Plant diseases are a major cause of degraded fruit quality and yield losses. These losses can be significantly reduced with early detection of diseases to ensure their timely treatment, particularly in developing countries. In this regard, an expert system based on deep learning model where the expert knowledge, particularly the one acquired by plant pathologist, is recursively learned by the system and is applied using a smart phone application for use in the target field environment, is being proposed. In this paper, a robust disease detection method is developed based on convolutional neural network (CNN), where its powerful features extraction capabilities are leveraged to detect diseases in images of fruits and leaves. The features extraction pipelines of several state-of-the-art pretrained networks are fine-tuned to achieve optimal detection performance. A novel dataset is collected from peach orchards and extensively augmented using both label-preserving and non-label-preserving transformations. The augmented dataset is used to study the effects of finetuning the pretrained networks' feature extraction pipeline as opposed to keeping the network parameters unchanged. The CNN models, particularly EfficientNet exhibited superior performance on the target dataset once their feature extraction pipelines are fine-tuned. The optimal model is able to achieve 96.6% average accuracy, 90% sensitivity and precision, and 98% specificity on the test set of images.
This paper aims to advance research in image segmentation by developing robust techniques for evaluating image segmentation algorithms. The key contributions of this work are as follows. First, we investigate the characteristics of existing measures for supervised evaluation of automatic image segmentation algorithms. We show which of these measures is most effective at distinguishing perceptually accurate image segmentation from inaccurate segmentation. Second, we develop a complete framework for evaluating interactive segmentation algorithms by means of user experiments. We explore four strategies for this simulation, and demonstrate that the best of these produces results very similar to those from the user experiments.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.