Title :
Neural network based classification of pollen grains
Author :
Dhawale, V.R. ; Tidke, J.A. ; Dudul, S.V.
Author_Institution :
Dept. of Appl. Electron., Sant Gadge Baba Amravati Univ., Amravati, India
Abstract :
Palynological data are used in a wide range of applications. A new classification algorithm is proposed for pollen grains. With a view to extract features from pollen images, an classifier algorithm is developed which proposes two-dimensional discrete Walsh-Hadamard Transform domain coefficients in addition to image statistics and shape descriptor. The suitability of classifiers based on Multilayer Perceptron (MLP) Neural Network, Generalized Feedforward (GFF) Neural Network, Support Vector Machine (SVM), Radial Basis Functions (RBF) Neural Networks, Recurrent Neural Networks (RNN) and Modular Neural Network (MNN) is explored with the optimization of their respective parameters in view of reduction in time as well as space complexity. Performance of all six classifiers has been compared with respect to MSE, NMSE, and Classification accuracy. The Average Classification Accuracy of MNN comprising of two hidden layers and four parallel MLP neural networks organized in a typical topology is found to be superior (85 % on Cross Validation dataset) amongst all classifiers. Finally, optimal classifier algorithm has been developed on the basis of the best performance. The algorithm suggested could be easily modified to classify more than 10 species. The classifier algorithm will provide an effective alternative to traditional method of pollen image analysis for plant taxonomy and species identification.
Keywords :
Hadamard transforms; biology computing; computational complexity; feature extraction; image classification; multilayer perceptrons; radial basis function networks; recurrent neural nets; support vector machines; GFF neural network; MNN; MSE; NMSE; RBF neural networks; RNN; SVM; classification accuracy; classifier algorithm; feature extraction; generalized feedforward neural network; hidden layers; image statistics; modular neural network; multilayer perceptron neural network; neural network based classification; palynological data; parallel MLP neural networks; parameter optimization; plant taxonomy; pollen grains; pollen image analysis; radial basis function neural networks; recurrent neural networks; shape descriptor; space complexity; species identification; support vector machine; two-dimensional discrete Walsh-Hadamard Transform domain coefficients; Artificial neural networks; Classification algorithms; Feature extraction; Multi-layer neural network; Shape; Training; Classification; Neural Network; Pollen SEM Images; Walsh-Hadamard Transform;
Conference_Titel :
Advances in Computing, Communications and Informatics (ICACCI), 2013 International Conference on
Conference_Location :
Mysore
Print_ISBN :
978-1-4799-2432-5
DOI :
10.1109/ICACCI.2013.6637150