|
Vol.12, No.3, August 2023. ISSN: 2217-8309 eISSN: 2217-8333
TEM Journal
TECHNOLOGY, EDUCATION, MANAGEMENT, INFORMATICS Association for Information Communication Technology Education and Science |
Non-Destructive Determination of Plant Pigments Based on Mobile Phone Data
Miroslav Vasilev, Vanya Stoykova, Petya Veleva, Zlatin Zlatev
© 2023 Petya Veleva, published by UIKTEN. This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. (CC BY-NC-ND 4.0)
Citation Information: TEM Journal. Volume 12, Issue 3, Pages 1430-1442, ISSN 2217-8309, DOI: 10.18421/TEM123-23, August 2023.
Received: 24 April 2023. Revised: 06 June 2023.
Abstract:
This paper proposes methods and tools for determining plant pigments using data from a mobile phone video sensor. A disadvantage of the known studies in this field is that they are mainly aimed at determining the chlorophyll content. There are few studies related to the determination of pigments such as carotenoids, flavonoids, and betalains, which are also important in terms of determining the condition of plants in their cultivation. Cucumbers were chosen because the long periods of drought in Bulgaria, lead to losses in cultivating these plants. Vectors containing colour and spectral indices were used. These features are obtained through a video sensor on a mobile phone. The kernel method variant of principal components reduces them. Feature vectors are selected using factor analysis, correspondence analysis, and the correlation method. Predictive models have been developed to determine plant pigments. With high accuracy (over 90%), the pigments xanthophyll and chlorophyll A can be predicted.
Keywords –Visual analysis, spectral data, mobile phone video sensor, leaves coloration, carotenoids, chlorophyll content. |
|
----------------------------------------------------------------------------------------------------------- ----------------------------------------------------------------------------------------------------------- |