| 摘要 |
<p>Scenes can be discriminated automatically and optimum prints corresponding to the scenes can be obtained. A face of person is detected from an inputted image and it is determined whether or not a person is on the scene of the inputted image. If it is determined that a person is not on the scene of the inputted image, then it is determined that the inputted image is a landscape image. If it is determined that a person is on the scene of the inputted image, then the face area is calculated and the number of people is counted. If the face area is more than a predetermined ratio of the screen and the number of people is not less than a predetermined number of people, then it is determined that the inputted image is a snapshot of people image. If the face area is more than the predetermined ratio of the screen and the number of people is less than the predetermined number of people, then it is determined that the inputted image is a portrait image.</p> |
