A Fractional-order Sobel Operator for Medical Image Structure Feature Extraction

This paper proposes a novel fractional-order gradient operator for medical image structure feature extraction. The proposed operator can be seen as generalization of the first-order Sobel operator. The goal is to utilize the frequency characteristic of the fractional derivative for extracting more structure feature details. A thresholding is set based on the average fractional-order gradient for marking the edge points, and then the image structure can be extracted. Experiments show that the proposed fractional-order operator yields good visual effects.