Plant leaf identification based on the multi-feature fusion and deep belief networks method
-
摘要: 基于叶片数字图像的植物识别是自动植物分类研究的热点。但是随着植物种类的增加,传统的分类方法由于提取的特征比较单一或者分类器结构过于简单,导致叶片识别率较低。为此,本文提出使用纹理特征结合形状特征进行识别,并且使用深度信念网络构架作为分类器。纹理特征通过局部二值模式、Gabor滤波和灰度共生矩阵方法得到。而形状特征向量由Hu氏不变量和傅里叶描述子组成。为了避免过拟合现象,使用“dropout”方法训练深度信念网络。这种基于多特征融合的深度信念网络的植物识别方法,在Flavia数据库中,对32种叶片的识别率为99.37%;在ICL数据库中,对220种叶片的识别率为93.939%。这表明相比一般的叶片识别方法,此方法鲁棒性更强,并且识别率更高。Abstract: Plant identification based on digital leaf image is a hot topic in research of automatic classification of plants. However, with the increase in the number of plant species, the leaf recognition rate is low due to the single trait extraction and simple structure classifier in the traditional classification methods. This study applied the combination of texture features and shape features for identification, using the deep belief networks (DBNs) as the classifier. Texture features are derived from local binary patterns, Gabor filters and gray level co-occurrence matrix while shape feature vector is modeled using Hu Moment invariants and Fourier descriptors. In order to avoid overfitting, we trained the DBNs with “dropout” method. The proposed algorithm was tested on the Flavia dataset, and the recognition rate was 99.37% for 32 species, while on the ICL dataset the recognition rate was 93.939% for 220 kinds of leaves. The experimental results illustrated that the proposed method has stronger robustness and higher recognition rate compared to the traditional methods.
-
-
[1] XIAO X Y. Study on features of plant leaf image recognition and realization of online recognition system[D]. Hefei: University of Science and Technology of China, 2011.
[1] 肖雪洋. 植物叶片图像识别特征的研究和在线识别系统实现[D]. 合肥:中国科学技术大学, 2011. [2] COPE J S, CORNEY D, CLARK J Y, et al. Plant species identification using digital morphometrics: a review[J]. Expert Systems with Applications, 2012, 39(8): 7562-7573.
[2] QI H N, SHOU T, JIN S H. Leaf characteristics-based computer-aided plant identification model[J]. Journal of Zhejiang Forestry College, 2003, 20(3):281-284.
[3] 祁亨年, 寿韬, 金水虎. 基于叶片特征的计算机辅助植物识别模型[J]. 浙江林学院学报, 2003, 20(3): 281-284. [3] HOU T, YAO L H, KAN J M.Plant recognition research based on shape features of leaf[J]. Hunan Agricultural Sciences, 2009(4):123-125,129.
[4] WANG L J, HUAI Y J, PENG Y C.Method of identification of foliage from plants based on extraction of multiple features of leaf images[J]. Journal of Beijing Forestry University, 2015, 37(1):96-104.
[4] NETO J C, MEYER G E, JONES D D, et al. Plant species identification using elliptic fourier leaf shape analysis[J]. Computers and Electronics in Agriculture, 2006, 50(2): 121-134.
[5] YU K, JIA L, CHEN Y Q, et al.Deep learning: yesterday, today, and tomorrow[J]. Journal of Computer Research and Development, 2013,50(9): 1799-1804.
[5] WANG X F, HUANG D S, DU J X, et al. Classification of plant leaf images with complicated background[J]. Applied Mathematics and Computation, 2008, 205(2): 916-926.
[6] 侯铜, 姚立红, 阚江明. 基于叶片外形特征的植物识别研究[J]. 湖南农业科学, 2009(4): 123-125,129. [6] YUAN B H, WANG H, REN M W. Face recognition based on completed local binary pattern[J]. Application Research of Computer, 2012, 29(4): 1557-1559.
[7] HUANG F F, LI J W, WANG W, et al. Human face description and recognition combining wavelet analysis and LBP operator[J]. Journal of Chongqing Institute of Technology (Natural Science), 2009, 23(1): 102-108.
[7] ANDRADE I M, MAYO S J, KIRKUP D, et al. Comparative morphology of populations of Monstera adans(Araceae) from natural forest fragments in Northeast Brazil using elliptic fourier analysis of leaf outlines[J]. Kew Bulletin, 2008, 63(2): 193-211.
[8] SHEN L L, JI Z. Gabor wavelet selection and SVM classification for object recognition[J]. ACTC Automatic Sinici, 2009, 35(4): 350-355.
[8] DU J X, ZHAI C M, WANG Q P. Recognition of plant leaf image based on fractal dimension features[J]. Neurocomputing, 2013, 116: 150-156.
[9] COPE J S, REMAGNINO P, BARMAN S, et al. Plant texture classification using gabor co-occurrences [M]. Berlin Heidelberg: Springer, 2010: 669-677.
[9] LIU L, KUANG G Y. Overview of image textural feature extraction methods[J]. Journal of Image and Graphics, 2009, 14(4): 622-635.
[10] CHAKI J, PAREKH R, BHATTACHARYA S. Plant leaf recognition using texture and shape features with neural classifiers[J]. Pattern Recognition Letters, 2015, 58: 61-68.
[10] KAN J M, WANG Y X, YANG X W, et al.Plant recognition method based on leaf images[J]. Science and Technology, 2010, 28(23):81-85.
[11] 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): 96-104. [11] REN G Z, JIANG T. Study on GLCM-based texture extraction methods[J]. Computer Applications and Software, 2014, 31(11): 190-192,325.
[12] DAI L R, ZHANG S L. Deep speech signal and information processing: research process and prospect[J]. Journal of Data Acquisition and Processing, 2014, 29(2): 171-179.
[12] WU S G, BAO F S, XU E Y, et al. A leaf recognition algorithm for plant classification using probabilistic neural network[C]∥2007 IEEE international symposium on signal processing and information technology. Cairo: IEEE, 2007: 11-16.
[13] NOVOTNY P, SUK T. Leaf recognition of woody species in central Europe[J]. Biosystems Engineering, 2013, 115(4): 444-452.
[13] CHAI R M, CAO Z J.Face recognition algorithm based on Gabor wavelet and deep belief networks [J]. Journal of Computer Applications, 2014, 34(9): 2590-2594.
[14] 余凯,贾磊,陈雨强,等. 深度学习的昨天, 今天和明天[J]. 计算机研究与发展, 2013,50(9): 1799-1804. [14] ZHENG Y, CHENG Q Q, ZHANG Y J. Deep learning and its new progress in object and behavior recognition[J]. Journal of Image and Graphics, 2014, 19(2): 175-184.
[15] HU R, JIA W, LING H, et al. Multiscale distance matrix for fast plant leaf recognition[J]. IEEE Transactions on Image Processing, 2012, 21(11): 4667-4672.
[16] 袁宝华, 王欢,任明武. 基于完整LBP特征的人脸识别[J]. 计算机应用研究, 2012, 29(4): 1557-1559. [17] 黄非非,李见为,王玮,等. 结合小波分析和LBP算子的人脸描述与识别[J]. 重庆工学院学报(自然科学版), 2009, 23(1): 102-108. [18] 沈琳琳,纪震. 采用精选Gabor小波和SVM分类的物体识别[J]. 自动化学报, 2009, 35(4): 350-355. [19] 刘丽,匡纲要. 图像纹理特征提取方法综述[J]. 中国图象图形学报, 2009, 14(4): 622-635. [20] 阚江明,王怡萱,杨晓微,等. 基于叶片图像的植物识别方法[J]. 科技导报, 2010, 28(23): 81-85. [21] 任国贞,江涛. 基于灰度共生矩阵的纹理提取方法研究[J]. 计算机应用与软件, 2014, 31(11): 190-192,325. [22] 戴礼荣,张仕良. 深度语音信号与信息处理: 研究进展与展望[J]. 数据采集与处理, 2014, 29(2): 171-179. [23] 柴瑞敏,曹振基. 基于Gabor小波与深度信念网络的人脸识别方法[J]. 计算机应用, 2014, 34(9): 2590-2594. [24] HINTON G, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554.
[25] 郑胤,陈权崎,章毓晋. 深度学习及其在目标和行为识别中的新进展[J]. 中国图象图形学报, 2014, 19(2): 175-184. [26] PALM R B. Prediction as a candidate for learning deep hierarchical models of data[D]. Kongens Lyngby: Technical University of Denmark, 2012.
[27] BENGIO Y. Learning deep architectures for AI[J]. Foundations and Trends in Machine Learning, 2009, 2(1): 1-127.
[28] HINTON G. A practical guide to training restricted Boltzmann machines[J]. Momentum, 2010, 9(1): 926.
[29] SRIVASTAVA N, HINTON G E, KRIZHEVSKY A, et al. Dropout: a simple way to prevent neural networks from overfitting [J]. The Journal of Machine Learning Research, 2014, 15(1) :1929-1958.
[30] SARI C, AKGUL C B, SANKUR B. Combination of gross shape features, fourier descriptors and multiscale distance matrix for leaf recognition[C]∥55th International symposium on ELMAR. Zadar: IEEE, 2013: 22-26.
[31] 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.
[32] LEI Y K, ZOU J W, DONG T, et al. Orthogonal locally discriminant spline embedding for plant leaf recognition[J]. Computer Vision and Image Understanding, 2014, 119: 116-126.
-
期刊类型引用(2)
1. 李建建，贺宸靖，黄小平，向太和. 植物长链非编码RNA调控发育与胁迫应答的研究进展. 生物技术通报. 2023(01): 48-58 . 
百度学术
2. 黄杰，陈勇，高日芳，毛莹莹，郑柏艳，张帆涛，谢建坤. 长链非编码RNA:与植物发育和胁迫响应相关的新型调控因子. 江西师范大学学报(自然科学版). 2023(06): 615-625 . 百度学术
其他类型引用(3)
计量
- 文章访问数: 2487
- HTML全文浏览量: 332
- PDF下载量: 60
- 被引次数: 5
下载:
