Indexing based on scale invariant interest points

Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 Pub Date : 2001-07-07 DOI:10.1109/ICCV.2001.937561

K. Mikolajczyk, C. Schmid

{"title":"Indexing based on scale invariant interest points","authors":"K. Mikolajczyk, C. Schmid","doi":"10.1109/ICCV.2001.937561","DOIUrl":null,"url":null,"abstract":"This paper presents a new method for detecting scale invariant interest points. The method is based on two recent results on scale space: (1) Interest points can be adapted to scale and give repeatable results (geometrically stable). (2) Local extrema over scale of normalized derivatives indicate the presence of characteristic local structures. Our method first computes a multi-scale representation for the Harris interest point detector. We then select points at which a local measure (the Laplacian) is maximal over scales. This allows a selection of distinctive points for which the characteristic scale is known. These points are invariant to scale, rotation and translation as well as robust to illumination changes and limited changes of viewpoint. For indexing, the image is characterized by a set of scale invariant points; the scale associated with each point allows the computation of a scale invariant descriptor. Our descriptors are, in addition, invariant to image rotation, of affine illumination changes and robust to small perspective deformations. Experimental results for indexing show an excellent performance up to a scale factor of 4 for a database with more than 5000 images.","PeriodicalId":429441,"journal":{"name":"Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001","volume":"2 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2001-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1357","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCV.2001.937561","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1357

Abstract

This paper presents a new method for detecting scale invariant interest points. The method is based on two recent results on scale space: (1) Interest points can be adapted to scale and give repeatable results (geometrically stable). (2) Local extrema over scale of normalized derivatives indicate the presence of characteristic local structures. Our method first computes a multi-scale representation for the Harris interest point detector. We then select points at which a local measure (the Laplacian) is maximal over scales. This allows a selection of distinctive points for which the characteristic scale is known. These points are invariant to scale, rotation and translation as well as robust to illumination changes and limited changes of viewpoint. For indexing, the image is characterized by a set of scale invariant points; the scale associated with each point allows the computation of a scale invariant descriptor. Our descriptors are, in addition, invariant to image rotation, of affine illumination changes and robust to small perspective deformations. Experimental results for indexing show an excellent performance up to a scale factor of 4 for a database with more than 5000 images.

查看原文本刊更多论文

基于尺度不变兴趣点的索引

提出了一种检测尺度不变兴趣点的新方法。该方法基于两个最近在尺度空间上的研究结果:(1)兴趣点可以适应尺度并给出可重复的结果(几何稳定)。(2)归一化导数在尺度上的局部极值表明了特征局部结构的存在。我们的方法首先计算Harris兴趣点检测器的多尺度表示。然后我们选择局部测度(拉普拉斯测度)在尺度上最大的点。这样就可以选择已知特征尺度的不同点。这些点不受缩放、旋转和平移的影响，对光照变化和视点的有限变化具有鲁棒性。对于索引，图像由一组尺度不变点表征;与每个点相关联的尺度允许计算一个尺度不变描述符。此外，我们的描述符不受图像旋转、仿射光照变化和小透视变形的影响。实验结果表明，对于拥有超过5000张图像的数据库，索引的性能达到了4的比例因子。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001

自引率

0.00%

发文量