| 基于 GaborSIFT+NNScSPM 图像特征抽取算法研究 |
| |
| 引用本文： | 江爱文,王春恒,肖柏华.基于 GaborSIFT+NNScSPM 图像特征抽取算法研究[J].自动化学报,2011,37(10):1183-1189. |
| |
| 作者姓名： | 江爱文 王春恒 肖柏华 |
| |
| 作者单位： | 1.江西师范大学计算机与信息工程学院 南昌 330022; |
| |
| 基金项目： | 国家自然科学基金(60835001,60933010)资助~~ |
| |
| 摘 要： | 视觉信息的特征表示是计算机视觉场景图像理解研究中的核心内容. 基于GaborSIFT+NNScSPM的图像特征抽取算法,借鉴生物视觉机制中的相关 研究成果,有机结合了HMAX层次计算模型的思想和非负稀疏编码的策略, 较为合理地模拟了生物视觉皮层中视觉处理的过程.在15类场景图 像和Caltech101两个公开数据集上进行了实验验证, 实验结果表明我们所提出的算法较同期算法有着良好的分类性能.
|
| 关 键 词： | 特征抽取 生物视觉机制 HMAX 非负稀疏编码 语义分类 |
| 收稿时间： | 2010-9-15 |
| 修稿时间： | 2011-5-17 |
An Image Feature Extraction Method Based on GaborSIFT+NNScSPM |
| |
| JIANG Ai-Wen,WANG Chun-Heng,XIAO Bai-Hua.An Image Feature Extraction Method Based on GaborSIFT+NNScSPM[J].Acta Automatica Sinica,2011,37(10):1183-1189. |
| |
| Authors: | JIANG Ai-Wen WANG Chun-Heng XIAO Bai-Hua |
| |
| Affiliation: | 1.College of Computer and Information Engineering, Jiangxi Normal University, Nanchang 330022;2.State Key Laboratory of Intelligent Control and Management of Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190 |
| |
| Abstract: | Feature representation of visual information is one of core research topics in computer vision and image understanding. In this paper, we propose a feature extraction method based on GaborSIFT+NNScSPM, trying to combine HMAX model with non-negative sparse coding to mimic the information process in V1 area in visual cortex. We have test our proposed method on two public data sets (15 scenes and Caltech101), and the experiment results show that our method outperforms the existing ones. |
| |
| Keywords: | Feature extraction biological inspired feature HMAX non-negative sparse coding semantic classification |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《自动化学报》浏览原始摘要信息 |
|
点击此处可从《自动化学报》下载全文 |
