Improvement in purity of healthy tomato seeds using an image-based one-class classification method

Authors: YASMIN, JANNAT - Chungnam National University; LOHUMI, SANTOSH - Chungnam National University; AHMED, MOHAMMED - Chungnam National University; KANDPAL, LALIT - Chungnam National University; FAQEERZADA, MOHAMMAD - Chungnam National University; Kim, Moon; CHO, BYOUNG-KWAN - Chungnam National University

Submitted to: Sensors
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 5/6/2020
Publication Date: 5/8/2020
Citation: Yasmin, J., Lohumi, S., Ahmed, M.R., Kandpal, L.M., Faqeerzada, M.A., Kim, M.S., Cho, B. 2020. Improvement in purity of healthy tomato seeds using an image-based one-class classification method. Sensors. 20(9):2690. https://doi.org/10.3390/s20092690.
DOI: https://doi.org/10.3390/s20092690

Interpretive Summary: Tomato accounts for approximately 15% of global vegetable crop production. Detection and removal of unhealthy seeds and foreign inert objects from the seed supply prior to planting is desirable to reduce the economic impact of non-germinating seeds and unhealthy seedlings. This study investigated the use of a color-based machine vision system to identify low-germination black-spotted tomato seeds and inert foreign materials among healthy tomato seeds. The results showed that a one-class classification method could effectively identify healthy seeds with an accuracy exceeding 97%. The study provides insightful information to the produce industry on the use of color-based rapid machine vision for quality inspection of tomato seeds that could help produce growers improve the health and yields of tomato crops.

Technical Abstract: The feasibility of a color machine vision technique with a one-class classification method was investigated for the quality assessment of tomato seeds. The health of seeds is an important quality factor that affects their germination rate, which may be affected by seed contamination. Hence, segregation of healthy seeds from diseased and infected seeds, along with foreign materials and broken seeds, is important to improve the final yield. In this study, a color-based machine vision system was used for image acquisition and a one-class classification method was used to identify healthy seeds after extracting features of the sample images. A significant difference was observed between the features of healthy and infected seeds, and foreign materials, implying a certain threshold. The results indicated that tomato seeds can be classified with an accuracy exceeding 97%. The infected tomato seeds exhibited a lower germination rate (<10%) compared to healthy seeds, as confirmed by a germination test. Thus, identification through image analysis and rapid measurement were observed as useful in discriminating between the quality of tomato seeds in real-time.