Jia Heming

Edge detection of plant roots image based on genetic BP neural network

In order to realize the contour extraction and edge detection of the images of the roots of slope protection plant, a hybrid algorithm which combined with genetic algorithm and back-propagation algorithm is presented to train a feed-forward artificial neural network (BPN). The built characteristics vectors to describe the edge are used as input signal of a three-layer feed-forward neural network. The built edge characteristics vectors are robust against noise and the genuine information of edge can be extracted effectively in the process of network training. The experimental results illustrate that the designed neural network achieves excellent performance. It is noise robust and accurate in true edge positioning. The contour extracted by this method is closer to the practical contour, therefore it is more beneficial to the monitoring of root morphology of vegetation for slope protection research. And a dynamic parameter of plant roots morphology is proposed as the application of roots edge detection.