Research on the Edge Detection Method of the Rice Leaves Image Based on Phase Consistency under the Complex Environment

In order to realize the effective segmentation of the rice leaf lesion, how to remove background interference and isolating single rice leaf from collected images is the basis of disease classification and recognition. The main body information of the images collected under the simple background of lighting box and field contains only single leaf, so we can use the normal way to detect the blade edge. However, because of the outside interference under the background of field, parameters can't be quantified and the treatment effect of using ordinary edge detection methods is bad. This paper takes advantage of the characteristics that phase consistency test methods that protect them from the image contrast and brightness change and have a strong ability to resist noise to realize complete extraction of the main blade edge in the rice leaf image under the complex background.