Convolutional Neural Networks and Deep Learning have revolutionized every field since their inception. Agriculture has also been reaping the fruits of developments in mentioned fields. Technology is being revolutionized to increase yield, save water wastage, take care of diseased weeds, and also increase the profit of farmers. Grapes are among the highest profit-yielding and important fruit related to the juice industry. Pakistan being an agricultural country, can widely benefit by cultivating and improving grapes per hectare yield. The biggest challenge in harvesting grapes to date is to detect their cluster successfully; many approaches tend to answer this problem by harvest and sort technique where the foreign objects are separated later from grapes after harvesting them using an automatic harvester. Currently available systems are trained on data that is from developed or grape-producing countries, thus showing data biases when used at any new location thus it gives rise to a need of creating a dataset from scratch to verify the results of research. Grape is available in different sizes, colors, seed sizes, and shapes which makes its detection, through simple Computer vision, even more challenging. This research addresses this issue by bringing the solution to this problem by using CNN and Neural Networks using the newly created dataset from local farms as the other research and the methods used don’t address issues faced locally by the farmers. YOLO has been selected to be trained on the locally collected dataset of grapes.
Shahzad, Mohammad Osama; Bin Aqeel, Anas; and Qureshi, Waqar Shahid, "Detection of Grape Clusters in Images using Convolutional Neural Network" (2023). Articles. 193.
This research received no external funding.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Share Alike 4.0 International License.