Cat Head Detection - How to Effectively Exploit Shape and Texture Features
Cat Head Detection - How to Effectively Exploit Shape and Texture Features
复制标题
DOI：
10.1007/978-3-540-88693-8_59
复制
发表时间：
2008-10
期刊：
影响因子：
--
通讯作者：
Weiwei Zhang;Jian Sun-;Xiaoou Tang
中科院分区：
文献类型：
--
作者：
Weiwei Zhang;Jian Sun-;Xiaoou Tang
本文以猫为例，研究了猫类动物头部的检测问题。我们表明，性能取决于如何有效地利用形状和纹理特征联合。具体来说，我们提出了一个两步的猫头检测方法。在第一步中，我们在两个训练集上训练两个独立的检测器。一个训练集被归一化以强调形状特征，另一个被归一化以强调纹理特征。在第二步中，我们训练一个联合形状和纹理融合分类器来做出最终的决定。我们证明，我们的两步方法可以得到显着的改善。此外，我们还提出了一组新的功能的基础上，有向梯度，它优于现有的领先功能，如。例如，在一个实施例中，Haar、HoG和EoH。我们评估了我们的方法在一个标记良好的猫头数据集10,000图像和PASCAL 2007猫数据。
In this paper, we focus on the problem of detecting the head of cat-like animals, adopting cat as a test case. We show that the performance depends crucially on how to effectively utilize the shape and texture features jointly. Specifically, we propose a two step approach for the cat head detection. In the first step, we train two individual detectors on two training sets. One training set is normalized to emphasize the shape features and the other is normalized to underscore the texture features. In the second step, we train a joint shape and texture fusion classifier to make the final decision. We demonstrate that a significant improvement can be obtained by our two step approach. In addition, we also propose a set of novel features based on oriented gradients, which outperforms existing leading features, e. g., Haar, HoG, and EoH. We evaluate our approach on a well labeled cat head data set with 10,000 images and PASCAL 2007 cat data.