A GA_FFNN algorithm applied for classification in diseased plant leaf system

In order to solve the problems of conventional neural network when it is applied to the diseased plant leaf system such as making itself for better classification, Genetic algorithm-based feed forward neural network (GA_FFNN) hybrid technique is proposed. Besides, Particle swarm optimization (PSO)-based segmented hybrid features were used for the analysis of classification of diseased leaf and its severity. The main contribution of this paper incorporates Genetic weight optimization-based neural network systems of diseased plant leaf classification for better classification accuracy. Various diseased plant leaves such as bitter gourd (Brown Leaf Spot), beans (Pest leaf minor), chilly (Pest), Cotton (Mineral Deficiency), pigeon pea (Blight Leaf minor) and tomato (Leaf spot) were used. In the proposed work, attributes are combined as a single vector for hybrid features. Five attributes, namely contrast, correlation, energy, homogeneity and area of the leaf were used as features. Initially, the features were extracted from the segmented image after preprocessing. Genetic-based Feed Forward Neural network architecture is constructed for the classification of diseased plant leaf. The weight of the neural network is updated by Genetic algorithm for specified iterations. Finally, the performance is analyzed in different classes (class 2, class 3 and class 6) of diseased plant leaves using classification accuracy.

[1]  Milan Sonka,et al.  Computer Vision Approaches to Medical Image Analysis, Second International ECCV Workshop, CVAMIA 2006, Graz, Austria, May 12, 2006 Revised Papers , 2006, CVAMIA.

[2]  M. Hemalatha,et al.  Identification of Cotton Diseases Based on Cross Information Gain_Deep Forward Neural Network Classifier with PSO Feature Selection , 2013 .

[3]  Milan Sonka,et al.  Proceedings of the Second ECCV international conference on Computer Vision Approaches to Medical Image Analysis , 2006 .

[4]  Kurt Hornik,et al.  FEED FORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS , 1989 .

[5]  Brian C. Lovell,et al.  Detecting kangaroos in the wild: the first step towards automated animal surveillance , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[6]  K. Muthukannan,et al.  A PSO MODEL FOR DISEASE PATTERN DETECTION ON LEAF SURFACES , 2015 .

[7]  Malik Braik,et al.  Fast and Accurate Detection and Classification of Plant Diseases , 2011 .

[8]  H. Hashim,et al.  Classification of Rubber Tree Leaf Diseases Using Multilayer Perceptron Neural Network , 2007, 2007 5th Student Conference on Research and Development.

[9]  Brian C. Lovell,et al.  What is the best way for extracting meaningful attributes from pictures? , 2016, Pattern Recognit..

[10]  Su Hang,et al.  A Research of Maize Disease Image Recognition of Corn Based on BP Networks , 2011, 2011 Third International Conference on Measuring Technology and Mechatronics Automation.

[11]  Qiuwen Zhang,et al.  Using Genetic Algorithm to Optimize Artificial Neural Network: A Case Study on Earthquake Prediction , 2008, 2008 Second International Conference on Genetic and Evolutionary Computing.

[12]  Hadzli Hashim,et al.  Classification of watermelon leaf diseases using neural network analysis , 2013, 2013 IEEE Business Engineering and Industrial Applications Colloquium (BEIAC).

[13]  David E. Goldberg,et al.  A niched Pareto genetic algorithm for multiobjective optimization , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[14]  Alex Fraser,et al.  Simulation of Genetic Systems by Automatic Digital Computers I. Introduction , 1957 .

[15]  Feiping Nie,et al.  Unsupervised automatic attribute discovery method via multi-graph clustering , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[16]  Cheng-Lung Huang,et al.  A GA-based feature selection and parameters optimizationfor support vector machines , 2006, Expert Syst. Appl..

[17]  Hans-Paul Schwefel,et al.  Evolution and optimum seeking , 1995, Sixth-generation computer technology series.

[18]  A. K. Misra,et al.  Detection of plant leaf diseases using image segmentation and soft computing techniques , 2017 .