图 书 馆
视觉识别的核心描述符Kernel Descriptors for Visual Recognition |
|
| 课程网址: | http://videolectures.net/nips2010_bo_kdvr/ |
| 主讲教师: | Liefeng Bo |
| 开课单位: | 华盛顿大学 |
| 开课时间: | 2011-03-25 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | The design of low-level image features is critical for computer vision algorithms. Orientation histograms, such as those in SIFT~\cite{Lowe2004Distinctive} and HOG~\cite{Dalal2005Histograms}, are the most successful and popular features for visual object and scene recognition. We highlight the kernel view of orientation histograms, and show that they are equivalent to a certain type of match kernels over image patches. This novel view allows us to design a family of kernel descriptors which provide a unified and principled framework to turn pixel attributes (gradient, color, local binary pattern, \etc) into compact patch-level features. In particular, we introduce three types of match kernels to measure similarities between image patches, and construct compact low-dimensional kernel descriptors from these match kernels using kernel principal component analysis (KPCA)~\cite{Scholkopf1998Nonlinear}. Kernel descriptors are easy to design and can turn any type of pixel attribute into patch-level features. They outperform carefully tuned and sophisticated features including SIFT and deep belief networks. We report superior performance on standard image classification benchmarks: Scene-15, Caltech-101, CIFAR10 and CIFAR10-ImageNet. |
| 关 键 词: | 低级图像; 视觉算法; 内核视图 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-07-25：cwx |
| 阅读次数: | 81 |