Method of on-the-fly image stitching

摘要

The presently claimed invention provides a method for stitching a plurality of images together in a way with least memory and CPU usage, and minimum file input and output, while still possessing fast computation speed to avoid post-scan delay for whole slide viewing and good stitching quality. The method of the present invention comprises the steps of calculating featureness of each candidate strip of a image by applying a mathematical transformation, calculating offset of the strip with correlation maximum location, calculating stitching reliability of the candidate strip from the pre-defined weighted function of its featureness and the correlation coefficients of each matching block, and determining optimal stitching path with stitching reliability.

主权项

1. A method for image stitching, comprising:
transforming at least one candidate strip in a first image into at least one transformed strip by mathematical transformation, wherein spatial pixel information within the candidate strip is transformed into frequency domain expression including frequency coefficients with co-existing physical location information including indexes of transform coefficient; calculating featureness of the candidate strip of the image based on energies of transformed regions of the transformed strip, wherein the featureness is a degree of image detail, and describes a high frequency ratio; calculating a candidate feature point of the candidate strip based on a maximum of high frequency coefficients and the corresponding index of transform coefficient; determining a position of a matching block based on the candidate feature point; comparing the matching block with at least one search block in a search area in a second image to calculate correlation coefficients between the matching block and the searching blocks, wherein the correlation coefficient determines similarity between the matching block and the searching block; determining a maximum correlation coefficient, which is a maximum from the correlation coefficients; calculating an offset value from the matching block based on a correlation maximum location, where the searching block is in maximum correlation with the matching block; calculating a strip-offset between the first and second images based on the offset value; and repeating the above steps for remaining images.