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...

基于WBCT和LBP融合的焦炭显微图像识别方法

DOI: 10.11834/jig.20091026

Keywords: 焦炭显微图像,光学组织,多尺度几何分析,小波分解Contourlet变换,局部二进制模式

Full-Text   Cite this paper   Add to My Lib

Abstract:

焦炭显微光学组织的分类识别是判定焦炭质量和指导生产配煤的关键内容,由于传统的空域和频域方法效果都不理想,提出了一种基于小波分解Contourlet变换(WBCT)与局部二进制模式(LBP)融合的焦炭显微图像识别算法。首先,运用WBCT对图像进行多尺度多方向分解,提取出各子频带的统计特征量;然后,在空域采用均匀LBP算子,计算图像LBP特征描述子;最后,根据融合的相似性度量准则判断图像的光学组织类别。与其他方法对比实验结果表明,该算法不仅可获得更高的识别精度,而且具有较强的抗干扰能力,尤其是对泊松分布噪声敏感性较小,因此,适合于焦炭显微图像的分析。

References

[1]  Jiao Li-cheng,Tan Shan.Development and prospect of image multiscale geometric analysis[J].Chinese Journal of Electronics,2003,31(12A):43-50.[焦李成,谭山.图像多尺度几何分析:回顾和展望[J].电子学报,2003,31(12A):43-50.]
[2]  Eslami R,Radha H.Wavelet-based contourlet transform and its application to image coding[A].In:Proceedings of International Conference on Image Processing[C],Singapore,2004:3189-3192.
[3]  Yang Jia-hong,Xu Can-hui,Wang Yao-nan.Texture image retrieval based on transform using generalized Gaussian model[J].Journal of Image and Graphics,2007,12(4):691-694.[杨家红,许灿辉,王耀南.基于Contourlet广义高斯模型的纹理图像检索[J].中国图象图形学报,2007,12(4):691-694.]
[4]  Yang Jian-li,Stonsberry P G,Zondlo J W,et al.Characteristics and carbonization behaviors of coal extracts[J].Fuel Processing Technology,2002,79(3):207-215.
[5]  Gluckman J.Visually distinct patterns with matching sub-band statistics[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(2):252-264
[6]  Ojala T,Pietikainen M,Maenpaa T.Multi-resolution gray-scale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[7]  Do M N,Vetterli M.Contourlets Beyond Wavelets[M].Stoeckler J and Welland G V eds.New York,USA:Acdemic Press,2002:1-27.
[8]  Ahonen T,Hadid A,Pietikainen M.Face recognition with local binary patterns[A].In:Proceedings of 8th European Conference on Computer Vision[C],Prague,Czech,2004:469-481.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133