WAPSI: Web Application for Plant Species Identification Using Fuzzy Image Retrieval

In this paper, a Web Application for Plant Species Identification (WAPSI) that incorporates content-based image retrieval (CBIR) is described. At the heart of this application is a shape-based leaf image retrieval system which uses a contour descriptor based on the curvature of the leaf contour which reduces the number of points for the shape representation. Futhermore, a two-step algorithm for retrieval is used which in the first step reduces the database using some geometrical features. Secondly, leaf images are ranked using a similarity measure between the contour representations. The similarity function between images uses a variant triangular membership function to calculate the distance between the characteristic points’ vectors. This membership function is the key of the good results obtained. The effectiveness for plant species identification of the method is shown through several experiments using our Web application.

[1]  Zheru Chi,et al.  Fuzzy integral for leaf image retrieval , 2002, 2002 IEEE World Congress on Computational Intelligence. 2002 IEEE International Conference on Fuzzy Systems. FUZZ-IEEE'02. Proceedings (Cat. No.02CH37291).

[2]  Seymour Papert.  Uses of Technology to Enhance Education , 1973 .

[3]  Xiaofeng Wang,et al.  Leaf shape based plant species recognition , 2007, Appl. Math. Comput..

[4]  Jing Liu,et al.  A Method of Plant Leaf Recognition Based on Locally Linear Embedding and Moving Center Hypersphere Classifier , 2009, ICIC.

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

[6]  Liqun Han.  Recognition of the part of growth of flue-cured tobacco leaves based on support vector machine , 2008, 2008 7th World Congress on Intelligent Control and Automation.

[7]  Farzin Mokhtarian,et al.  Scale-Based Description and Recognition of Planar Curves and Two-Dimensional Shapes , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Chomtip Pornpanomchai,et al.  Thai Herb Leaf Image Recognition System (THLIRS) , 2011 .

[9]  Zhiyong Wang,et al.  Shape based leaf image retrieval , 2003 .

[10]  Yunyoung Nam,et al.  ELIS: An Efficient Leaf Image Retrieval System , 2005, ICAPR.

[11]  Sean White,et al.  Exploring interfaces to botanical species classification , 2010, CHI EA '10.

[12]  Yan-Cheng Zhang,et al.  Features selection of cotton disease leaves image based on fuzzy feature selection techniques , 2007, 2007 International Conference on Wavelet Analysis and Pattern Recognition.

[13]  Carlos Caballero,et al.  Plant species identification using leaf image retrieval , 2010, CIVR '10.

[14]  Shanwen Zhang,et al.  A Method of Plant Classification Based on Wavelet Transforms and Support Vector Machines , 2009, ICIC.