In recent years, consumers have shown interest in non-destructive methods to assess the fruit’s internal quality during ripening. A common and commercial fruit in tropical and subtropical areas of the world is the mango. In this chapter, we investigate the problem of classifying an image of a fruit, specifically, mango as a raw or ripe. Several pre-trained models such as VGG16, MobileNetV2, and Xception are used for making the classification. Their performances are assessed using different performance measures including accuracy, precision, sensitivity, specificity, F1-score, and inference time. Results show that Xception model had the best performance with accuracy of 99.6% for differentiating raw and ripe mangos in terms of the mentioned performance measures.