Image edge detection based on the grey prediction model and discrete wavelet transform.

Purpose: Image edge detection is an essential issue in image processing and computer vision. The purpose of this paper is to provide a novel and effective algorithm for image edge detection. Design/methodology/approach: Because GM (1,1) model is a typical model for tendency analysis, GM (1,1) model can be used for detecting edge. Prediction image data are close to the original image data by reason of the data being smooth in the non-edge zone of image. The principle of edge detection by GM (1,1) model is that the predicted value at an edge point will be an overestimate or underestimate owing to the data changing drastically in the edge zone of the image. First, the edge image information is obtained by a preprocessed image subtracting from prediction image via GM (1,1). Second, median filter is used to eliminate isolated point noise in edge information images, and discrete wavelet transform is used to extract the image edge. Finally, this paper verifies the proposed algorithm by experiment. Findings: Experimental results show that the proposed algorithm has advantages such as precisely locating, abundant weak edge, and better anti-noise performance. Practical implications: The algorithm proposed in the paper can precisely detect the information of edge image, and get a clear image detail. Originality/value: Grey system theory developed vigorously lays the foundation for image processing. Wavelet analysis in image processing has its characteristics. This paper combines grey prediction model with discrete wavelet transform (DWT) successfully and obtains a novel and effective algorithm for image edge detection. © Emerald Group Publishing Limited.