This work presents a study of three important issues of the color pixel classification approach to skin segmentation: color representation, color quantization, and classification algorithm. Our analysis of several representative color spaces using the Bayesian classifier with the histogram technique shows that skin segmentation based on color pixel classification is largely unaffected by the choice of the color space. However, segmentation performance degrades when only chrominance channels are used in classification. Furthermore, we find that color quantization can be as low as 64 bins per channel, although higher histogram sizes give better segmentation performance. The Bayesian classifier with the histogram technique and the multilayer perceptron classifier are found to perform better compared to other tested classifiers, including three piecewise linear classifiers, three unimodal Gaussian classifiers, and a Gaussian mixture classifier.

A recurrent neural network is presented which performs quadratic optimization subject to bound constraints on each of the optimization variables. The network is shown to be globally convergent, and conditions on the quadratic problem and the network parameters are established under which exponential asymptotic stability is achieved. Through suitable choice of the network parameters, the system of differential equations governing the network activations is preconditioned in order to reduce its sensitivity to noise and to roundoff errors. The optimization method employed by the neural network is shown to fall into the general class of gradient methods for constrained nonlinear optimization and, in contrast with penalty function methods, is guaranteed to yield only feasible solutions.

One of the main challenges in through-the-wall radar imaging (TWRI) is the strong exterior wall returns, which tend to obscure indoor stationary targets, rendering target detection and classification difficult, if not impossible. In this paper, an effective wall clutter mitigation approach is proposed for TWRI that does not require knowledge of the background scene nor does it rely on accurate modeling and estimation of wall parameters. The proposed approach is based on the relative strength of the exterior wall returns compared to behind-wall targets. It applies singular value decomposition to the data matrix constructed from the space-frequency measurements to identify the wall subspace. Orthogonal subspace projection is performed to remove the wall electromagnetic signature from the radar signals. Furthermore, this paper provides an analysis of the wall and target subspace characteristics, demonstrating that both wall and target subspaces can be multidimensional. While the wall subspace depends on the wall type and building material, the target subspace depends on the location of the target, the number of targets in the scene, and the size of the target. Experimental results using simulated and real data demonstrate the effectiveness of the subspace projection method in mitigating wall clutter while preserving the target image. It is shown that the performance of the proposed approach, in terms of the improvement factor of the target-to-clutter ratio, is better than existing approaches and is comparable to that of background subtraction, which requires knowledge of a reference background scene.

This paper addresses an image classification technique that uses the Bayes decision rule for minimum cost to classify pixels into skin color and non-skin color. Color statistics are collected from YCbCr color space. The Bayesian approach to skin color classification is discussed along with an overview of YCbCr color space. Experimental results demonstrate that this approach can achieve good classification outcomes, and it is robust against different skin colors.

In this paper, we propose a new neural architecture for classification of visual patterns that is motivated by the two concepts of image pyramids and local receptive fields. The new architecture, called pyramidal neural network (PyraNet), has a hierarchical structure with two types of processing layers: Pyramidal layers and one-dimensional (1-D) layers. In the new network, nonlinear two-dimensional (2-D) neurons are trained to perform both image feature extraction and dimensionality reduction. We present and analyze five training methods for PyraNet [gradient descent (GD), gradient descent with momentum, resilient backpropagation (RPROP), Polak-Ribiere conjugate gradient (CG), and Levenberg-Marquadrt (LM)] and two choices of error functions [mean-square-error (mse) and cross-entropy (CE)]. In this paper, we apply PyraNet to determine gender from a facial image, and compare its performance on the standard facial recognition technology (FERET) database with three classifiers: The convolutional neural network (NN), the k-nearest neighbor (k-NN), and the support vector machine (SVM)

This paper presents a new human skin color model in YCbCr color space and its application to human face detection. Skin colors are modeled by a set of three Gaussian clusters, each of which is characterized by a centroid and a covariance matrix. The centroids and covariance matrices are estimated from large set of training samples after a k-means clustering process. Pixels in a color input image can be classified into skin or non-skin based on the Mahalanobis distances to the three clusters. Efficient post-processing techniques namely noise removal, shape criteria, elliptic curve fitting and face/non-face classification are proposed in order to further refine skin segmentation results for the purpose of face detection.