改进SIFT算法在图像数据相似性匹配中的应用研究

计算机科学 ›› 2014, Vol. 41 ›› Issue (Z6): 122-124.

改进SIFT算法在图像数据相似性匹配中的应用研究

张德全,董世存

92493部队98分队葫芦岛125000;江苏自动化研究所连云港222061

出版日期:2018-11-14 发布日期:2018-11-14

Application Research on Comparability Matching for Image-Data Based on Enhanced SIFT Algorithm

ZHANG De-quan and DONG Shi-cun

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 针对基本SIFT算法在效率和准确性上的不足,通过减少提取特征点主方向以及降低在生成描述子时的重叠运算复杂度,从行列两方面缩小特征点匹配的搜索范围,提高了算法的执行效率,增加了相似性匹配的匹配准确率, 使其在月球图像数据库匹配的应用中取得了较好的效果。

关键词: 尺度不变特征变换(SIFT)特征点,图像匹配,特征提取中图法分类号TP319文献标识码A

Abstract: For the deficiencies on efficiency and accuracy of the SIFT(Scale Invariant Feature Transform)algorithm,improvement was made by two ways,in which one is to reduce the overlap computation on major direction and generation of description,and the other is to shrink the search coverage of feature point match．The experiment on the match of moon image database gives a preferable result,in which the real-time performance and matching accuracy are improved.

Key words: Scale invariant feature transform(SIFT) feature point,Image matching,Feature extraction

张德全,董世存. 改进SIFT算法在图像数据相似性匹配中的应用研究[J]. 计算机科学, 2014, 41(Z6): 122-124. https://doi.org/

ZHANG De-quan and DONG Shi-cun. Application Research on Comparability Matching for Image-Data Based on Enhanced SIFT Algorithm[J]. Computer Science, 2014, 41(Z6): 122-124. https://doi.org/

参考文献

[1] 贾博,姜挺,郭丽,等．SIFT和相关系数在嫦娥一号月球影像匹配中的应用[J].测绘科学技术学报,2009,26(5):363-366
[2] 李晓明．基于SIFT特征的遥感影像自动匹配[D]．北京:北京理工大学机电工程学院,2006
[3] 甘哑莉．频率域基于梯度预处理的互相关图像匹配方法[D]．长沙:国防科技大学信息系统与管理学院,2007
[4] 许晓帆,杜江．面向景象匹配辅助导航的SIFT图像配准算法[J]．电子设计工程,2013,21(18):139-141
[5] 李彤斐,杨马英．足球机器人视觉目标识别的PCA-SIFT算法[J]．江南大学学报:自然科学版,2013,12(5):601-606
[6] Lowe D G．Object recognition from local scale-invariant features[C]∥International Conference on Computer Vision,Corfu,Greece(September 1999)．1999:1150-1157
[7] Lowe D G．Distinctive image features from scale invariant key points[J]．International Journal of Computer Vision,2004,60(2):91-110
[8] 王国美．SIFT特征匹配算法研究[D]．贵阳:贵州大学计算机学院,2007
[9] Ke Y,Sukthankar R．Pca-sift:a more distinctive representation for local image descriptors[C]∥Computer Vision and Pattern Recognition．2004
[10] Ledwich L,Williams S．Reduced SIFT Features for Image Retrieval and Indoo Localization[C]∥Australian Conference on Robotics and Automation.Canberra,Australia,2004
[11] 叶波,陆雪松,张素,等．基于互信息图像匹配中的局部极值问题研究[D]．上海:上海交通大学生物医学仪器研究所,2007

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed