Classification of oil palm fresh fruit maturity based on carotene content from Raman spectra

Abstract

The oil yield, measured in oil extraction rate per hectare in the palm oil industry, is directly affected by the ripening levels of the oil palm fresh fruit bunches at the point of harvesting. A rapid, non-invasive and reliable method in assessing the maturity level of oil palm harvests will enable harvesting at an optimum time to increase oil yield. This study shows the potential of using Raman spectroscopy to assess the ripeness level of oil palm fruitlets. By characterizing the carotene components as useful ripeness features, an automated ripeness classification model has been created using machine learning. A total of 46 oil palm fruit spectra consisting of 3 ripeness categories; under ripe, ripe, and over ripe, were analyzed in this work. The extracted features were tested with 19 classification techniques to classify the oil palm fruits into the three ripeness categories. The Raman peak averaging at 1515 cm−1 is shown to be a significant molecular fingerprint for carotene levels, which can serve as a ripeness indicator in oil palm fruits. Further signal analysis on the Raman peak reveals 4 significant sub bands found to be lycopene (ν1a), β-carotene (ν1b), lutein (ν1c) and neoxanthin (ν1d) which originate from the C=C stretching vibration of carotenoid molecules found in the peel of the oil palm fruit. The fine KNN classifier is found to provide the highest overall accuracy of 100%. The classifier employs 6 features: peak intensities of bands ν1a to ν1d and peak positions of bands ν1c and ν1d as predictors. In conclusion, the Raman spectroscopy method has the potential to provide an accurate and effective way in determining the ripeness of oil palm fresh fruits.

Oil Palm Fruits Ripeness Classification Based on the Characteristics of Protein, Lipid, Carotene, and Guanine/Cytosine from the Raman Spectra

“…Hyperspectral images however are known to have limitations of being heavy in storage and high in computational cost which could be a limitation for a rapid and portable solution in oil palm plantations. The study by Raj et al in 2021 achieved higher accuracy using Raman spectroscopy and KNN due to the extraction of features between the 1495 cm −1 to 1535 cm −1 band which consisted of stronger molecular assignments of beta carotene, lutein, lycopene, and neoxanthin [ 12 ].…”

“…After pre-processing, deconvolution was applied to decompose the overlapping peaks and extract information from the hidden peaks [ 12 , 14 ]. All rescaled Raman spectra were resolved into separate component bands in this stage.…”

“…However, due to the changes in light intensity throughout the day, images captured at different times may cause some discrepancies when determining the ripeness of oil palm fruits using the computer vision technique [ 10 ]. To overcome these problems, this study extends our previous work using Raman spectroscopy for oil palm fruit ripeness classification, due to its high potential in analyzing the biochemical content of a fruit sans light dependency [ 11 , 12 ].…”

“…However, some peaks could be hidden and appear as one peak on the Raman spectrum [ 14 ]. Using careful signal processing and feature extraction methods, these molecular assignments could be identified and assigned as significant characteristics of the sample, in this case, oil palm fruits exocarp, and later on, correlated with the ripeness level of the fruit samples [ 12 , 15 ]. This is due to the fact that the Raman spectra can be used as a chemical fingerprint for different organic compounds in which each peak of the Raman spectrum corresponds to an active vibration of the molecule in a particular Raman band [ 16 ].…”

“…The extracted features are fed into an ANN model to automatically classify the fruits into under-ripe, ripe, and over-ripe. This article revisits the methods devised for feature extraction from the Raman spectra to identify important organic compounds throughout the ripening process by Raj et al [ 12 ]. From this study, new characteristics of organic compounds from the Raman spectra were extracted, including chlorophyll-a, proteins (from amide III band, β-sheet), lipids, guanine/cytosine, tryptophan, and carotenes.…”