Multiple Fruit Disease Detection using Deep Learning

We propose a computer vision system that detects the external defects of fruits using multi-spectral imaging sensor. First, the pro- posed algorithm segments the fruit from the captured Near-Infra Red (NIR) and RGB images using only the NIR component. Second, some adaptive pre-processing techniques are applied on the segmented RGB and NIR fruit images. Hence, a thresholding technique is utilized in order to detect the defects in seven different color components of the fruit. Finally, a voting process is applied on the seven threshold color components images to determine if the fruit image is defected or defect free.