American Society of Agricultural and Biological Engineers

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 Sorting Method for Maize Haploid Based on Computer Vision

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

Citation:  Paper number  131590327,  2013 Kansas City, Missouri, July 21 - July 24, 2013. (doi: @2013
Authors:   Zhanyuan Wu, Junxiong Zhang, Peng Song, Wei Li, Yubin Lan
Keywords:   Maize Haploid Computer vision dynamic sorting Color feature

Abstract. A sorting method for maize haploid seeds based on computer vision was proposed in this paper. The maize seeds produced by hybrid induction after importing R-nj, the Navajo genetic marker gene, to the male parent during haploid breeding process can be classified into 3 types according to the different color features on different seed regions. Computer vision technology was used to pick the haploid seeds out. The area to extract the Navajo markers was found in RGB color space, and the Navajo markers were extracted in HSV color space. A quick recognition algorithm of maize haploid seeds had been obtained after the above steps. The result of the dynamic sorting test on the Maize Haploid Sorting System (MHSS) showed that the accuracy rate of recognition for haploid seeds was 95.0%, and that for hybrid deploid seeds was 94.9%. The general steps of maize haploid sorting based on computer vision with MHSS were summarized, and the main factors that affected the accuracy rate were studied. The research and the system may help realize the automatic sorting of maize haploid seeds which is labour-saving and efficient.

(Download PDF)    (Export to EndNotes)