Nowadays, quality inspection of fruit and vegetables is typically accomplished through visual inspection. Automation of this inspection is desirable to make it more objective. For this, hyperspectral imaging has been identified as apromising technique. When the field of view includes multiple objects, hypercubes should be segmented to assign individual pixels to different objects. Unsupervised and supervised methods have been proposed. While the latter are labour intensive asthey require masking of the training images, the former are too computationally intensive for in-line use and may provide different results for different hypercubes. Therefore, a semi-supervised method is proposed to train a computationally efficientsegmentation algorithm with minimal human interaction. As a first step, an unsupervised classification model is used to cluster spectra in similar groups. In the second step, a pixel selection algorithm applied to the output of the unsupervised classificationis used to build a supervised model which is fast enough for in-line use. To evaluate this approach, it is applied to hypercubes of vine tomatoes and table grapes. After first derivative spectral preprocessing to remove intensity variation due to curvature andgloss effects, the unsupervised models segmented 86.11% of the vine tomato images correctly. Considering overall accuracy, sensitivity, specificity and time needed to segment one hypercube, partial least squares discriminant analysis (PLS-DA) wasfound to be the best choice for in-line use, when using one training image. By adding a second image, the segmentation results improved considerably, yielding an overall accuracy of 96.95% for segmentation of vine tomatoes and 98.52% for segmentationof table grapes, demonstrating the added value of the learning phase in the algorithm.