Fast Keypoint Recognition Using Random Ferns
Fast Keypoint Recognition Using Random Ferns
复制标题
DOI：
10.1109/tpami.2009.23
复制
发表时间：
2010-03-01
影响因子：
23.6
通讯作者：
Fua, Pascal
中科院分区：
文献类型：
--
作者：
Oezuysal, Mustafa;Calonder, Michael;Fua, Pascal
虽然特征点识别是现代目标检测方法的关键组成部分，但现有方法需要计算昂贵的补丁预处理来处理透视失真。在本文中，我们表明，制定一个朴素的贝叶斯分类框架的问题，使这样的预处理不必要的，并产生一个算法，是简单的，高效的，和强大的。此外，它可以随着类数量的增加而扩展。为了识别关键点周围的补丁，我们的分类器使用了数百个简单的二进制特征和模型类后验概率。我们通过假设任意特征集之间的独立性，使问题在计算上易于处理。即使这不是严格正确的，我们证明，我们的分类器仍然表现得非常好的图像数据集包含非常显着的角度变化。
While feature point recognition is a key component of modern approaches to object detection, existing approaches require computationally expensive patch preprocessing to handle perspective distortion. In this paper, we show that formulating the problem in a naive Bayesian classification framework makes such preprocessing unnecessary and produces an algorithm that is simple, efficient, and robust. Furthermore, it scales well as the number of classes grows. To recognize the patches surrounding keypoints, our classifier uses hundreds of simple binary features and models class posterior probabilities. We make the problem computationally tractable by assuming independence between arbitrary sets of features. Even though this is not strictly true, we demonstrate that our classifier nevertheless performs remarkably well on image data sets containing very significant perspective changes.