详细信息
文献类型:期刊文献
中文题名:基于稀疏编码的图像语义分类器模型
英文题名:Sparse Coding-Based Image Semantic Classifier Model
作者:梁天一[1];宋国新[1];虞慧群[1]
机构:[1]华东理工大学信息科学与工程学院,上海200237
年份:2007
卷号:33
期号:6
起止页码:827
中文期刊名:华东理工大学学报(自然科学版)
外文期刊名:Journal of East China University of Science and Technology
收录:CSTPCD;;EI(收录号:20080411059288);Scopus;北大核心:【北大核心2004】;CSCD:【CSCD2011_2012】;
基金:国家自然科学基金(60473055);上海市浦江人才计划基金(05PJ14030)
语种:中文
中文关键词:视觉认知;稀疏编码;图像语义;图像分类
外文关键词:visual recognition; sparse coding; image semantics; image classification
摘要:为了解决图像检索以及遥感图像识别等图像处理研究中本质的问题——如何对高层抽象图像语义进行有效的分类,本文采用生物视觉认知机理,结合生物特征信息,用最小生成树的方法构造图像信息语义树,提出了一个基于稀疏编码的图像语义分类器(SCISC)的模型。实验结果表明:该模型在图像分类中有较高正确率。
In order to solve the problem in the image process researches, it is very important to find an efficient, biologic recognition related, and high-level semantic image classification method. By adopting the theories of biologic visual recognition and knowledge engineering combined with biologic characteristic information, and using minimum spanning tree as an image information construction tree, this paper presents a sparse coding based image semantic classifier (SCISC) model. The experimental result shows that this model has high accuracy in image classification.
参考文献:
正在载入数据...
