{GA}-Based Feed-Forward Neural Network For Image Classification: Application For the Grains of Pollen

• Autorzy: Khorissi N. , Mellit A. , Guessoum A. , Mesaouer A.
• Języki publikacji: EN

Abstrakty

EN

Palynological data are used in wide range application, the pattern recognition of pollen grains is very important in the determination of the original floral honey, and the prediction of the allergy, which touches lot of people. Due to the high computing time needed for classification of the pollen grains and complex architecture of the neural networks, the genetic algorithm is used in order to find the optimal architecture of the Multilayer perceptron (number of hidden layers and the number of neurons within each hidden layer). In this paper, a methodology for pollen grain classification based on the using of the MLP optimized by genetic algorithm (GA) called MLP-GA is described. A database of pollen images has been used in this work. Firstly, for each image we have calculated some morphological and geometric features. Subsequently, the MLP-GA network has been used for classification of the image pollen. The best classification performance is achieved by using an experimental data base of grains pollen. The classification rate is 90% which is very promising, and by comparing the hybrid MLP-GA with others ANN architectures, we can note that the MLP-GA is faster (the convergence time is 500 iterations).

Słowa kluczowe

EN

neural networks; image classification; palynological data

PL

sieci neuronowe; klasyfikacja obrazów

• Wydawca: Wydawnictwo Politechniki Łódzkiej
• Czasopismo: Journal of Applied Computer Science
• Rocznik: 2009
• Tom: Vol. 17, nr 2
• Strony: 83--96
• Opis fizyczny: Bibliogr. 18 poz.

Twórcy

autor

Khorissi N.

autor

Mellit A.

autor

Guessoum A.

autor

Mesaouer A.

• 1Department of Electronics, LATSI, Blida University Soumaa, B.O. Box. 272, Blida, Algeria

Bibliografia

• [1] Corbi, A., Corte, C., Bousquet, J., Basomba, A. A., Garcia-Selles C. J., Amato, G. D. and Carreira, J., Allerginic cross reactivity pollens of urticaceae. Int. Arch Allergy App. Vol. 77, (1985), pp. 377-383.
• [2] Rodriguez-Damian, M., Cenadas, E. and Sa-Otero, P., Pollen classification using brithness-based and shape-based descriptors. Proceedings of the 17 International Conference on Pattern Recognition IEEE 2004.
• [3] Ranzato, M., Taylor, P. E., House, J. M., Flagan, R. C., LeCun, Y., Perona, P. Automatic recognition of biological particles in microscopic images. Pattern Recognition Letters Vol. 28, 2007, pp. 31-39.
• [4] France, A. W. G., Duller, G. A. T. and Lamb, H. F., A new approach to Automatic pollen analysis, Quatenary Science Review Vol. 19, 2000, pp. 537-546.
• [5] Rodriguez-Damian, M. Cernadas, E., Formella, A. and Sa-Otero P. Pollen classification using brithness-based and shape-based descriptor, Proc. of the 17th ICPR04 IEEE.
• [6] Rodriguez-Damian, M., Cernadas, E., Formilla A, and Onzalez, A. Automatic identification and classification of pollen of the urticaceae family. Proc. of Acivs 2003, Ghent, Belgium 2003.
• [7] Hodgson, R. M., Holdaway, C. A., Fountain, D. W., Craig. Holdaway A., Zhang, Y., and Flenley, J. R. Progress towards a system for the automatic recognition of pollen using light Microscop images. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis IEEE, 2005, pp. 76-81
• [8] Li, P. and Flenley, J. Pollen texture identification using neural networks. Grana, 1999, pp. 59-64.
• [9] Khorissi, N., Mellit, A., and Guessoum, A., ANN-based wavelet analysis for image classification: Application for pollen grains. INISTA-IEEE International symposium of innovation intelligent system and applications 2007, pp. 215-219.
• [10] Khorissi, N., Mellit, A., Guessoum, A., and Bendekhis, M. Soft-computing technique for image classification: application for pollen grains. the 4th IEEE international summer school on signal processing's and its applications ISSSPA; 2007 Boumerdes, Algeria
• [11] Kesgin, F. and Yaslan, Y. Pollen Classification using RBF Networks. In Computational Intelligence, 2006, Actapress
• [12] Rodriguez-Damian, M., Cernadas Formella, E., Fermandez-Delgado M. and Sa-Otero P, Automatic Detection and classification of grains of pollen based on Shape and Tzecture, IEEE Transactions on systems, Man, and Cybernetices-Paret C Vol. 36, 2006, pp. 531-541.
• [13] Andrew, F.Weller , Anthony, J., Harris, J. AndrewWare, Artificial neural networks as potential classification tools for dinoflagellate cyst images: A case using the self-organizing map clustering algorithm. Review of Palaeobotany and Palynology Vol. 141, 2006, pp. 287-302
• [14] http://www.informatics.bangor.ac.uk/~ian/pdbase/pollen_dbase.html
• [15] Benardos, P. G. and Vosniakos, G. C., Optimizing feed-forward artificial neural network architecture. Engineering Applications of Artificial Intelligence; Vol. 20, 2007, pp. 365-382.
• [16] Roberto, C. P., Evolutionary learning methods for multilayer morphological Perceptron. Master dissertation, Dept. Computer Engineering. Univ. Puerto Rico Mayagüez Campus, 2004.
• [17] Koehn, P. Combining Genetic Algorithms and Neural Networks: The Encoding Problem, Master dissertation, Dept. Elect, Univ. Tennessee, Knoxville 1994.
• [18] Yao, X., and Liu, Y., A New Evolutionary System for Evolving Artificial Neural Networks. IEEE Transactions on Neural Networks, Vol. 8, No. 3, pp. 694-713, 1997.