电力设备铭牌特征提取方法的应用研究
Application Research of Feature Extraction Method of Power Equipment Nameplate
DOI: 10.12677/CSA.2019.911234, PDF,  被引量   
作者: 吴彦直：杭州市学军中学，浙江 杭州；李 志, 郑志曜：浙江华电器材检测研究所有限公司，浙江 杭州；王 勇*, 黄志朗：中国地质大学(武汉)，湖北 武汉
关键词: 电力设备铭牌；SIFT；多尺度特征提取；Power Equipment Nameplate； SIFT； Multi-Scale Feature Extraction
摘要: 电力设备铭牌图像在特征提取问题上，由于其本身的底层特征较为相似，采用传统的特征提取方法往往无法得到较好的特征表达。另一方面，随着近年来科学家们对基于不变性特征提取方法的研究逐渐兴起，以SIFT算法为代表的基于多尺度空间的特征算法在特征表达上具有良好的表现。本文针对SIFT方法，以及其改进的SURF和ORB算法在电力设备铭牌特征提取上的应用进行研究，并通过实验分析得到最适于电力设备铭牌图像的特征提取算法。
Abstract: In the feature extraction problem of power equipment nameplate image, because of its similar underlying features, traditional feature extraction methods often fail to obtain better feature representation. On the other hand, with the development of invariant feature extraction methods in recent years, the feature algorithm based on multi-scale space represented by SIFT algorithm has a good performance in feature representation. In this paper, the SIFT method and its improved SURF and ORB algorithms are applied to the extraction of power equipment nameplate features. The ex-perimental results show that SURF is the most suitable feature extraction algorithm for power equipment nameplate images.
文章引用：吴彦直, 李志, 王勇, 黄志朗, 郑志曜. 电力设备铭牌特征提取方法的应用研究[J]. 计算机科学与应用, 2019, 9(11): 2084-2097. https://doi.org/10.12677/CSA.2019.911234

参考文献

[1] Lowe, D.G. (2004) Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vi-sion, 60, 91-110. [Google Scholar] [CrossRef] 
[2] Yue, S.C., Wang, Q. and Zhao, R.C. (2009) Robust Wide Baseline Point Matching Based on Scale Invariant Feature Descriptor. Chinese Journal of Aero-nautics, 22, 70-74. [Google Scholar] [CrossRef] 
[3] Xu, Y.-P., Hu, K.-N., Tian, Y., et al. (2008) Classification of Hyper-Spectral Imagery Using SIFT for Spectral Matching. Proceedings of the 1st International Conference on Image and Signal Processing, Sanya, 27-30 May 2008, 704-708. [Google Scholar] [CrossRef] 
[4] 林传力, 赵宇明. 基于Sift特征的商标检索算法[J]. 计算机工程, 2008, 34(23): 275-277.
[5] 洪志令. 基于形状匹配的商标图像检索技术研究[D]: [博士学位论文]. 厦门: 厦门大学, 2008.
[6] 周明全, 耿国华, 韦娜. 基于内容图像检索技术[M]. 北京: 清华出版社, 2007.
[7] 孙剑, 徐宗本. 计算机视觉中的尺度空间方法[J]. 工程数学学报, 2005(6): 5-16.
[8] 张俭嘉. 视觉分类及其在场景分析中的应用[D]: [硕士学位论文]. 南京: 东南大学, 2012.
[9] 张华贵. 基于局部关键点特征的视频近重复检测算法研究[D]: [硕士学位论文]. 上海: 复旦大学, 2012.
[10] Dai, X.B., Zhang, H., Shu, H.Z. and Luo, L.M. (2010) Image Recognition by Combined Invariants of Legendre Moment. IEEE International Conference on Information and Automa-tion, Harbin, 20-23 June 2010, 1793-1798.
[11] Bin, Y. and Xiong, P.J. (2002) Improvement and Invariance Analysis of Zernike Moments. International Conference on Communications, Circuits and Systems and West Sino Expositions, Chengdu, 29 June-1 July 2002, 963-967.
[12] Bay, H., Ess, A., Tuytelaars, T. and Van Gool, L. (2007) Speeded-Up Robust Features (SURF). Computer Vision and Image Understanding, 110, 346-359. [Google Scholar] [CrossRef] 
[13] Rublee, E., Rabaud, V., Konolige, K. and Bradski, G. (2011) ORB: An Efficient Alternative to SIFT or SURF. IEEE International Conference on Computer Vision, Barcelona, 6-13 No-vember 2011, 2. [Google Scholar] [CrossRef] 
[14] Rosin, P.L. (1999) Measuring Corner Properties. Computer Vi-sion and Image Understanding, 73, 291-307. [Google Scholar] [CrossRef]