Papers by Keyword: Scan Line

Abstract: The similarity metric is a key on image registration. This paper divides similarity metric algorithms into two classes: similarity metrics based on pixels (or voxels) and similarity metrics based on image features. For those images that acquired contours easily, this paper proposes a new fast similarity metric arithmetic based on scan line. This algorithm is insensitive to illumination change and is robust without considering gray level of pixels (or voxels). In addition, this arithmetic does not consider all pixels (or voxels) in image, but consider pixels (or voxels) in the range of contour. So it is very simple and fast. It is not only suitable for 2D images but also suitable for higher dimension images. In experiment we use Laplacian pyramid to decompose image and use snake model to detect image contour. Lastly we give a novel registration result.

Abstract: The existence of holes in vehicle object makes it difficult to extract the feature. existing hole-filling method are capable of filling holes on small and smooth regions of a object, for large holes whit complex boundaries or in curved region in vehicle object, they may not obtain the satisfactory results. For resolving this problem, a novel hole-filling algorithm based on horizontal scan line was proposed to fill arbitrary holes in vehicle object obtained from vehicle image. Experiments show that the algorithm has good performance and efficiency, and in the filling processing, the feature of the area and perimeter of an object can be obtained at the same time.