Palm oil plant (Elaeis guineensis jacq) is one of the most popular plants in Indonesian plantation and also a species of the palm family. Harvesting process should obtain fresh fruit bunches at optimal ripeness. Some farmers are lack of ripeness knowledge and do not understand which color that represents optimal ripeness of palm fruit to harvest. Another issue on the scarcity of such system provides ripeness identification also encourage a study to develop an image-processing-based expert system. The aim of this study is to provide a tool for examining oil palm fruit ripeness level. Identification system consists of several image processing phases, namely image edge detection and feature value of the image to be calculated such as mean value, standard deviation, skewness, entropy, energy, homogeneity, contrast and intensity. In the proposed work, K-Nearest Neighbor (KNN) is applied as a computation method which allows the system to classify data of ripeness level based on user-entered image. The output is the identification of the ripeness level of the oil palm fruit.