A High-Precision Detection Method of Apple Leaf Diseases Using Improved Faster R-CNN
Apple leaf diseases seriously affect the sustainable production of apple fruit. Early infection monitoring of apple leaves and timely disease control measures are the key to ensuring the regular growth of apple fruits and achieving a high-efficiency economy. Consequently, disease detection schemes b...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/13/2/240 |
| _version_ | 1797623080138309632 |
|---|---|
| author | Xulu Gong Shujuan Zhang |
| author_facet | Xulu Gong Shujuan Zhang |
| author_sort | Xulu Gong |
| collection | DOAJ |
| description | Apple leaf diseases seriously affect the sustainable production of apple fruit. Early infection monitoring of apple leaves and timely disease control measures are the key to ensuring the regular growth of apple fruits and achieving a high-efficiency economy. Consequently, disease detection schemes based on computer vision can compensate for the shortcomings of traditional disease detection methods that are inaccurate and time-consuming. Nowadays, to solve the limitations ranging from complex background environments to dense and small characteristics of apple leaf diseases, an improved Faster region-based convolutional neural network (Faster R-CNN) method was proposed. The advanced Res2Net and feature pyramid network architecture were introduced as the feature extraction network for extracting reliable and multi-dimensional features. Furthermore, RoIAlign was also employed to replace RoIPool so that accurate candidate regions will be produced to address the object location. Moreover, soft non-maximum suppression was applied for precise detection performance of apple leaf disease when making inferences to the images. The improved Faster R-CNN structure behaves effectively in the annotated apple leaf disease dataset with an accuracy of 63.1% average precision, which is higher than other object detection methods. The experiments proved that our improved Faster R-CNN method provides a highly precise apple leaf disease recognition method that could be used in real agricultural practice. |
| first_indexed | 2024-03-11T09:19:20Z |
| format | Article |
| id | doaj.art-d781db088bb045019a384c83b51035ac |
| institution | Directory Open Access Journal |
| issn | 2077-0472 |
| language | English |
| last_indexed | 2024-03-11T09:19:20Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj.art-d781db088bb045019a384c83b51035ac2023-11-16T18:28:15ZengMDPI AGAgriculture2077-04722023-01-0113224010.3390/agriculture13020240A High-Precision Detection Method of Apple Leaf Diseases Using Improved Faster R-CNNXulu Gong0Shujuan Zhang1College of Agricultural Engineering, Shanxi Agricultural University, Jinzhong 030801, ChinaCollege of Agricultural Engineering, Shanxi Agricultural University, Jinzhong 030801, ChinaApple leaf diseases seriously affect the sustainable production of apple fruit. Early infection monitoring of apple leaves and timely disease control measures are the key to ensuring the regular growth of apple fruits and achieving a high-efficiency economy. Consequently, disease detection schemes based on computer vision can compensate for the shortcomings of traditional disease detection methods that are inaccurate and time-consuming. Nowadays, to solve the limitations ranging from complex background environments to dense and small characteristics of apple leaf diseases, an improved Faster region-based convolutional neural network (Faster R-CNN) method was proposed. The advanced Res2Net and feature pyramid network architecture were introduced as the feature extraction network for extracting reliable and multi-dimensional features. Furthermore, RoIAlign was also employed to replace RoIPool so that accurate candidate regions will be produced to address the object location. Moreover, soft non-maximum suppression was applied for precise detection performance of apple leaf disease when making inferences to the images. The improved Faster R-CNN structure behaves effectively in the annotated apple leaf disease dataset with an accuracy of 63.1% average precision, which is higher than other object detection methods. The experiments proved that our improved Faster R-CNN method provides a highly precise apple leaf disease recognition method that could be used in real agricultural practice.https://www.mdpi.com/2077-0472/13/2/240apple leaf diseasesFaster R-CNNdeep learningobject detection |
| spellingShingle | Xulu Gong Shujuan Zhang A High-Precision Detection Method of Apple Leaf Diseases Using Improved Faster R-CNN Agriculture apple leaf diseases Faster R-CNN deep learning object detection |
| title | A High-Precision Detection Method of Apple Leaf Diseases Using Improved Faster R-CNN |
| title_full | A High-Precision Detection Method of Apple Leaf Diseases Using Improved Faster R-CNN |
| title_fullStr | A High-Precision Detection Method of Apple Leaf Diseases Using Improved Faster R-CNN |
| title_full_unstemmed | A High-Precision Detection Method of Apple Leaf Diseases Using Improved Faster R-CNN |
| title_short | A High-Precision Detection Method of Apple Leaf Diseases Using Improved Faster R-CNN |
| title_sort | high precision detection method of apple leaf diseases using improved faster r cnn |
| topic | apple leaf diseases Faster R-CNN deep learning object detection |
| url | https://www.mdpi.com/2077-0472/13/2/240 |
| work_keys_str_mv | AT xulugong ahighprecisiondetectionmethodofappleleafdiseasesusingimprovedfasterrcnn AT shujuanzhang ahighprecisiondetectionmethodofappleleafdiseasesusingimprovedfasterrcnn AT xulugong highprecisiondetectionmethodofappleleafdiseasesusingimprovedfasterrcnn AT shujuanzhang highprecisiondetectionmethodofappleleafdiseasesusingimprovedfasterrcnn |