| 摘要 |
PROBLEM TO BE SOLVED: To apply unique position restraint to each object to be identified, to detect an object to be identified in a more accurate manner. SOLUTION: The learning device includes: a feature point extracting unit 24 for extracting a feature point from each of multiple generated ; a feature amount extracting unit 25 for extracting feature point feature amount representing the feature of the feature point from the generated image; an overall feature amount calculating unit 243 for calculating the overall feature amount representing the overall feature of the generated image based on the feature point feature amount of a feature point existing on a feature point selection range determined based on the multiple generated images, of the generated image range; and an identifier generating unit 27 for generating an identifier based on the overall feature amount of the generated image, and a correct answer label representing whether the generated image is the positive image or the negative image. For example, the learning device can be applied to a learning device for generating an identifier identifying a predetermined object. COPYRIGHT: (C)2011,JPO&INPIT
|
