Edge Detection of Inner Crack Defects Based on Improved Sobel Operator and Clustering Algorithm
The classical Sobel edge detection operator has the shortcomings of low edge positioning accuracy and coarse edge, image edge detection based on improved Sobel operator and clustering algorithm was proposed. Four Sobel-like edge operators are used to improve the edge positioning accuracy and clustering algorithm are used to edge thinning. The experimental result demonstrates that the effect of the edge detection is greatly improved comparing with the traditional edge detection methods.
K. F. Wang "Edge Detection of Inner Crack Defects Based on Improved Sobel Operator and Clustering Algorithm", Applied Mechanics and Materials, Vols. 55-57, pp. 467-471, 2011