Digital image processing methods for estimating leaf area of cucumber plants

Increasingly <span>emerging technologies in agriculture such as computer vision, artificial intelligence technology, not only make it possible to increase production. To minimize the negative impact on climate and environment but also conserve resources. A key task of these is monitor growth plants online with a high accuracy rate non-destructive manners. It known that leaf area (LA) one most important indexes plant monitoring system. Unfortunately, estimate LA natural outdoor scenes (the presence occlusion or overlap area) easy still remains big challenge eco-physiological studies. In this paper, two accurate approaches for estimating were proposed top-view side-view images, respectively. The successfully extract skeleton cucumber red, green, blue (RGB) images precision. results validated by comparing manual measurements. experimental our algorithms achieve 97.64% segmentation, relative error estimation varies from 3.76% 13.00%, which could meet requirements </span>systems.