Images containing faces are essential to intelligent vision-based human computer interaction, and research efforts in face processing include face recognition, face tracking, pose estimation, and expression recognition. However, many reported methods assume that the faces in an image or an image sequence have been identified and localized. To build fully automated systems that analyze the information contained in face images, robust and efficient face detection algorithms are required. Given a single image, the goal of face detection is to identify all image regions which contain a face regardless of its three-dimensional position, orientation, and the lighting conditions. Such a problem is challenging because faces are nonrigid and have a high degree of variability in size, shape, color, and texture. Numerous techniques have been developed to detect faces in a single image, and the purpose of this paper is to categorize and evaluate these algorithms. We also discuss relevant issues such as data collection, evaluation metrics, and benchmarking. After analyzing these algorithms and identifying their limitations, we conclude with several promising directions for future research.

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.

Perceptual user interfaces (PUIs) are an important part of ubiquitous computing. Creating such interfaces is difficult because of the image and signal processing knowledge required for creating classifiers. We propose an interactive machine-learning (IML) model that allows users to train, classify/view and correct the classifications. The concept and implementation details of IML are discussed and contrasted with classical machine learning models. Evaluations of two algorithms are also presented. We also briefly describe Image Processing with Crayons (Crayons), which is a tool for creating new camera-based interfaces using a simple painting metaphor. The Crayons tool embodies our notions of interactive machine learning.

A novel approach for real-time skin segmentation in video sequences is described. The approach enables reliable skin segmentation despite wide variation in illumination during tracking.

The performance of face verification systems has steadily improved over the last few years, mainly focusing on models rather than on feature processing. State-of-the-art methods often use the gray-scale face image as input. In this paper, we propose to use an additional feature to the face image: the skin color. The new feature set is tested on a benchmark database, namely XM2VTS, using a simple discriminant artificial neural network. Results show that the skin color information improves the performance.

This paper describes a system for ubiquitous interaction that does not require users to carry any physical devices. The environment is instrumented with camera/processor combinations that watch users while protecting their privacy. Any visible surface can be turned into an interactive widget that uses hand gestures. Light widgets are tied to the XWeb cross-modal interaction platform to integrate them with interactive feedback.

Vision based fire detection is potentially a useful technique. With the increase in the number of surveillance cameras being installed, a vision based fire detection capability can be incorporated in existing surveillance systems at relatively low additional cost. Vision based fire detection offers advantages over the traditional methods. It will thus complement the existing devices. In this paper, we present spectral, spatial and temporal models of fire regions in visual image sequences. The spectral model is represented in terms of the color probability density of fire pixels. The spatial model captures the spatial structure within a fire region. The shape of a fire region is represented in terms of the spatial frequency content of the region contour using its Fourier coefficients. The temporal changes in these coefficients are used as the temporal signatures of the fire region. Specifically, an autoregressive model of the Fourier coefficient series is used. Experiments with a large number of scenes show that our method is capable of detecting fire reliably.

Abstract not found

In this paper we describe a method for the detection and tracking of human's head and face inside indoor environment by a home robot. In this system we use signal of infrared sensor and also data from CCD camera for locating the human. By using a combination of motion detection, shape analysis and color information we locate heads and faces of different size and orientation in video images. At the initial search for locating the human we use an infrared detector which is mounted on a pan tilt camera. By detecting the presence of human we use motion information to determine head outlines. Head contour is approximated with a circle and we use Hough transform for locating its boundary. Then a skin color classifier looks for faces by searching pixels with a known color distribution in the segmented area, which resembles the head. Then the located head or face is determined and its centroid is fed back to tracking algorithm, which tries to keep the face or head inside the image. We tested t...

This paper attempts to cover the main algorithms used for clustering, with a brief and simple description of each. For each algorithm, I have selected the most common version to represent the entire family. Advantages and drawbacks are commented for each case, and the general idea of possible sub-variations is presented