| 引用本文: | 郭军,周晖,朱长仁,等.基于梯度方向二进制模式的空间金字塔模型方法.[J].国防科技大学学报,2014,36(2):129-133.[点击复制] |
| GUO Jun,ZHOU Hui,ZHU Changren,et al.A spatial pyramid model based on binary pattern of oriented gradients[J].Journal of National University of Defense Technology,2014,36(2):129-133[点击复制] |
|
| |
|
|
| 本文已被：浏览 8675次 下载 7473次 |
| 基于梯度方向二进制模式的空间金字塔模型方法 |
| 郭军1, 周晖2, 朱长仁1, 肖顺平1 |
|
(1.国防科技大学 电子科学与工程学院， 湖南 长沙 410073;2.北京跟踪与通信技术研究所， 北京 100094)
|
| 摘要: |
| 空间金字塔模型由于其优势在当前图像分类中得到了广泛应用。然而，其码本生成和特征量化这两个环节具有较高的计算复杂度。为了解决这个问题，提出了一种新的局部特征表述——梯度方向二进制模式，首先对图像稠密采样得到多个子图像块，再将每个子图像块均匀划分为2×2个网格，计算每个网格的梯度直方图，然后对所有网格的梯度主方向进行二进制编码并连接为二进制串值，该二进制串值转换的十进制数即为子图像块的特征表述，最后将该特征表述嵌入到SPM模型中。在标准分类数据库上的实验结果证明了本方法在算法耗时和分类精度上均优于基于SIFT的SPM方法。 |
| 关键词: 空间金字塔模型 梯度方向二进制模式 局部特征描述 图像分类 |
| DOI：10.11887/j.cn.201402022 |
| 投稿日期：2013-10-23 |
| 基金项目:国家部委资助项目 |
|
| A spatial pyramid model based on binary pattern of oriented gradients |
| GUO Jun1, ZHOU Hui2, ZHU Changren1, XIAO Shunping1 |
|
(1.College of Electronic Science and Engineering, National University of Defense Technology, Changsha 410073, China;2. Beijing Institute of Tracking and Telecommunications Technology, Beijing 100094, China)
|
| Abstract: |
| Recently spatial pyramid matching (SPM) with scale invariant feature transform (SIFT) descriptor has been successfully used in image classification. Unfortunately, the codebook generation and feature quantization procedures using SIFT feature have the high complexity both in time and space. To address this problem, a feature descriptor called Binary Pattern of Oriented Gradients is presented. Firstly, the input image was densely sampled and divided into small uniform image patches. Secondly, each patch was divided into 2*2 grids uniformly. For all grids the histograms of oriented gradient were computed and all dominant directions of the histograms were coded by binary coding. Then the descriptor was generated by converting the binary number to decimal number. Finally, this descriptor was combined in the spatial pyramid domain. Experiments on popular benchmark dataset demonstrate that the proposed method always significantly outperforms the popular SPM based SIFT descriptor method both in time and classification accuracy. |
| Keywords: spatial pyramid model binary pattern of oriented gradients local feature descriptor image classification |
|
|
|
|
|
