全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

随机亮度差量化的二进制特征描述

DOI: 10.11834/jig.20140418

Keywords: 多媒体技术,局部特征,图像检索,二进制特征

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的传统的基于浮点型向量表示的图像局部特征描述子(如SIFT、SURF等)已经成为计算机视觉研究和应用领域的重要工具,然而传统的高维特征向量在基于内容的大规模视觉检索应用中存在着维度灾难的问题,这使得传统浮点型视觉特征在大规模多媒体数据应用中面临严峻挑战。为了解决浮点型特征的计算复杂度高以及存储空间开销大的问题,越来越多的计算机视觉研究团队开始关注和研究基于二进制表达的局部特征并取得了重要进展。方法首先介绍了二进制特征的相关工作,并对这些方法进行了分类研究,在此基础上提出了基于亮度差量化的特征描述算法。有别于传统二进制特征描述算法,本文算法首先对图像局部进行随机像素点对采样,并计算像素点对之间的亮度差,通过对亮度差值作二进制量化得到图像的局部二进制特征。结果本文算法在公共数据集上与目前主流的几种二进制特征提取算法进行了比较评价,实验结果表明,本文二进制特征在特征匹配准确率和召回率上超过目前主流的几种二进制描述子,并且同样具有极高的计算速度和存储效率。结论通过实验结果验证,本文二进制特征在图像条件发生变化时仍然能保持一定的鲁棒性。

References

[1]  Lowe G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60: 91-110.
[2]  Bay H, Tuytelaars T, Van G. SURF: speeded up robust features.[C]//Proceedings of the 9th European Conference on Compu-ter Vision Graz. Berlin: Springert, 2006, 3951:404-417.
[3]  Ke Y, Sukthankar R. PCA-SIFT: a more distinctive representation for local image descriptors[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington DC: IEEE, 2004, 2: 506-513.
[4]  Indyk P, Motwani R. Approximate nearest neighbors: towards removing the curse of dimensionality[C]//The 30th Annual ACM Symposium on Theory of Computing. Dallas, USA: ACM, 1998: 604-613.
[5]  Weiss Y, Torralba A B, Fergus R. Spectral hashing[J]. Neural Information Processing Systems, 2008: 1753-1760
[6]  Kulis B, Grauman K. Kernelized locality-sensitive hashing for scalable image search[C]//Proceedings of the 12th IEEE International Conference on Computer Vision. Kyoto, Japan: IEEE, 2009: 2130-2137.
[7]  Raginsky M, Lazebnik, S. Locality-sensitive binary codes from shift-invariant kernels[J]. The Neural Information Processing Systems, 2009, 23:1509-1517.
[8]  Wang J, Kumar S, Chang S F. Semi-supervised hashing for large-scale search[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34:2393-2406.
[9]  Strecha C, Bronstein A, Bronstein M, Fua P. LDAHash: improved matching with smaller descriptors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34:66-78.
[10]  Zhou W, Lu Y, Li H, et al. Scalar quantization for large scale image search[C]//Proceedings of the 20th ACM International Conference on Multimedia. Nara, Japan: ACM, 2012: 169-178.
[11]  Gupta R, Mittal A, Forsyth D, et al. SMD: a locally stable monotonic change invariant feature descriptor[C]//Proceedings of the 10th European Conference on Computer Vision. Berlin: Springer, 2008, 5303: 265-277.
[12]  Calonder M, Lepetit V, Ozuysal M, et al. BRIEF: computing a local binary descriptor very fast[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34: 1281-1298.
[13]  Rosten E, Drummond T. Fusing points and lines for high performance tracking[C]//Proceedings of the 10th IEEE International Conference on Computer Vision. Beijing, China: IEEE, 2005, 2: 1508-1515.
[14]  Leutenegger S, Chli M, Siegwart R. BRISK: binary robust invariant scalable keypoints[C]//Proceedings of the 13rd IEEE International Conference on Computer Vision. Barcelona, Spain: IEEE, 2011: 2548-2555.
[15]  Alahi A, Ortiz R, Vandergheynst P. FREAK: fast retina keypoint[C]//Proceedings of the 25th IEEE Conference on Computer Vision and Pattern Recognition. Rhode Island, Providence, USA: IEEE, 2012: 16-21.
[16]  Rublee E, Rabaud V, Konolige K, et al. ORB: an efficient alternative to SIFT or SURF[C]//Proceedings of the 13th IEEE International Conference on Computer Vision. Barcelona, Spain: IEEE, 2011: 2564-2571.
[17]  Mikolajczyk K, Schmid C. A performance evaluation of local descriptors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, (27): 1615-1630.
[18]  Harris C, Stephens M. A combined corner and edge detector[C]//Proceedings of Alvey Vision Conference. Manchester, Britain: BMVA, 1988: 147-151.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133