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.
Research on Classification Method of Cotton Seeds on Machine Vision
Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org
Citation: 2018 ASABE Annual International Meeting 1800810.(doi:10.13031/aim.201800810)
Authors: Xiwei Bai, Wei Wang, Hongzhe Jiang, Xuan Chu, Xin Zhao, Bo Wang, Aijun Dong, Haodong Qin
Keywords: Machine vision, image processing, cotton seeds, area array CCD, feature extraction
Abstract. Cotton is an important economic crop in Xinjiang, the broad area located in southwest of China. Improving cotton seeds quality is of great significance to cotton production in Xinjiang, the demanding of high germination rate of cotton seeds is getting , along with the popularization of precision sowing techniques. A method based on machine vision combined with image processing is proposed in this paper. In order to remove crashed and red cotton seeds and then to screen out high quality cotton seeds, the images of differet quality cotton seeds are adapted by area array CCD camera, and the color and morphological characteristics of cotton seeds are extracted by image processing algorithms such as binarization and mean filter. After test analysis, the recognition accuracy of cotton seeds is greater than 87%.
(Download PDF) (Export to EndNotes)