作者: Chia-Feng Juang , Hwai-Sheng Perng , Shin-Kuan Chen
DOI: 10.1109/IJCNN.2005.1556413
关键词:
摘要: Skin color image segmentation by a histogram-based self-constructing neural fuzzy inference network (SONFIN) is proposed in this paper. Each pixel represented hue-saturation (HS) space. To represent block histogram as accurately possible, nonuniform quantization approach of HS space considered. Histogram information from images under different environments used to train SONFIN make the method robust possible. verify performance method, experiment on human-hand performed. For comparison, other methods are applied same problem.