| 摘要 |
Patterns in an image or graphical representation of a dataset are identified through centroid integration. The image or graphical representation is digitized. A collapsed image is created by identifying the centroid and at least one characteristic value for each feature in the digitized image. A shape, such as a line, curve, plane or hypersurface, is stepped across the image. At each step, the characteristic values are summed for all centroids within a predetermined distance of the shape. Peaks in the resulting summation represent matches between the shape and a pattern in the data, with steeper peaks representing a better match. Different shapes, or the same shape at different angles, can be applied to the data to find better fits with the patterns in the image. The image can be multidimensional, with the shape being one dimension less than the image.
|
