Deep convolutional neural network models for weed detection in polyhouse grown bell peppers

Conventional weed management approaches are inefficient and non-suitable for integration with smart agricultural machinery. Automatic identification and classification of weeds can play a vital role in weed management contributing to better crop yields. Intelligent and smart spot-spraying system's efficiency relies on the accuracy of the computer vision based detectors for autonomous weed control. In the present study, feasibility of deep learning based techniques (Alexnet, GoogLeNet, InceptionV3, Xception) were evaluated in weed identification from RGB images of bell pepper field. The models were trained with different values of epochs (10, 20,30), batch sizes (16, 32), and hyperparameters were tuned to get optimal performance. The overall accuracy of the selected models varied from 94.5 to 97.7%. Among the models, InceptionV3 exhibited superior performance at 30-epoch and 16-batch size with a 97.7% accuracy, 98.5% precision, and 97.8% recall. For this Inception3 model, the type 1 error was obtained as 1.4% and type II error was 0.9%. The effectiveness of the deep learning model presents a clear path towards integrating them with image-based herbicide applicators for precise weed management. •Automatic identification of weeds can play a vital role in developing smart machinery for weed management.•The feasibility of deep convolutional neural networks for weed identification was explored.•The DCNN models AlexNet, GoogLeNet, InceptionV3 and Xception models were evaluated.•Inception V3 model was found superior for weed identification in bell peppers.