DEVELOPMENT OF A MACHINE VISION ALGORITHM FOR RECOGNITION OF PEACH FRUIT IN A NATURAL SCENE

An algorithm for the automatic recognition of peach fruit in a natural scene was developed. Considering the red color characteristic of a mature peach, the red region of the peach was obtained first and then matching expansion was applied to recognize the entire region. By the intersection of the perpendicular bisector of the line on the contour, the potential center point of the fitting circle was obtained, and then it was grouped. Finally, by calculating the statistical parameters of the potential center points, the center point and radius of the fitting circle were obtained. Results showed that the algorithm was well adapted to the complexity of a natural environment; the area of the mature peach, the center point, and the radius were extracted quickly and accurately. The average processing time for each 640 x 480 image was 355 ms, and all the peaches were detected accurately in 383 of 400 images sampled under different natural conditions.