Multi-Scale Image Segmentation Model for Fine-Grained Recognition of Zanthoxylum Rust
Source abstract
Abstract
Zanthoxylum bungeanum Maxim, generally called prickly ash, is widely grown in China. Zanthoxylum rust is the main disease affecting the growth and quality of Zanthoxylum. Traditional method for recognizing the degree of infection of Zanthoxylum rust mainly rely on manual experience. Due to the complex colors and shapes of rust areas, the accuracy of manual recognition is low and difficult to be quantified. In recent years, the application of artificial intelligence technology in the agricultural field has gradually increased. In this paper, based on the DeepLabV2 model, we proposed a Zanthoxylum rust image segmentation model based on the FASPP module and enhanced features of rust areas. This paper constructed a fine-grained Zanthoxylum rust image dataset. In this dataset, the Zanthoxylum rust image was segmented and labeled according to leaves, spore piles, and brown lesions. The experimental results showed that the Zanthoxylum rust image segmentation method proposed in this paper was effective. The segmentation accuracy rates of leaves, spore piles and brown lesions reached 99.66%, 85.16% and 82.47% respectively. MPA reached 91.80%, and MIoU reached 84.99%. At the same time, the proposed image segmentation model also had good efficiency, which can process 22 images per minute. This article provides an intelligent method for efficiently and accurately recognizing the degree of infection of Zanthoxylum rust.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Technology and Security Systems · Smart Agriculture and AI
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (44)
Show source-provided references
1. Phytochemical investigation, anti-inflammatory, antipyretic and antinociceptive activities of Zanthoxylum armatum DC extracts-in vivo and in vitro experiments10.1016/j.heliyon.2020.e05571 ↗
2. Research on segmentation features in visual detection of rust on bridge pier
3. Coffee leaf rust detection using convolutional neural network
4. An automated image processing method for segmentation and quantification of rust disease in maize leaves
5. Refined image segmentation for calorie estimation of multiple-dish food items
6. Segmentation of white blood cells using image segmentation algorithms
7. Image segmentation using convolutional neural network for image annotation
8. Modeling multi-targets sentiment classification via graph convolutional networks and auxiliary relation10.32604/cmc.2020.09913 ↗
9. Dl-har: Deep learning-based human activity recognition framework for edge computing10.32604/cmc.2020.011740 ↗
10. Object detection and fuzzy-based classification using uav data10.32604/iasc.2020.010103 ↗
11. Classifying image analysis techniques from their output10.1080/18756891.2016.1180819 ↗
12. Visualizing the human subcortex using ultra-high field magnetic resonance imaging10.1007/s10548-018-0638-7 ↗
13. Symmetric region growing10.1109/TIP.2003.815258 ↗
14. Superpixel lattices
15. Automatic segmentation of point clouds from multi-view reconstruction using graph-cut10.1007/s00371-015-1076-0 ↗
16. View and illumination invariant object classification based on 3D color histogram using convolutional neural networks
17. Automated melanoma staging in lymph node biopsy image using deep learning
18. Fully convolutional networks for semantic segmentation
19. Learning deconvolution network for semantic segmentation
20. U-Net: Convolutional networks for biomedical image segmentation
21. Mask R-CNN
22. Faster R-CNN: Towards real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗
23. Pyramid scene parsing network
24. An exploratory of hybrid techniques on deep learning for image classification
25. A deep CNN approach with transfer learning for image recognition
26. Brain tumor segmentation with deep learning technique
27. Ore image segmentation method based on u-net and watershed10.32604/cmc.2020.09806 ↗
28. The instance-aware automatic image colorization based on deep convolutional neural network10.32604/iasc.2020.010118 ↗
29. A multi-agent system for environmental monitoring using boolean networks and reinforcement learning10.32604/jcs.2020.010086 ↗
30. Object tracking based on deep CNN features together with color features and sparse representation
31. Multi-model ensemble with rich spatial information for object detection10.1016/j.patcog.2019.107098 ↗
32. A fast human action recognition network based on spatio-temporal features10.1016/j.neucom.2020.04.150 ↗
33. Hybrid malware detection approach with feedback-directed machine learning10.1007/s11432-018-9615-8 ↗
34. Visual tracking with weighted adaptive local sparse appearance model via spatio-temporal context learning10.1109/TIP.2018.2839916 ↗
35. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs10.1109/TPAMI.2017.2699184 ↗
36. Infrared image semantic segmentation based on improved deeplab and residual network
37. DeepText: Detecting text from the wild with multi-ASPP-assembled deeplab
38. Ultrasound image segmentation method for thyroid nodules using ASPP fusion features10.1109/ACCESS.2020.3022249 ↗
39. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs10.1109/TPAMI.2017.2699184 ↗
40. A deep learning method with CRF for instance segmentation of metal-organic frameworks in scanning electron microscopy images
41. A method of CNN traffic classification based on sppnet
42. Ultrasound image segmentation method for thyroid nodules using ASPP fusion features10.1109/ACCESS.2020.3022249 ↗
43. LabelMe: Online image annotation and applications
44. Family-based big medical-level data acquisition system10.1109/TII.2018.2879430 ↗