【免费】harris-laplace主题的博士论文_Harris–LaplaceDetector资源-CSDN文库

4星 · 超过85%的资源需积分: 0 86 浏览量 2015-02-15 17:17:45 上传评论 1 收藏 8.18MB PDF 举报

资源推荐

资源详情

资源评论

Detection of local features invariant to aﬃnes

transformations

Krystian Mikolajczyk

To cite this version:

Krystian Mikolajczyk. Detection of local features invariant to aﬃnes transformations. Human-

Computer Interaction. Institut National Polytechnique de Grenoble - INPG, 2002. French.

<tel-00584096>

HAL Id: tel-00584096

https://tel.archives-ouvertes.fr/tel-00584096

Submitted on 7 Apr 2011

HAL is a multi-disciplinary open access

archive for the deposit and dissemination of sci-

entiﬁc research documents, whether they are pub-

lished or not. The documents may come from

teaching and research institutions in France or

abroad, or from public or private research centers.

L’archive ouverte pluridisciplinaire HAL, est

destin´ee au d´epˆot et `a la diﬀusion de documents

scientiﬁques de niveau recherche, publi´es ou non,

´emanant des ´etablissements d’enseignement et de

recherche fran¸cais ou ´etrangers, des laboratoires

publics ou priv´es.

Abstract

In recent years the use of local characteristics has become one of the dominant ap-

proaches to content based object recognition. The detection of interest points is the ﬁrst

step in the process of matching or recognition. A local approach signiﬁcantly improves

and accelerates image retrieval from databases. Therefore a reliable algorithm for feature

detection is crucial for many applications.

In this thesis we propose a novel approach for detecting characteristic points in an

image. Our approach is invariant to geometric and photometric transformations, which

frequently appear between scenes viewed in diﬀerent conditions. We emphasize the problem

of invariance to aﬃne transformations. This transformation is particularly important as it

can locally approximate the perspective deformations. Previous approaches provide partial

solutions to this problem, as not all essential parameters of local features are estimated

in an aﬃne invariant way. Our method is truly invariant to aﬃne transformations, which

include signiﬁcant scale changes.

An image is represented by a set of extracted points. The interest points are charac-

terized by descriptors, which are computed with local derivatives of the neighborhoods of

points. These descriptors together with a similarity measure enable point-to-point corres-

pondences to be established, and as a result, the geometry between images to be computed.

In the context of an image database, the descriptors are used to ﬁnd similar points in the

database, and therefore the similar image.

The usefulness of our method is conﬁrmed by excellent results for matching and image

retrieval. Several comparative evaluations show that our approach provided for larger

progress in the context of these applications. In our experiments we use a large set of real

images, enabling representative results to be obtained.

Keywords: Interest points, feature detection, aﬃne invariance, scale invariance, feature

description, matching, image retrieval, recognition.

剩余171页未读，继续阅读

内容反馈

小黄人的banana

2017-09-19

应该意识到博士论文是英文的

u011060307

粉丝: 0
资源: 3

最新资源

资源上传下载、课程学习等过程中有任何疑问或建议，欢迎提出宝贵意见哦~我们会及时处理！点击此处反馈

feedback-tip