| 摘要 |
PROBLEM TO BE SOLVED: To continuously detect the face of a person in composition, without losing the faces, even during zooming operation. SOLUTION: In step S3, a magnification/reduction rate of an image signal is calculated, and in step S4, the position and the size of a face detection frame in the present image during a zooming operation are linearly predicted, on the basis of the magnification/reduction ratio. In step S5, the correction amount of the face detection frame is calculated on the basis of face detection information (position and size of face), before maximum 4V, and in step S6, the face detection frame is temporarily corrected with the calculated correction amount. In step S7, whether the temporarily corrected face detection frame exceeds threshold is determined, and in step S8, the correction amount is corrected, according to the result of the determination. Then, in step S9, the face detection frame is corrected with a correction amount with which the face detection frame is corrected. The present invention is applicable to digital video cameras. COPYRIGHT: (C)2009,JPO&INPIT |
