Computer vision technology determines optimal physical parameters for sorting JinDan 73 maize seeds

文献类型： 外文期刊

第一作者： Wen, K. X.

作者： Wen, K. X.;Sun, B. Q.;Wang, J. H.;Sun, Q.;Xie, Z. M.;Yang, L. M.;Sun, B. Q.

作者机构：

期刊名称：SEED SCIENCE AND TECHNOLOGY （ 影响因子：0.905； 五年影响因子：0.996 ）

ISSN：

年卷期：

页码：

收录情况： SCI

摘要： Seed sorting is one of the most important methods used to improve seed quality, and computer vision technology has become widely used to select seeds. Here, images of the embryo and endosperm sides of JinDan 73 maize seeds were acquired with a flat-bed scanner and saved as PNG files. After identification, the seeds were placed in a vertical plate germinator. Seven days later, the fresh and dry weights of the seedlings were assessed and used as indicators of seed vigour. Correlation analyses showed that the correlation coefficients between the vigour parameters and the physical parameters of length, width and projected area were high (0.85, 0.68 and 0.90, respectively). The coefficients of variance for length, width and projected area were approximately 13, 13 and 19%, respectively. Scatter plot analyses of the three physical parameters with vigour confirmed that seeds with measurements greater than 5.0 mm wide or 8.0 mm long or with a projected area greater than 40 mm(2) showed the highest vigour; their average fresh weights increased by 2.75, 3.27 and 4.71%, respectively, compared with those values obtained for all seeds before sorting. Similar results were obtained in subsequent verification tests when seeds were selected based on these physical traits and parameters.

分类号： S5

  • 相关文献
作者其他论文 更多>>

微信小程序