Submitted to: Food Engineering Progress
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 9/26/2012
Publication Date: 10/1/2012
Citation: Ahn, C., Baek, I., Mo, C.Y., Kang, S., Kim, M.S., Cho, B. 2012. Development of non-destructive quality measurement technique for cabbage seed (Brassica campestris L) using hyperspectral reflectance imaging. Food Engineering Progress. 16(3):257-262. Interpretive Summary: Hyperspectral imaging techniques have found uses in a myriad of agricultural applications. In this research, the feasibility of hyperspectral imaging was investigated for evaluation of cabbage seed viability where a rapid nondestructive method of seed lot quality is critical in ensuring uniform and high-yield rate of crop product. To investigate the viable and nonviable seeds, viable seeds were artificially aged and the hyperspectral reflectance imaging technique was used to discriminate the two seed groups. The viable seeds could be discriminated from non-viable seeds with the classification accuracy rate of over 96%. This research and finds are useful to other scientists, and seed production industries.
Technical Abstract: Cabbage (Brassica campestris L) is an important crop for Asian countries especially in Korea, Japan and China. In order to achieve uniform and high-yield rate of cabbage product, the seed lot quality needs to be controlled. Non-destructive evaluation of seed viability is an important technique for investigating seed quality. Hyperspectral imaging technique, which combine the features of imaging and spectrum, has been considered one of the most powerful nondestructive evaluation methods allowing comprehensive analysis of the physical and biochemical characteristics of materials. In this study, the feasibility of hyperspectral reflectance imaging technique was investigated for the evaluation of seed viability. To investigate the viable and non-viable seeds, viable seeds were artificially aged. Hyperspectral reflectance technique was used to discriminate aged cabbage seeds from sound ones. The PLS-DA and simple image threshold methods were applied to investigate the feasibility of distinguishing the aged seeds from the normal seeds. The discrimination accuracy of calibration set was 96.7% and the test was set to 96.9%. The resultant images from the PLS-DA method showed high classification performance in distinguishing the nonviable from the viable seeds, which is an impossible task through the naked eyes and conventional color cameras. Hyperspectral reflectance imaging has good potential for discriminating nonviable seeds from the massive amount of viable cabbage seeds.