摘要 |
<p><P>PROBLEM TO BE SOLVED: To suppress over-learning in learning using a small number of learning images and learn a discriminator with high accuracy of identification. <P>SOLUTION: A learning section 26 learns, according as the learning image used for learning the discriminator is designated from a plurality of sample images by a user, the discriminator using a random feature amount including a dimension feature amount randomly selected from a plurality of dimension feature amounts included in an image feature amount indicating features of the learning image. The learning device can be applied to a computer to classify images, for example. <P>COPYRIGHT: (C)2011,JPO&INPIT</p> |