Recognition system of leaf images based on neuronal network

Abstract

In forest variety registration, visual traits of the plants appearance are widely used to discern different tree species. The new recognition system of leaf image strategy which based on neural network established to administrate a hierarchical list of leaf images, some sorts of edge detection can be performed to identify the individual tokens of every image and the frame of the leaf can be got to differentiate the tree species. An approach based on back-propagation neuronal network is proposed and the programming language for the implementation is also given by using Java. The numerical simulations results have shown that the proposed leaf strategy is effective and feasible.

Keywords

Neuronal network / Edge detection / Leaf images / Pattern recognition

References

[1] Camlin M.S., McMichael A.C. New methodology for the measurement of leaf color in ryegrass (Loliumspp) [J]. Plant Varieties and Seeds, 1994, 7: 37-49.

[2] Cawkell A. Managing image databases [J]. Image Processing, 1994, 6: 36-39.

[3] Draper S., Keefe P.D. An automated machine vision system for the morphometry of new cultivars and plant gene bank accessions [J]. Plant Varieties and Seeds, 1988, 1: 1-11.

[4] Maksymowych Analysis of leaf development [M], 1973 Cambridge: Cambridge University Press

[5] Schmundt D., Schurr U. Plant leaf growth studied by image sequence analysis [C] Computer Vision and Applications Volume 2 Signal Processing and Pattern Recognition, 1999 New York, Boston, London, Sydney, Tokyo, Toronto: Academic Press

[6] Schurr U., Heckenberger U., Herdel K., Walter A., Feil R. Leaf development in Ricinus communis during drought stress-dynamics of growth processes, of cellular structure and of sink source-transition [J]. Journal of Experimental Botany, 2000, 51(350): 1515-1529.

[7] Haykin S. Neural networks a comprehensive foundation [M], 2000 Second Edition Beijing: China Machine Press 112-123.

[8] Spies, H., Scharr, H. and Schurr, U. 2001. Root growth analysis in physiological coordinates [C]. In: ICIAP’01, Palermo, Italy.