-time performance on modest hardware platforms [1]. Swain and Ballard [5] described a scheme which used histograms for modelling the colours of an object. The colour space was quantised through the histogram's structure which comprised a number of "bins". An algorithm known as "histogram intersect...

Mean shift is a nonparametric estimator of density which has been applied to image and video segmentation. Traditional mean shift based segmentation uses a radially symmetric kernel to estimate local density, which is not optimal in view of the often structured nature of image and more particularly video data. In this paper we present an anisotropic kernel mean shift in which the shape, scale, and orientation of the kernels adapt to the local structure of the image or video. We decompose the anisotropic kernel to provide handles for modifying the segmentation based on simple heuristics. Experimental results show that the anisotropic kernel mean shift outperforms the original mean shift on image and video segmentation in the following aspects: 1) it gets better results on general images and video in a smoothness sense; 2) the segmented results are more consistent with human visual saliency; 3) the algorithm is robust to initial parameters.

This paper describes our entire color segmentation system, called CSC (Color Structure Code), in detail. In section 2 we introduce the hexagonal, hierarchical island structure on which our method is based. Section 3 describes the actual segmentation method. In Section 4 the new color similarity measure is presented. Section 5 discusses the complexity of our approach. The system is very fast and thus applicable in real world problems. Finally we present some results and conclusions in section 6. 2 Hexagonal, hierarchical island structure

We introduce an automatic segmentation framework that blends the advantages of color, texture, shape, and motion based segmentation methods in a computationally feasible way. A spatiotemporal data structure is first constructed for each group of video frames, in which each pixel is assigned a feature vector based on lowlevel visual information. Then, the smallest homogeneous components, so called as volumes, are expanded from selected marker points using an adaptive, three dimensional, centroid-linkage method. Self descriptors that characterize each volume, and relational descriptors that capture the mutual properties between pairs of volumes are determined by evaluating the boundary, trajectory, and motion of the volumes. These descriptors are used to measure the similarity between volumes based on which volumes are further grouped into objects. A fine-to-coarse clustering algorithm yields a multi-resolution object tree representation as an output of the segmentation.

Contents 1 INTRODUCTION 3 1.1 Malignant melanoma . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.2 Evolution of malignant melanoma . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.3 Image acquisition techniques . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.3.1 Traditional imaging . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.3.2 Dermatoscopic imaging . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 1.4 Dermatoscopic features . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2 FEATURE EXTRACTION IN DERMATOSCOPIC IMAGES 8 2.1 Image acquisition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.2 Image preprocessing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 2.2.1 Median filtering . . . . . . . . . . . . . . . . . . . . . . . . . . .

Photometric stereo is a well--known technique for recovering surface normals of a surface but requires three or more images of a surface taken under illumination from different directions. At best, one may dispense with the need for multiple images by using colored lights tuned to camera filters. But a less restrictive paradigm is available using the Orientation--from--Color approach, wherein multiple broadband illuminants impinge on a surface simultaneously. In that method, colors for a Lambertian surface lie on an ellipsoid in color space. The method has mostly been applied to single--color objects, with ellipsoid quadratic form parameters determined from a large number of pixels. However, recently Petrov et al. developed an entirely local approach, useful also for multicolored objects with color uniform in each patch. Here we investigate to what extent a method like Petrov's can be applied in the ostensibly simpler situation in which the complex lighting environment is known, i.e. a color photometric stereo situation, with all lights at play at once with only a single image to analyze. We find that, assuming a simple model of color formation, we are able to recover the object colors along with surface normals, using only a single image. Because we immerse the object in a known lighting environment, we show that only half of the equations utilized by Petrov are actually needed, making the method more stable. Nevertheless solutions do not exist at every pixel; instead we may determine a best estimate of patch color using a robust estimator, and then apply that estimate throughout a patch. Results are shown to be quite good, compared to ground truth. The simple color model can often be made to hold more exactly by transforming the color space to one corresponding to spe...