Skin Color Detection Model Using Neural Networks and its Performance Evaluation

Problem statement: Skin color detection is used as a preliminary step in numerous computer vision applications like face detection, n udity recognition, hand gesture detection and perso n identification. In this study we present a pixel ba sed skin color classification approach, for detecti ng skin pixels and non skin pixels in color images, us ing a novel neural network symmetric classifier. Th e neural classifiers used in the literature either us es a symmetric model with single neuron in the outp ut layer or uses two separate neural networks (asymmetric model) for each of the skin and non-skin classe s. The novelty of our approach is that it has two outp ut layer neurons; one each for skin and non-skin cl ass, instead of using two separate classifiers. Thus by using a single neural network classifier we have improved the separability between these two classes , eliminating additional time complexity that is needed in asymmetric classifier. Approach: Skin samples from web images of people from different ethnic groups were collected and used for training. Ground truth skin segmented images were obtained by using semiautomatic skin segmentation tool devel oped by the authors. The ground truth database of skin segmented images, thus obtained was used to evaluate the performance of our NN based classifier. Results: With proper selection of optimum classification th reshold that varies from image to image the classifier gave the detection rate of mor e than 90% with 7% false positives on an average, Conclusion/Recommendations: It is observed that the neural network is capable of detecting skin in complex lighting and background environments. The classifier has the ability to classify the skin pixe ls belonging to people from different ethnic groups ev en when they are present simultaneously in an image. The proper choice of optimum classification threshold that varies from image to image is an issue here. Automatic computation of this optimum t hreshold for each image is desired in practical skin detection applications. This issue can be take n up as a future study, which will enable us to perform fully automatic skin segmentation with redu ced false positives.