Show simple item record

dc.contributor.author杜晓凤
dc.contributor.author李翠华
dc.contributor.author李晶
dc.date.accessioned2016-05-17T02:42:52Z
dc.date.available2016-05-17T02:42:52Z
dc.date.issued2009
dc.identifier.citation电子与信息学报,2009,(7):110-114
dc.identifier.issn1009-5896
dc.identifier.otherDZYX200907022
dc.identifier.urihttps://dspace.xmu.edu.cn/handle/2288/105145
dc.description.abstract自然场景自动检测目标轮廓是非常困难的。该文提出了一种基于复合感受野的图像轮廓检测仿生模型。在传统的基于抑制模型的基础上引入去抑制机制,在减少背景纹理干扰的同时,保护较弱的轮廓,从而尽量保持轮廓的完整性。实验结果表明,这种仿生模型可以有效地抑制纹理边缘,减少对轮廓的破坏,提高了自然背景中轮廓检测的性能。
dc.description.abstractContour detection from natural scenes is a tough task in computer vision.This paper proposes a visual model of contour detection based on compound receptive field.By inducing dis-inhibition mechanism to traditional model that was based on inhibition mechanism,inferences are suppressed while weak edges are preserved,so that the integrity of contour is improved.Experiment results show that this approach can suppress edges due to texture,protect object contour and improve the performance of contour detection from nature scene.
dc.description.sponsorship国家973计划项目(2007CB311005);国家863计划项目(2006AA01Z129);福建省自然科学基金(A0710020);厦门大学985二期信息创新平台项目资助课题
dc.language.isozh_CN
dc.subject目标识别
dc.subject轮廓检测
dc.subject初级视皮层
dc.subject复合感受野
dc.subjectTarget identification
dc.subjectContour detection
dc.subjectPrimary visual cortex
dc.subjectCompound Receptive Field(CRF)
dc.title基于复合感受野的轮廓检测算法
dc.title.alternativeContour Detection Based on Compound Receptive Field
dc.typeArticle


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record