Image Segmentation Using Fuzzy Inference System on YCbCr Color Model
Álvaro Anzueto-Ríos, Jose Antonio Moreno-Cadenas, Felipe Gomez-Castaneda, Sergio Garduza-González · Advances in Science Technology and Engineering Systems Journal · 2017
This paper This paper presents a reliable method for image segmentation using a fuzzy inference system.The Fuzzy Membership function is applied on the YCbCr color space.Triangular membership functions are used in the input of the fuzzy system, Mamdani type fuzzy inference system is applied and for the output universe, singleton-type functions are used; to get the accurate output value, the Weighted Average Method (WAM) is applied.The YCbCr color space is used as feature space.One of the reasons being that it is standardized for the transmission and reception of digital video, (ITU-R Recommendation BT.601-5), and implemented by most of the sensors used in the acquisition of video.The fuzzy membership functions characterize the different membership levels between hue and Chroma from the YCbCr color model.The fuzzy inference system classifies data and generates regions of pixels with a homogeneous color level in the output images.The proposed method was also compared with another system segmentation using Euclidean distance applied to the RGB color space.The best results were obtained in the YCbCr color space.In such model, the changes of hue in presence of illumination variations are considered so that it has a better performance in the segmentation task.In addition, the processing time was lower in this color space.