Recognition method of low-resolution coal-rock images based on curvelet transform
-
摘要: 针对小波变换仅能有效表达图像中的点奇异性,难以提取煤岩图像曲线特征的弱点,以及高分辨率煤岩图像计算量大,难以满足煤岩识别实时性要求的问题,提出了一种基于曲波变换的低分辨率煤岩识别方法.该方法通过曲波变换对煤岩图像进行曲波分解,得到各尺度层曲波系数,利用主分量分析进行降维,并将结果分别输入不同k-NN分类器中,对分类结果加权融合,实现煤岩图像的分类识别.实验表明:通过曲波分解提取的特征能够有效地表达煤岩图像的曲线特征,与现有方法相比较,所提出方法具有更高的识别率,平均识别率达95.0%,在煤岩图像分辨率较低情况下也可以获得很高的识别率,满足煤岩识别实时性的要求.Abstract: Considering the limitations of wavelet in image representation—that it is only optimal in representing point singularities and difficult to extract curve features of coal and rock images,a new recognition method for low-resolution coal-rock images based on curvelet transform was proposed.The method used curvelet transform to decompose images into curvelet coefficients in different scales.Then,PCA was applied to obtain a lower dimensional representation that was put into a k-NN classifier. Finally,the final recognition result was obtained via weighted fusion of classification results.Experimental results showed that the features extracted by curvelet decomposition could effectively express the curve features of coal-rock images.Compared with several other existing methods,the proposed method had higher recognition accuracy rate,with the average recognition rate reaching 95.0%.Under the condition of low image resolution can it also get high recognition rate and meet the real-time requirements of coal-rock recognition.
-
Key words:
- curvelet transform /
- coal-rock recognition /
- feature extraction /
- weighted fusion /
- low resolution
-
[1] 孙继平.基于图像识别的煤岩界面识别方法研究[J].煤炭科学技术,2011,39(2):77-79. [2] Sun Jiping.Study on identified method of coal and rock interface based on image identification[J].Coal Science and Technology,2011,39(2):77-79. [3] Bessinger S L,Nelson M G.Remnant roof coal thickness measurement with passive gamma ray instruments in coal mines[J].IEEE Transactions on Industry Application,1993,29(3):562-565. [4] Bausov I Y,Stolarzyk G L,Stolarczyk L G,et al.Look-ahead radar and horizon sensing for coal cutting drums[C]//Proceedings of the 4th International Workshop on Advanced Ground Penetrating Radar,Aula Magna Partenope,2007:208-211. [5] 孙继平,佘杰.基于小波的煤岩图像特征抽取与识别[J].煤炭学报,2013,38(10):1900-1904. [6] Sun Jiping,She Jie.Wavelet-based coal-rock image feature extraction and recognition[J].Journal of China Coal Society,2013,38(10):1900-1904. [7] 郝清玉,朱元忠,陈健.基于图像多小波变换的煤岩界面识别[J].工矿自动化,2015,41(2):50-53. [8] Hao Qingyu,Zhu Yuanzhong,Chen Jian.Coal-rock interface identification based on image multi-wavelet transformation[J].Industry and Mine Automation,2015,41(2):50-53. [9] 金丹,程建远,王保利,等.基于Curvelet 变换的地震资料弱信号识别及去噪方法[J].煤炭学报,2016,41(2):332-337. [10] Jin Dan,Cheng Jianyuan,Wang Baoli,et al.Seismic weak signal identification and noise elimination based on curvelet domain[J].Journal of China Coal Society,2016,41(2):332-337. [11] Starck J C,Candes E J,Donoho D L.The curvelet transform for image denoising[J].IEEE Transactions on Image Processing,2002,11(6):670-684. [12] Hammouche A M,El-Bakry H M,Mostafa R R.Image contrast enhancement using fast discrete curvelet transform via unequally spaced fast fourier transform(FDCT-USFFT)[J].International Journal of Computer Engineering and Information Technology,2016,8(3):36-42. [13] Namratha H N,Raghu M T.Remote sensing satellite image fusion using fast curvelet transforms[J].International Journal of Science and Research,2015,4( 4):1537-1542. [14] Parmer C K,Pancholi P K.Image Compression based on curvelet transform[J].International Journal of Engineering Research & Technology,2013,2(4):2057-2061. [15] Prabha S,Sasikala D M.Texture classification using curvelet transform[J].International Journal of Advancements in Research & Technology,2013,2(4):249-253. [16] Mandal T,Wu Q M J.Face recognition using curvelet based PCA[C]//International Conference on Pattern Recognition,Tampa,Florida USA,2008:1-14. [17] Chitaliya N G,Trivedi A I.Automated vehicle identification system based on discrete curvelet transform for visual surveillance and traffic monitoring system[J].International Journal of Computer Applications,2012,57(1):39-44. [18] Farhad M K,Jalaleddin I,Reihane M,et al.Numeral recognition using curvelet transform[C]//IEEE/ACS International Conference on Computer Systems and Applications.Tehran: Payame Noor University,2008:606-612. [19] Candes E J,Donoho D L.Curvelets—a suprisingly effective nonadaptive representation for objects with edges[C]//Curves and Surfaces.Nashville,TN:Vanderbilt University Press,2000:105-120. [20] Candes E J,Demanet L,Donoho D L,et al.Fast discrete curvelet transforms[R]//Applied and Computational Mathematics.California:California Institute of Technology,2005:1-43. [21] 倪雪,李庆武,孟凡,等.Curvelet变换用于人脸特征提取与识别[J].应用科学学报,2009,27(1):34-38. [22] Ni Xue,Li Qingwu,Meng Fan,et al.Face feature extraction and face recognition using curvelet transform[J].Journal of Applied Sciences,2009,27(1):34-38. [23] 张九龙,张志禹,屈小娥,等.基于曲波与主分量分析的人脸识别[J].计算机应用,2008,28( 5):1255-1256. [24] Zhang Jiulong,Zhang Zhiyu,Qu Xiaoe,et al.Face recognition based on curvelet and PCA[J].Computer Applications,2008,28(5):1255-1256. [25] 杜磊,杜星,宋擒豹.一种k-NN 分类器k值自动选取方法[J].控制与决策,2013,28(7):1073-1077. [26] Du Lei,Du Xing,Song Qinbao.An automatic selection method of k in k-NN classifier[J].Control and Decision,2013,28(7):1073-1077. [27] 黄金钰,张会林,闫日亮.LBP 直方图与PCA 的欧式距离的人脸识别[J].计算机系统应用,2012,21(6):202-204. [28] Huang Jinyu,Zhang Huiling,Yan Riliang.Face recognition of LBP histogram PCA and euclidean distance[J].Computer Systems & Applications,2012,21(6):202-204. [29] Wu Xianxing Zhao Jieyu.Curvelet feature extraction for face recognition and facial expression recognition[R].Sixth International Conference on Natural Computation,2010:1212-1216. [30] 丁晓莲,周激流,李晓华,等.人脸识别率与图像分辨率关系的比较分析[J].人工智能及识别技术,2009,35(11):181-183. [31] Ding Xiaolian,Zhou Jiliu,Li Xiaohua,et al.Comparative analysis of relation between face recognition rate and image resolution[J].Computer Engineering,2009,35(11):181-183.
点击查看大图
计量
- 文章访问数: 631
- HTML全文浏览量: 81
- PDF下载量: 274
- 被引次数: 0