| 摘要 |
A method of estimating the dot frequency of an area of a band of an image. The band is divided into small areas, and within each area, each column is processed, pixel by pixel. If a pixel is encountered that is not of the same type as a neighbor, it is assigned a new identification. If a current pixel is the same as the one above or to the left, it is given the same identification. If the pixel is the same as the one above and to the left, the two identifications are merged. At the end of each column two numbers are calculated, one is the number of separate identifications there are in the column, the other is the number of identifications that are in use since the beginning of the entire image. For each area, the dot frequency is the number of separate identifications in the first column plus the number of identifications used in the image up to the last column minus the number of identifications in use at the end of the first column of the band. During the processing of a band the area is moved one pixel to the right and process is repeated. At the end of each band the area is moved one pixel down and the process starts again at the beginning of the image.
|
