Show simple item record

dc.contributor.author江涛
dc.contributor.author王程
dc.contributor.author王博亮
dc.contributor.author谢杰镇
dc.contributor.author焦念志
dc.contributor.author骆庭伟
dc.date.accessioned2016-05-17T02:59:39Z
dc.date.available2016-05-17T02:59:39Z
dc.date.issued2010
dc.identifier.citation厦门大学学报(自然科学版),2010,(1):53-57
dc.identifier.issn0438-0479
dc.identifier.otherXDZK201001014
dc.identifier.urihttps://dspace.xmu.edu.cn/handle/2288/107978
dc.description.abstract提出了一种基于支持向量机(SVM)和支持向量域描述(SVdd)的赤潮藻类分类系统.该系统是赤潮藻类流式监测系统的子系统.设计这套系统的主要难点在于:1)同一种藻类的形态由于个体差异和生长期不同而不同;2)藻类图像是任意位置三维目标在成像平面的投影,投影存在任意性并可能产生局部遮挡;3)藻类图像包含非目标藻类和杂质.在特征提取算法的基础上,首先对输入的藻类采用SVdd进行拒识或接受处理,最后针对接受的藻类再利用基于超平面分割的SVM分类器进行分类判决.实验证明:基于SVM和SVdd的赤潮藻类分类系统分类精度更高并具有较好的拒识性能,是一种较好的藻类自动分类方法.
dc.description.abstractThis paper presents a real-time alga classifier designed for flow-cytometry-based marine alga monitoring systems.The difficulties of such classification includes:1)the shape of the same algae category is deformable,and largely variant due to the individual differences and mature stage,2)the image of algae may vary due to different 3D positions to the imaging plane and partial occlusion, 3)the images also contain unknown algae and contaminations.In the proposed method,several shape features were developed,support vector data description(SVDD) was trained to reject the contaminative objects and unknown algae and a support vector machine (SVM) was used to classify the algae to taxonomic categories.Our approach achieved greater than 90%accuracy on a collection of algal images.The test on contaminated algal image set(contains unknown algae and non-algae objects,such as sands) also demonstrated promising results.
dc.description.sponsorship国家高技术研究发展计划(863)项目(2003AA635160)
dc.language.isozh_CN
dc.subject赤潮
dc.subject支持向量数据域
dc.subject特征提取
dc.subject流式细胞技术
dc.subjectred tide
dc.subjectsupport vector data description
dc.subjectfeature extraction
dc.subjectflow cytometry
dc.title基于SVDD和SVM的赤潮藻类识别
dc.title.alternativeRed Tide Algae Recognition Based SVDD and SVM
dc.typeArticle


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record