Over the last several years there has been a renewed interest in the automation of harvesting of\r\nfruits and vegetables. The two major challenges in the automation of harvesting are the\r\nrecognition of the fruit and its detachment from the tree. This paper deals with fruit recognition\r\nand it presents the development of a machine vision algorithm for the recognition of orange\r\nfruits. The algorithm consists of segmentation, region labeling, size filtering, perimeter extraction\r\nand perimeter-based detection. In the segmentation of the fruit, the orange was enhanced by\r\nusing the red chromaticity coefficient which enabled adaptive segmentation under variable\r\noutdoor illumination. The algorithm also included detection of fruits which are in clusters by\r\nusing shape analysis techniques. Evaluation of the algorithm included images taken inside the\r\ncanopy (varying lighting condition) and on the canopy surface. Results showed that more than\r\n90% of the fruits visually recognized in the images were detected in the 110 images tested with a\r\nfalse detection rate of 4%. The proposed segmentation was able to deal with varying lighting\r\ncondition and the perimeter-based detection method proved to be effective in detecting fruits in\r\nclusters. The development of this algorithm with its capability of detecting fruits in varying\r\nlighting condition and occlusion would enhance the overall performance of robotic fruit\r\nharvesting.
Loading....