An Improved Method for Image Edge Detection Based on GM(1,1) Model

The GM(1,1) model usually uses the first component of the first order accumulated generating operation(AGO) sequence X(1) as the initial condition to model in the research and application of image edge detection. This model has the disadvantage of being unable to completely utilize the latest information. Also it can´t detect out all edge points because it detects the image only on two directions of horizontal and vertical. So in this paper, an improved GM(1,1) model is proposed for edge detection. It uses the last component of sequence X(1) as the initial condition of GM(1,1) model and predicts the pixel value on eight directions. Then the predicted image is subtracted by the original image to find out the position points with hopping grey values, which are edge points. Experimental results show that this algorithm can effectively detect out a complete image edge.