[1]梅星宇,李新华,鲍文霞,等.基于复频域纹理特征的植物叶片识别算法[J].江苏农业学报,2019,(06):1334-1339.[doi:doi:10.3969/j.issn.1000-4440.2019.06.009]
　MEI Xing-yu,LI Xin-hua,BAO Wen-xia,et al.Research of leaf recognition algorithm based on complex frequency domain texture features[J].,2019,(06):1334-1339.[doi:doi:10.3969/j.issn.1000-4440.2019.06.009]
点击复制

基于复频域纹理特征的植物叶片识别算法()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2019年06期
页码:
1334-1339
栏目:
耕作栽培·资源环境
出版日期:
2019-12-31

文章信息/Info

Title:
Research of leaf recognition algorithm based on complex frequency domain texture features
作者:
梅星宇; 李新华; 鲍文霞; 张东彦; 梁栋
（安徽大学农业生态大数据分析与应用技术国家地方联合工程研究中心，安徽合肥230601）
Author(s):
MEI Xing-yu; LI Xin-hua; BAO Wen-xia; ZHANG Dong-yan; LIANG Dong
(National Engineering Research Center for Agro-Ecological Big Data Analysis and Application, Anhui University, Hefei 230601, China)
关键词:
植物叶片识别; 复频域纹理特征; 双树复小波变换
Keywords:
plant leaf recognition; complex frequency domain texture features; dual-tree complex wavelet transform
分类号:
TP391; S126
DOI:
doi:10.3969/j.issn.1000-4440.2019.06.009
文献标志码:
A
摘要:
针对空间域特征不能全面准确地描述叶片的问题，提出了一种基于复频域纹理特征（Complex frequency domain texture features，CFDTF）的叶片识别算法。首先，对叶片图像进行预处理。其次，对预处理后的图像进行分块，并对每一个图像块进行双树复小波变换（Dual-tree complex wavelet transform，DTCWT），分别计算复频域局部二值模式（Local binary pattern，LBP）和局部相位量化（Local phase quantization，LPQ）特征，得到图像块的特征。接着，串联所有图像块的特征得到整个图像的特征。最后，在Flavia数据库上通过KNN分类器分类识别。结果表明，与传统的颜色、形状、纹理等特征相比，该算法平均识别精度明显提高，达到95.75%。
Abstract:
In the most time, the traditional spatial domain feature cannot describe a leaf completely and accurately. In this study, an algorithm of leaf recognition based on complex frequency domain texture features (CFDTF) was proposed. Firstly, the image of leaf should be preprocessed. Secondly, the preprocessed image could be divided into many blocks, and every image block was processed by the dual-tree complex wavelet transform (DTCWT). Next, the local binary pattern (LBP) and local phase quantization (LPQ) features of image blocks were calculated respectively, and the features of image blocks were obtained. Thirdly, all block features were concatenated to obtain the feature of an entire image. Finally, KNN classifier was used for classification and recongnition in the Flavia dataset. Compared with the traditional color, shape, texture and other features, the average recognition accuracy of our algorithm was significantly improved, reaching 95.75%.

参考文献/References:

[1]WU S G, BAO F S, XU E Y, et al. A leaf recognition algorithm for plant classification using probabilistic neural network[C]//IEEE. 2007 IEEE international symposium on signal processing and information technology. New York: IEEE, 2007: 11-16.
[2]王艳菲, 朱俊平, 蔡骋. 基于CENTRIST 的植物叶片识别研究与实现[J]. 计算机工程与设计, 2012, 33(11): 4343-4346.
[3]KULKARNI A H, RAI H M, JAHAGIRDAR K A, et al. A leaf recognition technique for plant classification using RBPNN and Zernike moments[J]. International Journal of Advanced Research in Computer and Communication Engineering, 2013, 2(1): 984-988.
[4]CARRANZA-ROJAS J, MATA-MONTERO E. Combining leaf shape and texture for Costa Rican plant species identification[J]. Clei Electronic Journal, 2016, 19(1): 7.
[5]KUMAR N, BELHUMEUR P N, BISWAS A, et al. Leafsnap: A computer vision system for automatic plant species identification[C]// FITZGIBBON A. European conference on computer vision. Berlin: Springer, 2012: 502-516.
[6]郑一力, 钟刚亮, 王强, 等. 基于多特征降维的植物叶片识别方法[J]. 农业机械学报, 2017, 48(3): 30-37.
[7]李洋, 李岳阳, 罗海驰, 等. 基于形状特征的植物叶片在线识别方法[J]. 计算机工程与应用, 2017, 53(2): 162-165.
[8]姜枫, 顾庆, 郝慧珍, 等. 基于内容的图像分割方法综述[J]. 软件学报, 2017, 28(1): 160-183.
[9]朱长水, 丁勇, 袁宝华, 等. 融合 LBP 和 LPQ 的人脸识别[J]. 南京师大学报 (自然科学版), 2015, 38 (1): 104-107.
[10]SELESNICK I W, BARANIUK R G, KINGSBURY N C. The dual-tree complex wavelet transform[J]. IEEE Signal Processing Magazine, 2005, 22(6): 123-151.
[11]OJALA T, PIETIKAINEN M, MAENPAA T. Multiresolution 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.
[12]OJANSIVU V, HEIKKILA J. Blur insensitive texture classification using local phase quantization[C]//ELMOATZA A. International conference on image and signal processing. Berlin: Springer, 2008: 236-243.
[13]周志华. 机器学习[M]. 北京: 清华大学出版社, 2016: 225-226.
[14]李航. 统计学习方法[M]. 北京: 清华大学出版社, 2012: 39-40.
[15]王丽君, 淮永建, 彭月橙. 基于叶片图像多特征融合的观叶植物种类识别[J]. 北京林业大学学报, 2015, 37(1): 55-61.
[16]王昊鹏, 李慧. 基于局部二值模式和灰度共生矩阵的籽棉杂质分类识别[J]. 农业工程学报, 2015, 31(3): 236-241.

备注/Memo

备注/Memo:
收稿日期：2019-02-20 基金项目：国家自然科学基金项目（41771463、61672032） 作者简介：梅星宇（1992-），男，安徽安庆人，硕士研究生，研究方向为计算机视觉。(E-mail) meixingyu@163.com 通讯作者：李新华，(E-mail)lixinhua@ahu.edu.cn
更新日期/Last Update: 2020-01-09