摘要 |
Disclosed is a method for object correspondence identification between two image sets, said method steps comprising roughly aligning the two image sets, receiving 200 a selected point in said one image set, locating 210 a rough matching point in said another image, defining 210 a first volume-of-interest around said selected point, defining 230 a search window around said matching point comprising a plurality of neighboring points, for every point in said search window, defining 240 a second volume-of-interest, computing 250 the similarity between each said second volume-of-interest with said first volume-of-interest, and selecting 280 that second volume-of-interest that is most similar to said first volume-of-interest. |