A Novel Technique in Crop Maturity Prediction: Agriculture Automation and Farm Mechanization Application in Oil Palm Plantation and Industry

Harvesting of the primary crop in Malaysia namely oil palm fresh fruit bunches (FFB) at correct stage of ripening is important in maximizing crop yield. Digital value of image known as Hue was used to measure the oil palm fruit colour skin in actual plantation condition. Using Analysis of Variance (ANOVA) method, the Hue was found the best digital value for determine the color surface of FFB among another digital value component of Red, Green and Blue. The relationship of the oil content for Mesocarp oil palm fruits with the digital value of Hue was analysed. The procedure starts from image capturing of the FFB during unripe (black color surface until overripe stage (orange color surface). The variety of oil palm is Tenera: Elaeis Guineensis. The formulated predicted equation was Y = -0.0116X2 + 5.2376X ? 514.88 (R2 = 0.884) with Y as the Mesocarp oil content and X as the Hue optical property. High correlation of Hue digital value was found between the developed systems using the Nikon digital camera and the Keyence machine vision with correlation close to 0.929 and accuracy of 97%. Simulation model was developed for estimation the harvesting days of FFB.