Full ranking as local descriptor for visual recognition: A comparison of distance metrics on sn
Full ranking as local descriptor for visual recognition: A comparison of distance metrics on sn
复制标题
DOI：
10.1016/j.patcog.2014.10.010
复制
发表时间：
2015-04
期刊：
影响因子：
--
通讯作者：
Chi-Ho Chan;F. Yan;J. Kittler;K. Mikolajczyk
中科院分区：
文献类型：
--
作者：
Chi-Ho Chan;F. Yan;J. Kittler;K. Mikolajczyk
在本文中，我们建议使用一组像素的完整排序作为局部描述符。与仅使用部分排序信息的现有方法相比，完整排序编码了像素之间的完整比较信息，同时保持了对单调光度变换的不变性。描述符用于视觉识别的“视觉词袋”范式。我们证明了将描述符分配给视觉词的距离度量的选择对性能至关重要，并为排列组提供了8个距离度量的广泛评估，包括4个广泛使用的人脸验证和纹理分类基准。结果表明：(1)像素完全排序编码的信息比部分排序编码的信息更多，且始终具有更好的性能；(2)满秩描述子可以被简化为旋转不变量；(3)所提出的描述符适用于图像强度和滤波器响应，并且能够产生最先进的性能。
In this paper we propose to use the full ranking of a set of pixels as a local descriptor. In contrast to existing methods which use only partial ranking information, the full ranking encodes the complete comparative information among the pixels, while retaining invariance to monotonic photometric transformations. The descriptor is used within the bag-of-visual-words paradigm for visual recognition. We demonstrate that the choice of distance metric for assigning the descriptors to visual words is crucial to the performance, and provide an extensive evaluation of eight distance metrics for the permutation groupSnon four widely used face verification and texture classification benchmarks. The results demonstrate that (1) full ranking of pixels encodes more information than partial ranking, consistently leading to better performance; (2) full ranking descriptor can be trivially made rotation invariant; (3) the proposed descriptor applies to both image intensities and filter responses, and is capable of producing state-of-the-art performance.