| 一种基于特征整合理论的物体识别模型 |
| |
| 作者姓名： | 王喜顺 刘曦 史忠植 隋红建 |
| |
| 作者单位： | 1. 中国科学院研究生院, 北京 100049;2. 中国科学院计算技术研究所, 北京 100190 |
| |
| 基金项目： | Supported by the National Basic Research Priorities Programme (2007CB311004), National Science and Technology Support Plan (2006BAC08B06) and National Science Foundation of China (60775035, 60903141, 60933004, 60970088, 61035003) |
| |
| 摘 要： | 基于认知科学的研究提出一个新颖的计算模型用于物体识别.特征整合理论为计算模型提供了总体路线.基于最大熵原理构建学习过程,获得必要的先验知识构成认知网络.利用认知网络,将底层的图像特征和高层知识捆绑起来.利用条件随机场的基本概念和原理建模捆绑过程.将计算模型应用于现实世界的物体识别,在标准图像库上进行评估,取得了很好的效果.
|
| 关 键 词： | 条件随机场 特征捆绑 特征整合 物体识别 |
| 收稿时间： | 2010-10-13 |
| 修稿时间： | 2011-03-04 |
A new object recognition model based on feature integration theory |
| |
| Authors: | WANG Xi-Shun LIU Xi SHI Zhong-Zhi SUI Hong-Jian |
| |
| Institution: | 1. Graduate University, Chinese Academy of Sciences, Beijing 100049, China;2. Key Laboratory of Intelligent Information Processing,Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China |
| |
| Abstract: | We propose a new computational model for object recognition based on the vision cognitive findings. Feature integration theory offers the roadmap for our computing model. We construct the learning procedure to acquire necessary pre-knowledge for the recognition network on the basis of the hypothesis-maximum entropy principle. With the recognition network, we can bind the low-level image features and the high-level knowledge. Fundamental concepts and principles of conditional random fields are employed to model the binding process. We apply our model to real object recognition problem and evaluate it on the benchmark image databases to show its satisfactory performance. |
| |
| Keywords: | conditional random fields feature binding feature integration object recognition |
|
| 点击此处可从《》浏览原始摘要信息 |
| 点击此处可从《》下载免费的PDF全文 |
|
