Intelligent Color Vision System for Ripeness Classification of Oil Palm Fresh Fruit Bunch

Fadilah, Norasyikin; Mohamad–Saleh, Junita; Halim, Zaini Abdul; Ibrahim, Haidi; Ali, Syed Salim Syed

doi:10.3390/s121014179

Cited by 83 publications

(52 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This technique has already been successfully used to classify fruits according to their level of ripeness; examples of these successes can be found in the following works: Paulraj et al Paulraj Table 5, the accuracies of the ANN models were significantly influenced by the chosen color space. The ANN model based on the L*a*b* color space obtained a suitable Cape gooseberry fruit classification accuracy (89.85% ± 0.24%), which agrees with the results obtained by Fadilah et al Fadilah et al (2012).…”

Section: Discussionsupporting

confidence: 81%

Using machine learning techniques and different color spaces for the classification of Cape gooseberry (Physalis peruviana L.) fruits according to ripeness level

Castro

Oblitas

De-la-Torre

et al. 2019

Preprint

View full text Add to dashboard Cite

The classification of fresh fruits according to their visual ripeness is typically a subjective and tedious task; consequently, there is growing interest in the use of non-contact techniques to automate this process. Machine learning techniques such as artificial neural networks, support vector machines, decision trees, and K-nearest neighbor algorithms have been successfully applied for classification problems in the literature, particularly for images of fruit. However, the particularities of each classification problem make it difficult, if not impossible, to select a general technique that is applicable to all types of fruit. In this paper, combinations of four machine learning techniques and three color spaces (RGB, HSV, and L*a*b*) were evaluated with regard to their ability to classify Cape gooseberry fruits. To this end, 925 Cape gooseberry fruit samples were collected, and each fruit was manually classified into one of seven different classes according to its level of ripeness. The color values of each fruit image in the three color spaces and their corresponding ripening stages were organized for training and validation following a 5-fold cross-validation strategy in an iterative process repeated 100 times. According to the results, the classification of Cape gooseberry fruits by their ripeness level was sensitive to both the color space and the classification technique used. The models based on the L*a*b* color space and the SVM classifier showed the highest f-measure regardless of the color space, and the principal component analysis combination of color spaces improved the performance of the models at the expense of an increased complexity.

show abstract

Section: Discussionsupporting

confidence: 81%

Using machine learning techniques and different color spaces for the classification of Cape gooseberry (Physalis peruviana L.) fruits according to ripeness level

Castro

Oblitas

De-la-Torre

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…This mesocarp is extracted to produce palm oil and the palm oil kernel is extracted from the kernel seed. To obtain high quantity of oil extracted from mesocorp, it is important to harvest the palm oil at its optimum stage [3][4]. In [5] state about the importance of collecting the palm oil Fresh Fruit Bunch (FFB) at the right phase of maturity to ensure ideal quality and the amount of oil production, thus profitability to the oil palm industry.…”

Section: Introductionmentioning

confidence: 99%

“…The color of the unripe fresh fruit bunch is purplish black, covering more than 90% of the surface of the bunch. Meanwhile, the ripe FFB is red in color [11,4]. The samples of two stages of FFB are shown in Fig.…”

Section: Introductionmentioning

confidence: 99%

“…However, this practice is unreliable due to the possibilities that the loosed fruit might come from different trees. The probability of the dropped fruit took or brought by animals or flood can increase the chance of errors in determining the level of maturity [4]. Therefore, it is important to find a solution to identify the maturity phases before the palm oils falls to the ground and evade losses [6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Palm oil fresh fruit bunch ripeness grading identification using color features

Sabri¹,

Ibrahim²,

Syahlan³

et al. 2018

J. Fundam and Appl Sci.

View full text Add to dashboard Cite

show abstract

“…There are two color regions on the oil palm FFB which are fruit colors, and redundant colors contributed by unnecessary elements such as spikes, empty sockets, palm fibers, and palm fronds. In this research, the captured FFB image is segmented into two different regions of fruit colors and redundant colors by using the existing image segmentation software developed by Fadilah [18][19] [20] in the previous research.…”

Section: Methodsmentioning

confidence: 99%

Artificial Lighting System in Outdoor Image Analysis Application for Oil Palm Fresh Fruit Bunches

2016

6th International Conference on Advances in Engineering Sciences and Applied Mathematics (ICAESAM-2016) Dec. 21-22, 2016 Kuala

View full text Add to dashboard Cite

Abstract-In the application of outdoor image analysis for oil palm fresh fruit bunches (FFB) ripeness classification, color properties of the captured FFB images is constantly altered due to irregular outdoor lighting environment. In this research, an artificial lighting system is developed to control light intensity around the oil palm FFB before the image is captured for ripeness classification. The system consists of a light source which is LED and a light sensor which is LDR. Light sensor will measure the ambient lighting and automatically regulates the intensity of the artificial lighting according to the ambient lighting. The total of 540 images for four categories of ripeness, which are unripe, under-ripe, ripe and overripe are captured and analyzed. Three types of lighting modes, which are Off, Auto and On are used during the images acquisition. Hue values are extracted from every image. At an effective distance, which is 11 inches between the oil palm FFB and the artificial light source, the distinction of maturity level for unripe, under-ripe, ripe and overripe can be improved. By using the Auto lighting mode, the system can save power consumption by 22.5%. Keywords-Fruit ripeness classification, outdoor imageanalysis, artificial lighting and oil palm fresh fruit bunches.

show abstract

Intelligent Color Vision System for Ripeness Classification of Oil Palm Fresh Fruit Bunch

Cited by 83 publications

References 18 publications

Using machine learning techniques and different color spaces for the classification of Cape gooseberry (Physalis peruviana L.) fruits according to ripeness level

Using machine learning techniques and different color spaces for the classification of Cape gooseberry (Physalis peruviana L.) fruits according to ripeness level

Palm oil fresh fruit bunch ripeness grading identification using color features

Artificial Lighting System in Outdoor Image Analysis Application for Oil Palm Fresh Fruit Bunches

Contact Info

Product

Resources

About