基于高斯尺度空间粗糙度描述子的花粉图像分类识别

doi:10.11772/j.issn.1001-9081.2015.07.2039

计算机应用 ›› 2015, Vol. 35 ›› Issue (7): 2039-2042.DOI: 10.11772/j.issn.1001-9081.2015.07.2039

基于高斯尺度空间粗糙度描述子的花粉图像分类识别

谢永华^1,2, 徐赵飞¹, 范文晓²

1. 南京信息工程大学计算机与软件学院, 南京 210044;
2. 南京信息工程大学江苏省网络监控中心, 南京 210044

收稿日期:2015-01-19 修回日期:2015-03-15 出版日期:2015-07-10 发布日期:2015-07-17
通讯作者: 徐赵飞(1991-),女,江苏无锡人,硕士研究生,主要研究方向:生物图像处理与识别,892210505@qq.com
作者简介:谢永华(1976-),男,江苏靖江人,教授,博士,CCF会员,主要研究方向:模式识别、基于内容的图像检索; 范文晓(1990-),女,江苏连云港人,硕士研究生,主要研究方向:生物图像处理与识别。
基金资助:
国家自然科学基金资助项目(61375030)。

Pollen image classification and recognition based on Gaussian scale-space roughness descriptor

XIE Yonghua^1,2, XU Zhaofei¹, FAN Wenxiao²

1. School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing Jiangsu 210044, China;
2. Jiangsu Engineering Center of Network Monitoring, Nanjing University of Information Science and Technology, Nanjing Jiangsu 210044, China

Received:2015-01-19 Revised:2015-03-15 Online:2015-07-10 Published:2015-07-17

摘要/Abstract

摘要：

针对现有粗糙度描述子大多依赖于灰度值平均值,容易造成图像信息的丢失的问题,提出了一种新的基于高斯尺度空间粗糙度描述子的特征提取方法,并应用于花粉图像的分类和识别。首先,采用高斯金字塔算法,将花粉图像分割成不同层次的尺度空间;然后,在各个尺度空间上提取图像的粗糙度纹理特征;其次,通过计算粗糙度频率直方图的统计分布,提取不同尺度空间的粗糙度描述子(SSRHD);最后,采用欧氏距离计算图像的相似度。通过Confocal和Pollenmonitor图像库上的仿真结果表明,与基于隐马尔可夫模型的轮廓描述子(DHMMD)相比,该描述子在Confocal图像库上的平均正确识别率(CRR)提高了2.32%、平均错误识别率(FRR)降低了0.1%,而在Pollenmonitor图像库上的平均识别率也提高了1.2%。实验结果表明,该描述子能较好地描述花粉颗粒图像的纹理分布,对于花粉图像的旋转和姿态变化也具有良好的鲁棒性。

关键词: 高斯金字塔, 粗糙度, 花粉识别, 纹理特征, 尺度空间

Abstract:

According to the problem that the existing roughness descriptors are mostly dependent on the average grey value, which is easy to cause the loss of image information, a new roughness descriptor based on Gaussian scale space was presented for pollen image classification and recognition. With this method, the Gaussian pyramid algorithm was used to divide the image into several different levels of scale space, and then the roughness texture feature was extracted from the different level scale space. The statistical distribution of roughness frequency was calculated to build the Scale-Space Roughness Histogram Descriptor (SSRHD). At last, the Euclidean distance was used to measure the similarity between images. The simulation results on Confocal and Pollenmonitor image database demonstrate that, compared with Discrete Hidden Markov Model Descriptors (DHMMD), the Correct Recognition Rate (CRR) performed by the SSRHD increases by 2.32% on Confocal and 1.2% on Pollenmonitor, and the False Recognition Rate (FRR) decreases by 0.1% on Confocal. The experimental results show that the SSRHD feature can effectively describe the pollen image texture and it also has good robustness to pollen rotation and pose variation.

Key words: Gaussian pyramid, roughness, pollen recognition, texture feature, scale space

中图分类号:

谢永华, 徐赵飞, 范文晓. 基于高斯尺度空间粗糙度描述子的花粉图像分类识别[J]. 计算机应用, 2015, 35(7): 2039-2042.

XIE Yonghua, XU Zhaofei, FAN Wenxiao. Pollen image classification and recognition based on Gaussian scale-space roughness descriptor[J]. Journal of Computer Applications, 2015, 35(7): 2039-2042.

参考文献

[1] REISERT M, BURKHARDT H. Invariant features for 3D-data based on group integration using directional information and spherical harmonic expansion [C]// ICPR 2006: Proceedings of the 18th International Conference on Pattern Recognition. Piscataway: IEEE, 2006: 206-209.
[2] TIAN H, CUI W, WAN T, et al. A computational approach for recognition of electronic microscope plant pollen images [C]// CISP 2008: Proceedings of the 2008 Congress on Image and Signal Processing. Piscataway: IEEE, 2008: 259-263.
[3] WANG Q, RONNEBERGER O, BURKHARDT H. Rotational in-variance based on Fourier analysis in polar and spherical coordinates [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(9): 1715-1722.
[4] TRAVIESO C M, BRICENO J C, TICAY-RIVAS J R, et al. Pollen classification based on contour features [C]// INES 2011: Proceedings of the 15th International Conference on Intelligent Engineering Systems. Piscataway: IEEE, 2011: 17-21.
[5] RODRIGUEZ-DAMIAN M, CERNADAS E, FORMELLA A, et al. Automatic detection and classification of grains of pollen based on shape and texture [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 2006, 36(4): 531-542.
[6] RODRIGUEZ-DAMIAN M, CERNADAS E, FORMELLA A, et al. Pollen classification using brightness-based and shape-based descriptors [C]// ICPR 2004: Proceedings of the 17th International Conference on Pattern Recognition. Piscataway: IEEE, 2004: 212-215.
[7] WANG S. SIFT based image matching algorithm research [D]. Xi'an: Xidian University, 2013: 37-38.(汪松.基于SIFT算法的图像匹配方法研究[D].西安:西安电子科技大学,2013:37-38.)
[8] PAN Z. Research on matching based on SIFT algorithm [D]. Xi'an: Xidian University, 2013: 19-24.(潘子昂.基于SIFT算法的图像匹配研究[D].西安:西安电子科技大学,2013:19-24.)
[9] CHAMORRO-MARTINEZ J, MARTINEZ-JIMENEZ P. A comparative study of texture coarseness measures [C]// ICIP 2009: Proceedings of the 2009 IEEE International Conference on Image Processing. Piscataway: IEEE, 2009: 1337-1340.
[10] XU G, HUI W, ZHAO H, et al. A new metric algorithm of image textural coarseness [C]// ICCASM 2010: Proceedings of the 2010 International Conference on Computer Application and System Modeling. Piscataway: IEEE, 2010: 544-548.
[11] LI B. Intelligent image processing technology [M]. Beijing: Publishing House of Electronics Industry, 2004: 219-223.(李弼程.智能图像处理技术[M].北京:电子工业出版社,2004:219-223.)
[12] RONNEBERGER O, SCHULTZ E, BURKHARDT H. Automated pollen recognition using 3D volume images from fluorescence microscopy [J]. Aerobiologia, 2002, 18(2): 107-115.
[13] RANZATO M, TAYLOR P E, HOUSE J M, et al. Automatic recognition of biological particles in microscopic images [J]. Pattern Recognition Letters, 2007, 28(1): 31-39.

[1]	蒋考林, 白玮, 张磊, 陈军, 潘志松, 郭世泽. 基于多通道图像深度学习的恶意代码检测[J]. 计算机应用, 2021, 41(4): 1142-1147.
[2]	余英东, 杨怡, 林澜. 结合纹理特征分析的图像风格转换网络[J]. 计算机应用, 2020, 40(3): 638-644.
[3]	郎大鹏, 丁巍, 姜昊辰, 陈志远. 基于多特征融合的恶意代码分类算法[J]. 计算机应用, 2019, 39(8): 2333-2338.
[4]	刘玉珍, 蒋政权, 赵娜. 基于近邻三值模式和协作表示的三维掌纹识别[J]. 计算机应用, 2019, 39(6): 1690-1695.
[5]	翁理国, 刘万安, 施必成, 夏旻. 基于多维多粒度级联森林的高原地区云雪分类[J]. 计算机应用, 2018, 38(8): 2218-2223.
[6]	谢永华, 韩丽萍. 基于主梯度编码局部二进制模式的花粉图像识别[J]. 计算机应用, 2018, 38(6): 1765-1770.
[7]	邹玮刚, 周志辉, 王洋. 基于非降采样轮廓波变换的图像修复算法[J]. 计算机应用, 2017, 37(2): 553-558.
[8]	杨琪莉, 朱兰艳, 李海涛. 改进FAST特征点支持下的实时影像地标匹配算法[J]. 计算机应用, 2016, 36(5): 1404-1409.
[9]	刘珏先, 滕奇志, 王正勇, 何小海. 基于协同表示的多特征融合岩石分类[J]. 计算机应用, 2016, 36(3): 854-858.
[10]	刘军, 白雪. 基于梯度方向直方图与高斯金字塔的车牌模糊汉字识别方法[J]. 计算机应用, 2016, 36(2): 586-590.
[11]	吴伟, 丁香乾, 闫明. 基于异常区域感知的多时相高分辨率遥感图像配准[J]. 计算机应用, 2016, 36(10): 2870-2874.
[12]	韩建栋, 朱婷婷, 李月香. 结合粗糙集与分层思想的彩色图像分割算法[J]. 计算机应用, 2015, 35(7): 2020-2024.
[13]	马强, 王文伟. 融合显著性因子的行人纹理提取[J]. 计算机应用, 2015, 35(11): 3293-3296.
[14]	邓超李火星王志衡. 多通道奇Gabor梯度相关矩阵的角点检测算法[J]. 计算机应用, 2013, 33(12): 3548-3551.
[15]	朱志玲阮秋琦. 结合尺度不变特征变换和Kalman滤波的Mean Shift视频运动目标跟踪[J]. 计算机应用, 2013, 33(11): 3179-3182.

基于高斯尺度空间粗糙度描述子的花粉图像分类识别

Pollen image classification and recognition based on Gaussian scale-space roughness descriptor

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics