Plant Leaf Classification Using Soft Computing Techniques

For the existence of human living and development, plants play a crucial part. In order to effectively collect and preserve the genetic resources, the intra- and inter-specific variations must be estimated in proper manner. In plant classification, the leaf shape plays a significant role. In machine intelligence, the most significant part essential for both decision-making and data processing is shape recognition. In this paper, a feed forward neural network is used to automate the leaf recognition for plant classification. The classification accuracy of the proposed method Normalized Cubic Spline Feed Forward Neural Network (NCS - FFNN) is compared with RBF, CART and MLP. approximately two-dimensional and it is three-dimensional for flowers. The complex 3D structures (7) of the shapes and structures of flowers make it difficult to be analyzed. And also, in all seasons leaves are easily obtained and collected everywhere whereas, only during the blooming season the flowers can be collected. Hence, for computer-aided plant classification, leaves are widely used. In this paper, a feed forward neural network is used to automate the leaf recognition for plant classification. The classification accuracy of the proposed Normalized Cubic Spline Feed Forward Neural Network (NCS - FFNN) is compared with RBF, CART and MLP. The rest of this paper is organized as follows: in Section II, reviews some of the related work available in literature, Section III details the materials and methods used in this investigation, Section IV discusses the results and Section V concludes the paper.

[1]  Zheru Chi,et al.  Combined thresholding and neural network approach for vein pattern extraction from leaf images , 2006 .

[2]  De-shuang Huang,et al.  Computer-Aided Plant Species Identification (CAPSI) Based on Leaf Shape Matching Technique , 2006 .

[3]  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.

[4]  Ying-Chun Guo.  Knowledge-Enabled Short-Term Load Forecasting Based on Pattern-Base Using Classification & Regression Tree and Support Vector Regression , 2009, 2009 Fifth International Conference on Natural Computation.

[5]  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).

[6]  A. Samal,et al.  Plant species identification using Elliptic Fourier leaf shape analysis , 2006 .

[7]  Fernando C. Monteiro.  A Survey : Image Segmentation Techniques 89 International Journal of Future Computer and Communication , 2013 .

[8]  Francesco Piazza,et al.  Learning and Approximation Capabilities of Adaptive Spline Activation Function Neural Networks , 1998, Neural Networks.

[9]  Seishi Ninomiya,et al.  Discrimination of soybean leaflet shape by neural networks with image input , 2000 .

[10]  Sadegh Abbasi,et al.  Matching shapes with self-intersections:application to leaf classification , 2004, IEEE Transactions on Image Processing.

[11]  Changle Zhou,et al.  Feature Extraction and XML Representation of Plant Leaf for Image Retrieval , 2006, APWeb Workshops.

[12]  Gurpreet Kaur,et al.  Classification of Biological Species Based on Leaf Architecture , 2012 .

[13]  Reinhard Klein,et al.  Shape retrieval using 3D Zernike descriptors , 2004, Comput. Aided Des..

[14]  Chia-Ling Lee,et al.  Classification of leaf images , 2006, Int. J. Imaging Syst. Technol..

[15]  Tosiyasu L. Kunii,et al.  Recognizing plant species by leaf shapes-a case study of the Acer family , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).