Related references
Note: Only part of the references are listed.
Article
Green & Sustainable Science & Technology
Normaisharah Mamat et al.
Summary: An accurate image retrieval technique is needed due to the increasing number of images, and it is important to implement fast, simple, and automatic image annotation techniques. This study focuses on the agriculture field and uses automatic image annotation to classify the ripeness of oil palm fruit and recognize different types of fruits. The proposed approach improves fruit classification methods and enhances production for farmers. Simple and effective models using deep learning with You Only Look Once (YOLO) versions are developed and trained with a dataset of 100 oil palm fruit images and 400 images of various fruits in RGB format. The performance and accuracy of the models in annotating 3500 fruit images are evaluated, achieving excellent results with an mAP of 98.7% for oil palm fruit and 99.5% for different types of fruit.
Article
Green & Sustainable Science & Technology
Yonis Gulzar
Summary: Due to the rapid emergence and evolution of AI applications, the utilization of smart imaging devices has significantly increased. Researchers have used deep learning models, such as CNN, for image classification without the need for handcrafted features. In this study, a dataset of 26,149 images of 40 different types of fruits was used to develop TL-MobileNetV2, a modified version of MobileNetV2, using transfer learning and a customized head. TL-MobileNetV2 achieved an accuracy of 99%, outperforming other models, and demonstrated the effectiveness of transfer learning and dropout technique in improving results.
Article
Computer Science, Artificial Intelligence
Haoran Liu et al.
Summary: In this paper, a hierarchical feature fusion attention network (HFANet) is proposed to enhance the feature extraction capability for glomerular immunofluorescence (IF) images. An intensity equalization (IE) algorithm is also introduced to improve image quality and generate IF descriptions. An encoder-decoder architecture with HFANet as the core is utilized to generate descriptions that emulate the reading habits of clinicians. Extensive experiments validate the effectiveness of the proposed modules and the generalization performance of the framework.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Agriculture, Multidisciplinary
Yun Zhao et al.
Summary: In this paper, a convolutional neural network model based on Inception and residual structure with an embedded modified convolutional block attention module (CBAM) was proposed to enhance classification accuracy of plant leaf diseases. The model achieved a high overall accuracy of 99.55% for the identification of corn, potato, and tomato diseases. Additionally, individual accuracy rates of 98.44%, 99.43%, and 95.20% were achieved for corn, potato, and tomato, respectively. The model demonstrated fewer parameters, shorter training time, and higher recognition accuracy compared to existing image classification models.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Computer Science, Artificial Intelligence
Chunbin Gu et al.
Summary: This paper addresses the issue of cross-modal image retrieval through a new approach based on contrastive self-supervised learning methods to bridge the gap between modalities. The experiments demonstrate that the method achieves state-of-the-art retrieval performance on three large-scale benchmarks.
Article
Agriculture, Multidisciplinary
Shufei Li et al.
Summary: This study proposes an efficient detection method, MTC-YOLOv5n, based on the YOLOv5 model, for plant disease detection in natural scenarios. The method integrates Coordinate Attention and Transformer, and combines Multi-scale training and feature fusion network to improve small object detection accuracy. Experimental results show that MTC-YOLOv5n has higher detection accuracy and speed, smaller computation and model size, and strong robustness.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Agriculture, Multidisciplinary
Jiawei Li et al.
Summary: This study proposes an improved algorithm based on YOLOv5s for vegetable disease detection. By enhancing certain modules in the algorithm, the accuracy of disease detection has been improved, and it shows good performance in detecting and localizing diseases in complex backgrounds and small scales. The experiments demonstrate that the proposed algorithm has higher detection and localization accuracy compared to other algorithms.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Green & Sustainable Science & Technology
Jinlong Dong et al.
Summary: Global human health and sustainable production are threatened by an imbalance and deficiency of plant-based diet vegetable consumption across countries worldwide. The predicted increase in vegetable supply by 2030 is still lower than the recommended intake, with the top vegetable supply regions centered at the global vegetable belt. Developed regions struggle to ensure vegetable supply, while regions with meat-preferred diets and modern vegetable supply systems have low levels of vegetable supply.
JOURNAL OF CLEANER PRODUCTION
(2022)
Article
Agriculture, Multidisciplinary
Keke Zhang et al.
Summary: The paper develops a synthetic soybean leaf disease image dataset and designs a multi-feature fusion Faster R-CNN (MF3 RCNN) to address the issues of insufficient dataset and technical difficulties in detecting soybean leaf disease. The model achieves an optimal mean average precision of 83.34% in real test dataset, indicating its effectiveness in detecting soybean leaf disease in complex scene and outperforming the state-of-the-art methods.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Automation & Control Systems
Xubing Yang et al.
Summary: The proposed automatic annotation method for forest fire images introduces supervised information through interactive convex hulls at the pixel level, allowing visually selecting irregular fire and no-fire regions. It expands the view of fire detection to multi-class classification and loosens the constraints of i.i.d hypothesis in machine learning methods. Experimental evaluations show that it achieves higher fire detection rate and lower false alarm rate compared to state-of-the-art methods.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Review
Nutrition & Dietetics
Dominika Glabska et al.
Article
Computer Science, Artificial Intelligence
Xianhua Zeng et al.
Article
Plant Sciences
Alvaro Fuentes et al.
FRONTIERS IN PLANT SCIENCE
(2019)
Article
Agriculture, Multidisciplinary
Artzai Picon et al.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Linjie Yang et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Justin Johnson et al.
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2016)
Proceedings Paper
Computer Science, Artificial Intelligence
Ross Girshick
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2015)
Article
Computer Science, Artificial Intelligence
J. R. R. Uijlings et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2013)
Article
Computer Science, Artificial Intelligence
Dumitru Dan Burdescu et al.
Article
Computer Science, Artificial Intelligence
Yong Wang et al.
PATTERN RECOGNITION
(2009)
