Classification of maturity levels of oil palm fresh fruit bunches using LED-based multispectral imaging methods and principal component analysis

Mohammad Fisal Rabin, Minarni Shiddiq, Rahmondia Nanda Setiadi, Ihsan Okta Harmailil, Ramdani Ramdani, Dedi Permana

Abstract


Multispectral imaging (MSI) is one of the optical methods used for the classification of fruits and vegetables based on ripeness levels. MSI is simpler than hyperspectral imaging due to fewer wavelength bands used hence less processing time. In this study, MSI is used to classify the ripeness of oil palm fresh fruit bunch (FFB). The MSI system consists of three main components, namely a VIS-NIR camera, a camera lens, an LED array, and a current control unit. The use of the LED array as a light source in the MSI system aims to minimize the use of bandwidth filters. The LEDs used are arranged in a circular pattern with 8 wavelengths, namely 680, 700, 750, 780, 810, 850, 880, and 900 nm. FFB samples were recorded using the MSI system and then processed using Python language to obtain relative reflectance intensity values. The purposes of this research are to analyze the relationship between relative reflectance intensity and wavelength and to classify the ripeness level of oil palm FFB using principal component analysis (PCA). We used two categories of ripeness, unripe and ripe FFBs.The results of the PCA analysis showed that the classification carried out was able to group into two levels of ripenesses with a total variant percentage value for PC1 and PC2 of 90.95%.

Keywords


Multispectral imaging; oil palm fresh fruit bunches; PCA analisys; ripeness levels

Full Text:

PDF (INDONESIAN)

References


1. Abasi, S., Minaei, S., Jamshidi, B., & Fathi, D. (2018). Dedicated non-destructive devices for food quality measurement: A review. Trends in Food Science & Technology, 78, 197–205.

2. Tan, J. Y., Ker, P. J., Lau, K. Y., Hannan, M. A., & Tang, S. G. H. (2019). Applications of photonics in agriculture sector: A review. Molecules, 24(10), 2025.

3. El-Rahman, S. A. (2016). Big data analysis: hyperspectral image processing for agriculture applications. International Journal of Computing and Digital Systems, 5(04).

4. Dong, X., Jakobi, M., Wang, S., Köhler, M. H., Zhang, X., & Koch, A. W. (2019). A review of hyperspectral imaging for nanoscale materials research. Applied Spectroscopy Reviews, 54(4), 285–305.

5. Fu, X. & Chen, J. (2019). A review of hyperspectral imaging for chicken meat safety and quality evaluation: application, hardware, and software. Comprehensive Reviews in Food Science and Food Safety, 18(2), 535–547.

6. ElMasry, G., Mandour, N., Al-Rejaie, S., Belin, E., & Rousseau, D. (2019). Recent applications of multispectral imaging in seed phenotyping and quality monitoring—An overview. Sensors, 19(5), 1090.

7. Sendin, K., Manley, M., & Williams, P. J. (2018). Classification of white maize defects with multispectral imaging. Food Chemistry, 243, 311–318.

8. Amigo, J. M. & Grassi, S. (2019). Configuration of hyperspectral and multispectral imaging systems. Data Handling in Science and Technology, 32, 17 – 34.

9. Khan, Z. (2014). Hyperspectral imaging and analysis for sparse reconstruction and recognition. arXiv preprint arXiv:1407.7686.

10. MMohd. Hudzari Razali, M. H. R., Abdul Ssomad, M. A. H., & Syazili Roslan, S. R. (2012). A review on crop plant production and ripeness forecasting. Int. J Agric. Crop Sci., 4(2).

11. Bensaeed, O. M., Shariff, A. M., Mahmud, A. B., Shafri, H., & Alfatni, M. (2014). Oil palm fruit grading using a hyperspectral device and machine learning algorithm. IOP Conference Series: Earth and Environmental Science, 20(1), 012017.

12. Yap, X. Y., Chia, K. S., Rahman, H. A., & Teh, V. (2019). A non-destructive oil palm fruit freshness prediction system with artificial neural network. International Journal of Integrated Engineering, 11(8), 159–163.

13. Setiawan, A. W., & Prasetya, O. E. (2020, February). Palm oil fresh fruit bunch grading system using multispectral image analysis in HSV. 2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT), 85–88.

14. Liu, C., Liu, W., Lu, X., Ma, F., Chen, W., Yang, J., & Zheng, L. (2014). Application of multispectral imaging to determine quality attributes and ripeness stage in strawberry fruit. PloS One, 9(2), e87818.

15. Ningsih, S. A., Shiddiq, M., Arief, D. S., & Husein, I. R. (2020). Pengunaan pencitraan multispektral pada panjang gelombang 520 nm dan 800 nm untuk mengevaluasi tingkat kematangan TBS kelapa sawit. Komunikasi Fisika Indonesia, 17(3), 144–149.

16. Junkwon, P., Takigawa, T., Okamoto, H., Hasegawa, H., Koike, M., Sakai, K., ... & Bahalayodhin, B. (2009). Potential application of color and hyperspectral images for estimation of weight and ripeness of oil palm (Elaeis guineensis Jacq. var. tenera). Agricultural Information Research, 18(2), 72–81.




DOI: http://dx.doi.org/10.31258/jkfi.21.1.91-98

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Indexing by:

  

 

Image