基于改进型LBP算法的植物叶片图像识别研究

doi:10.3778/j.issn.1002-8331.2006-0304

摘要/Abstract

摘要：

为了解决LBP算法抽取的纹理特征仅考虑了邻域像素的特征，忽略关键的局部和全局特征的问题，提出一种基于改进型LBP算法的WCM-LBP植物叶片图像特征提取方法。该算法融合了加权局部均值算法WRM-LBP和加权全局均值算法WOM-LBP，通过提取叶片基于区域的关键几何特征和纹理特征对LBP特征描述符进行加权改造，并采用加权局部均值和加权全局均值代替传统的中心像素点，最后将叶片图像的R、G和B通道颜色分量和灰度值作为特征输入矩阵进行图像分析。该算法结合特征加权的模糊半监督聚类算法（SFFD）应用于经典的Flavia、Swedish、Foliage以及自测图片集等4种植物叶片图像数据集中进行实验。实验结果表明，该算法具有很强的鲁棒性，能够有效区分机器视觉下植物叶片图像的关键性识别特征，有效解决叶片图像的分类识别中关键特征的描述问题。

关键词: 图像识别, 全局均值, 特征提取, 颜色分量, 植物叶片

Abstract:

In order to solve the problem of the classic Local Binary Pattern（LBP） algorithm that only the features of neighborhood pixels of the extracted texture features are considered and the key local and global features are ignored during the texture feature extraction process, an improved local binary pattern algorithm named WCM-LBP is proposed, which is combined with WCM-LBP and WOM-LBP, to extract the features from plant leaf images. It extracts the regional key geometry features and texture features of the leaf images to modify the LBP image descriptor, and uses weighted local mean value and weighted global mean value of the pixels instead of traditional center pixel, and finally extracts the color components of R, G, B channel and the common gray value for image analysis. Combined with the algorithm Semi-supervised Fuzzy clustering with Feature Discrimination（SFFD）, this algorithm is applied to the experimental data such as classic Flavia, Swedish, Foliage datasets and self-test photo collections. The experimental results show that the algorithm has strong robustness, can effectively find out the key identification features of plant leaf images under machine vision, and effectively solve the problem of describing the key features in the classification and recognition of leaf images.

Key words: image recognition, global mean value, feature extraction, color component, plant leaf

李龙龙，何东健，王美丽. 基于改进型LBP算法的植物叶片图像识别研究[J]. 计算机工程与应用, 2021, 57(19): 228-234.

LI Longlong, HE Dongjian, WANG Meili. Study of Plant Leaf Image Recognition Based on Improved Local Binary Pattern Algorithm[J]. Computer Engineering and Applications, 2021, 57(19): 228-234.

参考文献

[1] ZHANG S W，HUANG W Z，HUANG Y A，et al.Plant species recognition methods using leaf image：Overview[J].Neurocomputing，2020，408：246-272.
[2] SHAO Y.Supervised global-locality preserving projection for plant leaf recognition[J].Computers and Electronics in Agriculture，2019，158：102-108.
[3] GAO M F，GAO M R，SUáSTEGUI M，et al.Building microbial factories for the production of aromatic amino acid pathway derivatives：From commodity chemicals to plant-sourced natural products[J].Metabolic Engineering，2020，58：94-132.
[4] ZHU X，ZHU M，REN H.Method of plant leaf recognition based on improved deep convolutional neural network[J].Cognitive Systems Research，2018，52：223-233.
[5] TURKOGLU M，HANBAY D.Recognition of plant leaves：An approach with hybrid features produced by dividing leaf images into two and four parts[J].Applied Mathematics & Computation，2019，352：1-14.
[6] LUKIC M，TUBA E，TUBA M.Leaf recognition algorithm using support vector machine with Hu moments and local binary patterns[C]//2017 IEEE 15th International Symposium on Applied Machine Intelligence and Informatics（SAMI），2017：485-490.
[7] LE V N T，APOPEI B，ALAMEH K.Effective plant discrimination based on the combination of local binary pattern operators and multiclass support vector machine methods[J].Information Processing in Agriculture，2019，6（1）：116-131.
[8] MUTHEVI A，UPPU R B.Leaf classification using completed local binary pattern of textures[C]//Advance Computing Conference，2017：870-874.
[9] SALIMA A，HERDIYENI Y，DOUADY S.Leaf vein segmentation of medicinal plant using Hessian matrix[C]//International Conference on Advanced Computer Science & Information Systems，2016.
[10] NARESH Y G，NAGENDRASWAMY H S.Classification of medicinal plants：An approach using modified LBP with symbolic representation[J].Neurocomputing，2016，173：1789-1797.
[11] WANG X，LIANG J，GUO F.Feature extraction algorithm based on dual-scale decomposition and local binary descriptors for plant leaf recognition[J].Digital Signal Processing，2014，34：101-107.
[12] KAYNAR O，ISIK Y E，GORMEZ Y，et al.Fabric defect detection with LBP-GLMC[C]//2017 International Artificial Intelligence and Data Processing Symposium（IDAP），2017：1-5.
[13] FLORINDO J B，BRUNO O M.Texture classification using non-Euclidean Minkowski dilation[J].Physica A：Statal Mechanics and its Applications，2018，493：189-202.
[14] SIIRCI I O，ALBAYRAK A，BILGIN G.Detection of mitotic cells using completed local binary pattern in histopathological images[C]//Signal Processing & Communications Applications Conference，2015：1078-1081.
[15] TUNCER T，AVCI E.Yerel ?kili ?rüntü Tabanli Veri Gizleme Algoritmasi：LBP-LSB[J].Türkiye Bili?im Vakf?Bilgisayar Bilimleri ve Mühendisli?i Dergisi，2017，10（1）：48-53.
[16] LI L L，JONATHAN G，HE D J，et al.Semi-supervised fuzzy clustering with feature discrimination[J].Plos One，2015，10（9）：e0131160.
[17] 李龙龙，何东健，王美丽.基于图像分析的叶片特征识别相关度[J].计算机工程与设计，2016，37（8）：2259-2263.
LI L L，HE D J，WANG M L.Leaf feature relevance for recognition rate based on image analysis algorithm[J].Computer Engineering and Design，2016，37（8）：2259-2263.