The application of image processing for cultivar discrimination of apples based on texture features of the skin, longitudinal section and cross-section

Abstract The study was aimed at the evaluation of usefulness textures outer surface from images apple skin and flesh for discrimination different cultivars. texture parameters were calculated color channels: R , G B L a b U V H S I X Y Z . In case cultivar performed skin, highest accuracies obtained channels apples classified with total accuracy up to 93%. For channel 90%. based on selected longitudinal section apples, reached 100% cross-section images, also satisfactory 93% 97% results proved that use image processing can allow cultivars high probability in section. be applied practice detection falsification revealed features identification very an inexpensive, objective, fast way. Graphic abstract