Use bin-ratio information for category and scene classification
Use bin-ratio information for category and scene classification
复制标题
DOI：
10.1109/cvpr.2010.5539917
复制
发表时间：
2010-06
期刊：
影响因子：
--
通讯作者：
Nianhua Xie;Haibin Ling;Weiming Hu;Xiaoqin Zhang
中科院分区：
文献类型：
--
作者：
Nianhua Xie;Haibin Ling;Weiming Hu;Xiaoqin Zhang
在本文中，我们提出使用从直方图的仓值之间的比率收集的仓比信息来进行场景和类别分类。为了充分利用这些信息，设计了一种新的直方图相异度--仓比相异度(BRD)。研究表明，该算法对于类别和场景分类任务具有几个显著的优势：第一，它对杂波、部分遮挡和直方图归一化具有较强的鲁棒性；第二，它能够捕获丰富的共现信息，同时具有线性的计算复杂度；第三，它可以很容易地与其他相异度量相结合，如L1和χ2，来收集互补信息。我们将所提出的方法应用于词袋框架中的类别和场景分类任务。实验是在几个广泛测试的数据集上进行的，包括Pascal 2005、Pascal 2008、Oxford Flowers和Scene-15数据集。在所有的实验中，与以前报道的解决方案相比，所提出的方法表现出了优异的性能。
In this paper we propose using bin-ratio information, which is collected from the ratios between bin values of histograms, for scene and category classification. To use such information, a new histogram dissimilarity, bin-ratio dissimilarity (BRD), is designed. We show that BRD provides several attractive advantages for category and scene classification tasks: First, BRD is robust to cluttering, partial occlusion and histogram normalization; Second, BRD captures rich co-occurrence information while enjoying a linear computational complexity; Third, BRD can be easily combined with other dissimilarity measures, such as L1 and χ2, to gather complimentary information. We apply the proposed methods to category and scene classification tasks in the bag-of-words framework. The experiments are conducted on several widely tested datasets including PASCAL 2005, PASCAL 2008, Oxford flowers, and Scene-15 dataset. In all experiments, the proposed methods demonstrate excellent performance in comparison with previously reported solutions.