A New Approach for Measuring Leaf Projected Area for Potted Plant Based on Computer Vision
Leaves are the main organs for plant photosynthesis and transpiration, and thus accurate and rapid measurements of their surface area are of great significance in plant growth studies. A novel method was developed to utilize computer vision to determine the leaf projected area for potted plants using a reference object. During leaf extraction, the excess green vegetation index and the Otsu algorithm were used for image binarization. Blob analysis was then performed to eliminate noise and extract leaf images. After grey level transform and obtaining the binary image, the Sobel operator and Hough transform were utilized to detect pot’s external boundary. The image including the extracted leaves and the detected reference borders were then processed using a Geometric correction to improve the measurement accuracy, and based on this, the leaf projected area was calculated. Results of the experimental image showed that this newly proposed method proved is effective and can continuously measure the plant’s leaf area for non-destructive monitoring.
KeywordsImage segmentation Edge detection Hough transform Projected area Image correction
This work was supported by Grant No. 2014BAD05B05 from the Ministry of Science and technology of China and the fundamental research funds for the central universities of China.
- 8.Xia, Y.W., Xu, D.Y., Du, J.S.: On-line measurement of tobacco leaf area based on machine vision. Trans. Chin. Soc. Agric. Mach. 43(10), 167–173 (2012)Google Scholar
- 10.Kataoka, T., Kaneko, T., Okamoto, H., Hata, S.I.: Crop growth estimation system using machine vision. In: Proceedings of the IEEE/ASME International Conference on Advanced Intelligent Mechatronics, pp. 1079–1083 (2003)Google Scholar