Classification of Oil Palm Fruit Ripeness Using Artificial Neural Network

Hong, Tan; Hashim, Fazida Hanim; Raj, Thinal; Huddin, Aqilah Baseri

doi:10.1109/i2cacis52118.2021.9495857

Cited by 7 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since color is an important indicator used by agriculturists to determine the ripeness of OPFFB, it is critical to determine the right ripeness color. Oil palm fruit contains beta-carotene (Hong et al, 2021), which can become fluorescent when stimulated by the appropriate UV LED spectrum. The RGB color system is based on the combination of red, green and blue light with additive combinations.…”

Section: Experimental Setup and Designmentioning

confidence: 99%

“…A portable, multi-band system with active optical sensors was developed to detect OPFFB ripeness with four spectral bands (Saeed et al, 2012). The OPFFB spectral reflectance was investigated using two statistical analyses based on a forward-stepwise method and a combination of principal component analysis and a multilayer perceptron neural network, producing a classification accuracy of greater than 80% (Makky and Soni, 2014), while Hong et al (2021) also included Raman spectral features and achieved 95.48% accuracy. An artificial neural network based on principal component analysis was combined with color vision to improve the classification accuracy by 1.66% (Fadilah et al, 2012), while Suharjito et al (2021) included this approach in an Android application on a mobile device with 81-89% accuracy.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Real-time oil palm ripeness classification of fresh fruit bunches using fluorescence technology

2023

ANRES

View full text Add to dashboard Cite

Importance of the work:The precise and non-destructive grading of oil palm fresh fruit bunches (OPFFBs) is crucial in determining the profit for farmers selling the product to factories. Objectives: To investigate the accuracy of fluorescence technology combined with image analysis technology in categorizing OPFFB ripeness. Materials & Methods: A combination of eight ultraviolet light-emitting diodes (UV LEDs) were used in the wavelength range 395-400 nm along with image processing techniques to classify oil palm ripening in the Tenera variety (80 ripe and 20 under-ripe bunches). Afterward, the UV LEDs stimulated the OPFFBs in darkness, as indicated by fluorescence in the image processing. To validate the results, the fluorescence visibility results were compared with the results manually provided by five experts and with crude palm oil percentages obtained from 600 fruits samples extracted using an organic solvent (six fruits were sampled from each bunch). Results: The equipment yielded results that were deemed 100% accurate, as confirmed by experts and the crude palm oil percentages obtained from laboratory analysis. Main finding:The research equipment demonstrated enhanced fluorescence visibility for assessing the maturity of Tenera variety oil palm fresh fruit bunches. This technique may have potential applications in assessing the maturity of other oil palm varieties, as well as different types of fruit.

show abstract

Section: Experimental Setup and Designmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Real-time oil palm ripeness classification of fresh fruit bunches using fluorescence technology

2023

ANRES

View full text Add to dashboard Cite

show abstract

“…Advanced color-based machine vision was able to categorize distinct fruits into correct groups with an accuracy of 90% [27,28]. Further studies have been conducted with high accuracy values, including 95.48% [29], 97.9% [30] and 98.70% [31].…”

Section: G 2 Fruit Color and Ripeningmentioning

confidence: 99%

The Intended Blessed Tree in the Quran - Is it Olive Tree or Palm Oil Tree?

Koutb

2023

SQU Journal for Science

View full text Add to dashboard Cite

This article aims to provide an alternative scientific interpretation for verse 35 in Surat An-Nur. This verse addresses the very famous simile in the Quran which describes the light of Allah. In this verse Allah mentioned that ꞌAllah (is the) light (of) the heavens and the earth. (The) example (of) His Light (is) like a niche in it (is) a lamp; the lamp (is) in a glass, the glass as if it were a star brilliant (which) is lit from a tree blessed - an olive, not (of the) east and not (of the) west, would almost its oil glow, even if not touched it fireꞌ [1]Despite all the most commentators who have addressed this verse singled the olive tree as the blessed tree, the intended tree still has one characteristic that is enigmatic. Regarding this characteristic ꞌnot east and not westꞌ, all previous interpretations directed this characteristic to the compass directions. But they did not give any logical and acceptable justification. Dealing with this verse with another linguistic concept, particularly with three words in the verse ꞌzaytūnatin, sharqiyyatin, and gharbiyyatinꞌ can change the story of the intended blessed tree. The first word in the Arabic language could be considered as an adjective for exaggeration meaning a high oil producer rather than the genus olive. More interestingly, this word has been mentioned as an indefinite noun without ꞌAlꞌ which makes the noun definite when it is used as a prefix; therefore, in this case, it is not specific to olive but it could refer to any tree producing high amount of oil. The second word ꞌsharqiyyatinꞌ comes from the verb ꞌsharekꞌ, which in Arabic means, particularly for dates, that they became reddish in color as a sign of maturity. The third word ꞌgharbiyyatinꞌ derives its meaning from the verb ꞌgharbꞌ which means it became black. When these new meanings are applied to the verse, the first word will now mean any tree with high oil production. The other two words, will mean reddish and black colors of the fruit not the east and west directions. These two characteristics could be considered to be distinguishable features for palm oil tree not for olive trees. In this paper two additional evidences supporting this idea have been addressed. Therefore, the palm oil tree, particularly the subspecies nigrescens could be a potential candidate for the blessed tree in the Quran. [1] ꞌٱللَّهُ نُورُ ٱلسَّمَـٰوَ ٰتِ وَٱلۡأَرۡضِۚ مَثَلُ نُورِهِۦ كَمِشۡكَوٰةࣲ فِیهَا مِصۡبَاحٌۖ ٱلۡمِصۡبَاحُ فِی زُجَاجَةٍۖ ٱلزُّجَاجَةُ كَأَنَّهَا كَوۡكَبࣱ دُرِّیࣱّ یُوقَدُ مِن شَجَرَةࣲ مُّبَـٰرَكَةࣲ زَیۡتُونَةࣲ لَّا شَرۡقِیَّةࣲ وَلَا غَرۡبِیَّةࣲ یَكَادُ زَیۡتُهَا یُضِیۤءُ وَلَوۡ لَمۡ تَمۡسَسۡهُ نَارࣱࣱۚꞌ (النور– 35)

show abstract

“…Due to the high demand in palm oil industry, Malaysian Palm Oil Board (MPOB) needs to regulate the fresh fruit bunch (FFB) quality in accordance with the ripeness of fruit, to ensure that the produced palm oil products are in high quality [2]. To increase the production of good quality crude palm oil for food industry and cosmetic industry, one of the challenges is to harvest the oil palm fresh fruit bunches at the optimum ripen stage [3,4].…”

Section: Introductionmentioning

confidence: 99%

Novel Feature Extraction for Oil Palm Bunches Classification

Hui Hui Wang,

Yin Chai Wang,

Bui Lin Wee

et al. 2023

ARASET

View full text Add to dashboard Cite

This paper presents research on an image processing approach for oil palm fruit brunches classification on automating the process of classifying palm fruit brunches based on their visual characteristics, which can have applications in the agriculture and palm oil industry. The research aims to classify the bunches into four categories which are unripe, under ripe, ripe and over ripe. Additionally, this approach can reduce the manual labour involved in palm oil grading and provide a more objective and consistent method for grading the oil. The proposed approach consists of the process of image acquisition, image pre-processing, colour processing, image segmentation and classification. The ripeness of the oil palm fruit bunches is determined based on the percentage of ripeness areas masked on the fruit surface. The proposed algorithms successfully classified the palm oil bunches and improved the accuracy of grading palm oil, achieving 85% accuracy from the experiment results.

show abstract

Classification of Oil Palm Fruit Ripeness Using Artificial Neural Network

Cited by 7 publications

References 12 publications

Real-time oil palm ripeness classification of fresh fruit bunches using fluorescence technology

Real-time oil palm ripeness classification of fresh fruit bunches using fluorescence technology

The Intended Blessed Tree in the Quran - Is it Olive Tree or Palm Oil Tree?

Novel Feature Extraction for Oil Palm Bunches Classification

Contact Info

Product

Resources

About