Grading of oil palm fresh fruit bunches (FFB) is commonly conducted using visual inspection by trained workers who inspect the oil palm FFB according to the colour and the number of the loose fruits on the ground. However, this method is labour intensive and time consuming. In addition, the workers may misclassify the fruit’s ripeness due to the height of the tree, miscounting the loose fruits, unclear vision of the bunches on the tree and lighting conditions. Unripe or overripe bunches result in a less efficient palm oil refining process, low palm oil quality and profit losses. Non-destructive techniques can offer better solutions for ripeness classifications with higher accuracy. The techniques are field and lab spectroscopy, computer vision, hyperspectral imaging, laser-light backscattering imaging and fruit battery sensor. Spectroscopy, hyperspectral imaging and laser-light backscattering imaging techniques need to be deployed with a special set up which may not be suitable for real-time ripeness classification. Computer vision, using image processing techniques and machine learning algorithms allow real-time in-situ ripeness classification via mobile devices. This article aims to review the feasibility of each method to allow real-time in-situ ripeness classification of the oil palm fruit bunches with high accuracy.