Rotationally Invariant Descriptors Using Intensity Order Pooling
Rotationally Invariant Descriptors Using Intensity Order Pooling
复制标题
使用强度顺序池的旋转不变描述符
DOI：
10.1109/tpami.2011.277
复制
发表时间：
2012-10-01
影响因子：
23.6
通讯作者：
Hu, Zhanyi
中科院分区：
文献类型：
--
作者：
Fan, Bin;Wu, Fuchao;Hu, Zhanyi
This paper proposes a novel method for interest region description which pools local features based on their intensity orders in multiple support regions. Pooling by intensity orders is not only invariant to rotation and monotonic intensity changes, but also encodes ordinal information into a descriptor. Two kinds of local features are used in this paper, one based on gradients and the other on intensities; hence, two descriptors are obtained: the Multisupport Region Order-Based Gradient Histogram (MROGH) and the Multisupport Region Rotation and Intensity Monotonic Invariant Descriptor (MRRID). Thanks to the intensity order pooling scheme, the two descriptors are rotation invariant without estimating a reference orientation, which appears to be a major error source for most of the existing methods, such as Scale Invariant Feature Transform (SIFT), SURF, and DAISY. Promising experimental results on image matching and object recognition demonstrate the effectiveness of the proposed descriptors compared to state-of-the-art descriptors.
