A Machine Vision Algorithm Combining Adaptive Segmentation and Shape Analysis for Orange Fruit Detection
Over the last several years there has been a renewed interest in the automation of harvesting of fruits and vegetables. The two major challenges in the automation of harvesting are the recognition of the fruit and its detachment from the tree. This paper deals with fruit recognition and it presents the development of a machine vision algorithm for the recognition of orange fruits. The algorithm consists of segmentation, region labeling, size filtering, perimeter extraction and perimeter-based detection. In the segmentation of the fruit, the orange was enhanced by using the red chromaticity coefficient which enabled adaptive segmentation under variable outdoor illumination. The algorithm also included detection of fruits which are in clusters by using shape analysis techniques. Evaluation of the algorithm included images taken inside the canopy (varying lighting condition) and on the canopy surface. Results showed that more than 90% of the fruits visually recognized in the images were detected in the 110 images tested with a false detection rate of 4%. The proposed segmentation was able to deal with varying lighting condition and the perimeter-based detection method proved to be effective in detecting fruits in clusters. The development of this algorithm with its capability of detecting fruits in varying lighting condition and occlusion would enhance the overall performance of robotic fruit harvesting.