| 摘要 |
An image recognition device capable of accurately recognizing an object by efficiently selecting a specific object area as a recognition target, from detected object areas. The image recognition device recognizes a specific object area from images sequentially input in time series. An object detection section detects object areas from each image. An appropriateness determination section determines whether or not each detected object area is appropriate as a recognition target. A recognition target-selecting section selects an object area for use as the recognition target, from the detected object areas, based on a result of determination by the appropriateness determination section. An image recognition device recognizes whether or not the object area selected by the recognition target-selecting section is the specific object area. |
