This paper presents an analysis of the performance of two different skin chrominance models and of nine different chrominance spaces for the color segmentation and subsequent detection of human faces in two-dimensional static images. For each space, we use the single Gaussian model based on the Mahalanobis metric and a Gaussian mixture density model to segment faces from scene backgrounds. In the case of the mixture density model, the skin chrominance distribution is estimated by use of the ExpectationMaximisation (EM) algorithm [14]. Feature extraction is performed on the segmented images by use of invariant Fourier-Mellin moments [21]. A multilayer perceptron neural network (NN), with the invariant moments as the input vector, is then applied to distinguish faces from distractors. With the single Gaussian model, normalized color spaces are shown to produce the best segmentation results, and subsequently the highest rate of face detection. The results are comparable to those obtained with the more sophisticated mixture density model. However, the mixture density model improves the segmentation and face detection results significantly for most of the un-normalized color spaces. Ultimately, we show that, for each chrominance space, the detection efficiency depends on the capacity of each model to estimate the skin chrominance distribution and, most importantly, on the discriminability between skin and "non-skin" distributions.

No abstract

No abstract

This paper proposes a scheme that offers accurate and robust identification of human faces. The scheme is characterized by four aspects: facial feature detection using color image segmentation, target image extraction using a sub-space classi$cation method, robust feature extraction based on K-L expansion of an invariant feature space, and face classifer training based on 3D CG modeling of the human face. The scheme'sflexibility under a wide range of image acquisition conditions has been confirmed through the assessment of an experimental face identification system.

This paper considers pedestrian detection, specialized for a near infrared imaging system at night. The main objective is the detection of a distant pedestrian, beyond an illuminated area in a low-beam mode, using a monocular on-board camera. In this method, the region of interest (ROI) is first selected by extracting bright regions, and shape information from a whole human body, is later used for verification. Motion information is not used, due to difficulties in cancellation of ego-motion. The ROI selector is implemented by a modified boosted cascade, in combination with dynamic perspective constraints. After filtering out typical non-pedestrian objects, the remaining ROIs are verified using a support vector machine (SVM). The verified ROIs are tracked with a simple alpha-beta tracker, in combination with final validation, based on a classification score from the SVM. The effectiveness of the proposed modules has been confirmed using several typical night time scenarios.