[计算机]图像处理_Caltech 256加利福尼亚理工学院256类图像数据库.pdf

Caltech 256(加利福尼亚理工学院256 类图像数据库) 数据摘要： We introduce a challenging set of 256 object categories containing a total of 30607 images. The original Caltech-101 was collected by choosing a set of object categories, downloading examples from Google Images and then manually screening out all images that did not fit the category. Caltech-256 is collected in a similar manner with several improvements: a) the number of categories is more than doubled, b) the minimum number of images in any category is increased from 31 to 80, c) artifacts due to image rotation are avoided and d) a new and larger clutter category is introduced for testing background rejection. We suggest several testing paradigms to measure classification performance, then benchmark the dataset using two simple metrics as well as a state-of-the-art spatial pyramid matching algorithm. Finally we use the clutter category to train an interest detector which rejects uninformative background regions. 中文关键词： 识别,多类,标注,轮廓,图像, 英文关键词： Recognition,Multi class,Annotations,Outline,Images, 数据格式： IMAGE 数据用途： To train and test several Computer Vision recognition and classification algorithms. 数据详细介绍： Caltech 256 Abstract We introduce a challenging set of 256 object categories containing a total of 30607 images. The original Caltech-101 was collected by choosing a set of object categories, downloading examples from Google Images and then manually screening out all images that did not fit the category. Caltech-256 is collected in a similar manner with several improvements: a) the number of categories is more than doubled, b) the minimum number of images in any category is increased from 31 to 80, c) artifacts due to image rotation are avoided and d) a new and larger clutter category is introduced for testing background rejection