Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

A Novel Method of Object Identification and Leaf Area Calculation in Multi-leaf Image

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  2007 ASAE Annual Meeting  073047.(doi:10.13031/2013.23173)
Authors:   Zhen LI, Tian-sheng HONG, Wei-bin WU, Min-juan LIU
Keywords:   flat scanner, target identification, leaf area, image processing, region marking

Both advantages and disadvantages of CCD camera and flat scanner used as image taking equipment for leaf area measurement using digital image processing methods have been analyzed in this paper. For the main limitation of currently used leaf area measuring methods is that only one piece of leaf can be measured separately, a novel algorithm based on MATLAB and flat scanner has been figured out to measure leaf areas synchronously in a multi-leaf scanned digital image. Results of experiments were: the accuracy of leaf identification when no superposition between leaves was 100%, the relative error of calculated leaf area between using this method and in weighing method was 2.43%, the determination coefficient R2 was 0.9996. Results indicated that this method can be used in the object identification and leaf area calculation in a multi-leaf scanned image.

(Download PDF)    (Export to EndNotes)