Optimization of SIFT-Based Image Retrieval
-
摘要: 基于SIFT(scale-invariant feature transform,尺度不变特征转换)向量的图像检索在精度和实时性方面都与使用者的心理预期有较大的偏差,该文在建树(build vocabulary tree)、检索、以及匹配度计算方面做了一些改进,在满足实时性的要求下,提高了检索精度;在建树过程中,重新定义了SIFT特征向量聚类机制,将分类和K均值聚类法结合起来代替传统的K均值聚类法;在进行图像检索时,直接利用已有欧氏距离信息,减少向量之间距离的计算,对SIFT向量统一化处理;最后通过改进单位化处理方法,克服SIFT大数据造成的误差.数值结果表明,改进后vocabulary tree的节点有更强的差异性, 克服了将训练集按数量均分而不是按距离均分和直接决定树的层数的缺陷;使得检索时间很好地满足了实时性的要求;改进的单位化方法消除了SIFT大数据的误差,从而极大地提高了检索精度.Abstract: In order to deal with the great discrepancy between the expectations of users and the real performance in image retrieval, some improvement on building tree, retrieval and matching methods were made with great success both in accuracy and in efficiency. More precisely, a new clustering strategy was firstly redefined during the building of vocabulary tree, which combined the classification and the conventional K-means method. Then a new matching method to eliminate the error caused by large-scale SIFT was introduced. What was more, a new unit mechanism was adopted to shorten the cost of indexing time. Finally, the numerical results show that an excellent performance is obtained after these improvements. A vocabulary tree with more distinguished nodes is achieved, of which the height is defined automatically and the index accuracy is enhanced greatly. Furthermore, a faster indexing procedure is realized, of which the indexing time is much less than 1 s.
-
Key words:
- SIFT /
- image retrieval /
- inverted-file /
- K-means clustering
-
[1] Lowe D G. Distinctive image features from scaleinvariant keypoints[J]. International Journal of Computer Vision,2004, 60(2): 91-110. [2] Nistér D, Stewénius H. Scalable recognition with a vocabulary tree[C]// IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR).Vol 2. New York, USA, 2006: 2161-2168. [3] Indyk P, Motwani R. Approximate nearest neighbors: towards removing the curse of dimensionality[C]//30-th Annual ACM Symposium on Theory of Computing.New York, USA, 1998: 604-613. [4] Mikolajczyk K, Schmid C. A performance evaluation of local descriptors[J].IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI),2005, 27(10): 1615-1630. [5] [6] Obdrzalek S, Matas J. Sub-linear indexing for large scale object recognition[C]// British Machine Vision Conference(BMVC).Oxford, UK, 2005. [7] 王群伟. 基于SIFT特征点提取的图像检索研究[D]. 硕士学位论文. 武汉: 华中科技大学, 2010.(WANG Qun-wei. Image retrieval based on SIFT feature point detection[D]. Master Thesis. Wuhan: Huazhong University of Science and Technology, 2010.(in Chinese)) [8] Sivic J, Zisserman A. Video google: a text retrieval approach to object matching in videos[C]//9-th IEEE International Conference on Computer Vision (ICCV ). Vol 2. Nice, France, 2003: 1470-1477. [9] Berg A C, Berg T L, Malik J. Shape matching and object recognition using low distortion correspondence[C]// IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). Vol 1. San Diego, USA, 2005: 26-33. [10] 陈作平, 叶正麟, 郑红婵, 赵红星. 基于K-均值聚类的快速分形编码方法[J]. 中国图象图形学报, 2007, 12(4): 586-591.(CHEN Zuo-ping, YE Zheng-lin, ZHENG Hong-chan, ZHAO Hong-xing. Fast fractal coding technique based on K-mean clustering[J]. Journal of Image and Graphics,2007, 12(4): 586-591.(in Chinese)) [11] Beis J S, Lowe D G. Shape indexing using approximate nearest-neighbor search in high-dimensional spaces[C]// IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). San Juan, Puerto Rico, 1997:1000-1006.
点击查看大图
计量
- 文章访问数: 2041
- HTML全文浏览量: 37
- PDF下载量: 2335
- 被引次数: 0