Creating A New Color Space utilizing PSO and FCM to Perform Skin Detection by using Neural Network and ANFIS

Skin color detection is an essential required step in various applications\nrelated to computer vision. These applications will include face detection,\nfinding pornographic images in movies and photos, finding ethnicity, age,\ndiagnosis, and so on. Therefore, proposing a proper skin detection method can\nprovide solution to several problems. In this study, first a new color space is\ncreated using FCM and PSO algorithms. Then, skin classification has been\nperformed in the new color space utilizing linear and nonlinear modes.\nAdditionally, it has been done in RGB and LAB color spaces by using ANFIS and\nneural network. Skin detection in RBG color space has been performed using\nMahalanobis distance and Euclidean distance algorithms. In comparison, this\nmethod has 18.38% higher accuracy than the most accurate method on the same\ndatabase. Additionally, this method has achieved 90.05% in equal error rate\n(1-EER) in testing COMPAQ dataset and 92.93% accuracy in testing Pratheepan\ndataset, which compared to the previous method on COMPAQ database, 1-EER has\nincreased by %0.87.\n