External quality is an important factor in the extraction of olive oil and the marketing of olive fruits. The
appearance and presence of external damage are factors that influence the quality of the oil extracted
and the perception of consumers, determining the level of acceptance prior to purchase in the case of
table olives. The aim of this paper is to report on artificial vision techniques developed for the online
estimation of olive quality and to assess the effectiveness of these techniques in evaluating quality based
on detecting external defects. This method of classifying olives according to the presence of defects is
based on an infrared (IR) vision system. Images of defects were acquired using a digital monochrome
camera with band-pass filters on near-infrared (NIR). The original images were processed using
segmentation algorithms, edge detection and pixel value intensity to classify the whole fruit. The
detection of the defect involved a pixel classification procedure based on nonparametric models of the
healthy and defective areas of olives. Classification tests were performed on olives to assess the
effectiveness of the proposed method.