A Color Image Edge Detection Model with Morphological Amoebas and Two Kinds of Color Spaces

For solving the problems of the vector ordering in RGB space,edge location and denoising of the color image edge detection,a color image edge detection model based on the morphological amoebas(adaptive structuring elements) and RGB space and HSV space is presented.Firstly,the amoeba structural elements are calculated in the HSV space which overcomes the shortcomings of unreasonable selection of traditional morphological structure elements.Secondly,the vector ordering in RGB space is given according to the metric in HSV space.Thirdly,the edge intensity is defined in RGB space by calculating the minimum distance between pixels in the amoeba structural elements obtained,which not only avoids the inaccurate edge location in HSV space,but also improves the noise suppression.Finally,the idea of the Canny operator is used to get single pixel edge.The experimental results show that the proposed method can fully take into account the local features of an image edge and has the properties of accurate edge positioning and noise suppression.