Yellow Apple Recognition Method under Natural Environment

Recognition method of yellow apple fruit under natural environment was studied in the work. Firstly, image segmentation was conducted using K-Means clustering based on normalized R+G-B color feature. Meanwhile, the work adopted algorithms of Flood Fill for hole filling and elimination method of regional threshold for noise elimination. Then, edge detection of segmented images was implemented based on Canny operator, improving randomized Hough transform method for application in fruit recognition of apple image. Finally, experiments were carried out on recognition of apple fruit, indicating feasibility and effectiveness of the proposed method.