Recognition of Plants with Complicated Background by Leaf Features

Leaf classification is a significant and meaningful work. However, the interference and overlapping of objects may affect the recognition effect of leaves with complicated background. In this paper, a hybrid framework of classifying leaves with complicated background is proposed. Firstly, a novel watershed segmentation based on iterative opening and closing reconstruction is introduced to segment leaves from complicated background, which contains texture and shape information of leaf. Then, the block Local Binary Pattern(LBP) operators, whose dimensionality is reduced by locally linear embedding(LLE), are extracted as texture features. In addition, the shape features of leaves are described with the Fourier descriptors. Finally, the texture features and shape features are combined as the input of Support Vector Machine(SVM) classifier to realize the accurate classification of plant species. Experimental results show that the proposed method is effective.

[1]  J. Liu,et al.  Plant leaf classification based on weighted locally linear embedding , 2010, Third International Workshop on Advanced Computational Intelligence.

[2]  Paolo Remagnino,et al.  Plant Texture Classification Using Gabor Co-occurrences , 2010, ISVC.

[3]  Luc Vincent,et al.  Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Zheru Chi,et al.  Machine learning techniques for ontology-based leaf classification , 2004, ICARCV 2004 8th Control, Automation, Robotics and Vision Conference, 2004..

[5]  Xiaofeng Wang,et al.  Classification of plant leaf images with complicated background , 2008, Appl. Math. Comput..

[6]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[7]  Ghassan Hamarneh,et al.  Watershed segmentation using prior shape and appearance knowledge , 2009, Image Vis. Comput..

[8]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[9]  T. Suk,et al.  Leaf recognition of woody species in Central Europe , 2013 .

[10]  David Jones,et al.  Individual leaf extractions from young canopy images using Gustafson-Kessel clustering and a genetic algorithm , 2006 .

[11]  Paolo Remagnino,et al.  Plant species identification using digital morphometrics: A review , 2012, Expert Syst. Appl..

[12]  Jyotismita Chaki,et al.  Plant leaf recognition using texture and shape features with neural classifiers , 2015, Pattern Recognit. Lett..

[13]  Odemir Martinez Bruno,et al.  Fractal analysis of leaf-texture properties as a tool for taxonomic and identification purposes: a case study with species from Neotropical Melastomataceae (Miconieae tribe) , 2010, Plant Systematics and Evolution.

[14]  G. Meyer,et al.  Color indices for weed identification under various soil, residue, and lighting conditions , 1994 .

[15]  Berrin A. Yanikoglu,et al.  Morphological features for leaf based plant recognition , 2013, 2013 IEEE International Conference on Image Processing.

[16]  R. Radha,et al.  An Effective Algorithm for Edges and Veins Detection in Leaf Images , 2014, 2014 World Congress on Computing and Communication Technologies.

[17]  Yuxuan Wang,et al.  A Leaf Recognition Algorithm for Plant Classification Using Probabilistic Neural Network , 2007, 2007 IEEE International Symposium on Signal Processing and Information Technology.

[18]  Matti Pietikäinen,et al.  A comparative study of texture measures with classification based on featured distributions , 1996, Pattern Recognit..

[19]  Arvind R. Yadav,et al.  Hardwood species classification with DWT based hybrid texture feature extraction techniques , 2015 .

[20]  C. Berg,et al.  Comparative morphology of populations of Monstera Adans. (Araceae) from natural forest fragments in Northeast Brazil using elliptic Fourier Analysis of leaf outlines , 2008, Kew Bulletin.