| 摘要 |
It is aimed to provide a technology capable of increasing a speed of searching for a corresponding point irrespective of an image condition. In order to achieve this object, based on first phase information on each frequency component regarding a first standard area including a first standard point of a first converted standard image generated from a first image, and based on second phase information on each frequency component regarding a first reference area including a first search standard point of a first converted reference image generated from a second image, the first converted reference image is searched for a first corresponding point that corresponds to the first standard point. Based on a position of the first corresponding point in the first converted reference image, a second search standard point is determined on the second image. Further, based on third phase information on each frequency component regarding a second standard area including a second standard point that corresponds to the first standard point of the first image, and based on fourth phase information on each frequency component regarding a second reference area including the second search standard point of the second image, the second image is searched for a second corresponding point corresponding to the second standard point. The information on a frequency component obtained in the computation on another stage is reused in the search on the two stages above. |
