Neuron-Like Algorithms of Adaptive Segmentation and Semantic Description of Images in the 'Adult Image' Recognition Problem

摘要

We describe the possibility of using the methods of color segmentation and semantic description of images in the "adult image" recognition problem. A method for the construction of an adaptive color model of human skin, which uses information about the faces found in the image, is proposed. The possibility of using the semantic features obtained by face attribute detectors for a more detailed classification of such images is also considered.