论文部分内容阅读
A new edge detection method combining the scan ni ng window central edge (SWCE) detector and an improved active contour model is p roposed. The method first emploies the SWCE detector based on the difference of area pixel value means to perform an optimal edge detection, and then proposes an improved active contour model with modified energy functions to refine the lo cation of the edges. The initial nodes of the improved active contour model are automatically found from the vectorised results of the SWCE detector. Tests on s imulated speckled images and real airborne SAR images show that the combined met hod can benefit from the advantages of the both techniques and get satisfactory edge detection and localization abilities at the same time.
A new edge detection method combining the scan ni ng window central edge (SWCE) detector and an improved active contour model is p roposed. The method first emploies the SWCE detector based on the difference of area pixel value means to perform an optimal edge detection, and then Proposition an improved active contour model with modified energy functions to refine the lo cation of the edges. The initial nodes of the improved active contour model are automatically found from the vectorized results of the SWCE detector. Tests on s imulated speckled images and real airborne SAR images show that the combined met hod can benefit from the advantages of the both techniques and get satisfactory edge detection and localization abilities at the same time.