Recent advances in image processing techniques for automated harvesting purposes: A review

Abstract

Image processing has been proved to be an effective tool for analysis in various human activity areas, namely, agricultural applications. Interpreting a digital color image of fruit orchard captured in field environment is extremely challenging due to adverse weather conditions, luminance variability and the presence of dust, insects and other unavoidable image noises. The purpose of this survey is to categorize and briefly review the literature on computer analysis of fruit images in agricultural operations, which comprises more than 60 papers published in the last 10 years. With the aim to perform applied research in agricultural imaging, this paper intends to focus on advanced image processing and analysis techniques used in applications for detection and classifications of fruits, developed in the last decade. For the reviewed techniques, some performance evaluation metrics achieved in various experiments are emphasized to help the researchers when making choices and develop new computer vision applications in fruit images.