Semantic Segmentation of Plant Leaves Based on Generative Adversarial Network and Attention Mechanism
Due to the rapid growth of the population, the pressure on food is increasing and the demand for higher crop yields is rising. It is crucial to periodically monitor plant phenotypic traits, and deep learning has a good effect on image recognition and segmentation. This paper proposes a method based...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9828400/ |
| _version_ | 1818002499876945920 |
|---|---|
| author | Liying Cao Hongda Li Xuerui Liu Guifen Chen Helong Yu |
| author_facet | Liying Cao Hongda Li Xuerui Liu Guifen Chen Helong Yu |
| author_sort | Liying Cao |
| collection | DOAJ |
| description | Due to the rapid growth of the population, the pressure on food is increasing and the demand for higher crop yields is rising. It is crucial to periodically monitor plant phenotypic traits, and deep learning has a good effect on image recognition and segmentation. This paper proposes a method based on generative adversarial network and attention mechanism to improve the accuracy of semantic segmentation of plant leaves. First, the data set is standardized and divided into a training set and test set. The generator that produces the confrontation network uses Segnet as the backbone network and adds an attention mechanism to extract the phenotypic characteristics of plants. The discriminator utilizes a dual-input fully connected layer for true and false estimate. The experimental results show that compared with the original Segnet segmentation network, the proposed strategy improves the precision of pixel recognition PA. Also, the suggested technique has a high level of robustness and feature extraction precision. In addition to providing technical assistance for future crop cultivation and breeding, monitoring crop growth, ensuring yields as well as solving the food shortage problem. |
| first_indexed | 2024-04-14T03:46:40Z |
| format | Article |
| id | doaj.art-2a42b5fda0b94aa5b2b66f51ae819c42 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-14T03:46:40Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-2a42b5fda0b94aa5b2b66f51ae819c422022-12-22T02:14:12ZengIEEEIEEE Access2169-35362022-01-0110763107631710.1109/ACCESS.2022.31903479828400Semantic Segmentation of Plant Leaves Based on Generative Adversarial Network and Attention MechanismLiying Cao0https://orcid.org/0000-0001-7413-8385Hongda Li1Xuerui Liu2Guifen Chen3Helong Yu4College of Information and Technology, Jilin Agricultural University, Changchun, ChinaCollege of Information and Technology, Jilin Agricultural University, Changchun, ChinaCollege of Information and Technology, Jilin Agricultural University, Changchun, ChinaChangchun Humanities and Sciences College, Changchun, ChinaCollege of Information and Technology, Jilin Agricultural University, Changchun, ChinaDue to the rapid growth of the population, the pressure on food is increasing and the demand for higher crop yields is rising. It is crucial to periodically monitor plant phenotypic traits, and deep learning has a good effect on image recognition and segmentation. This paper proposes a method based on generative adversarial network and attention mechanism to improve the accuracy of semantic segmentation of plant leaves. First, the data set is standardized and divided into a training set and test set. The generator that produces the confrontation network uses Segnet as the backbone network and adds an attention mechanism to extract the phenotypic characteristics of plants. The discriminator utilizes a dual-input fully connected layer for true and false estimate. The experimental results show that compared with the original Segnet segmentation network, the proposed strategy improves the precision of pixel recognition PA. Also, the suggested technique has a high level of robustness and feature extraction precision. In addition to providing technical assistance for future crop cultivation and breeding, monitoring crop growth, ensuring yields as well as solving the food shortage problem.https://ieeexplore.ieee.org/document/9828400/Semantic segmentationattention mechanismgenerative adversarial networkSegnetphenotypic characteristics |
| spellingShingle | Liying Cao Hongda Li Xuerui Liu Guifen Chen Helong Yu Semantic Segmentation of Plant Leaves Based on Generative Adversarial Network and Attention Mechanism IEEE Access Semantic segmentation attention mechanism generative adversarial network Segnet phenotypic characteristics |
| title | Semantic Segmentation of Plant Leaves Based on Generative Adversarial Network and Attention Mechanism |
| title_full | Semantic Segmentation of Plant Leaves Based on Generative Adversarial Network and Attention Mechanism |
| title_fullStr | Semantic Segmentation of Plant Leaves Based on Generative Adversarial Network and Attention Mechanism |
| title_full_unstemmed | Semantic Segmentation of Plant Leaves Based on Generative Adversarial Network and Attention Mechanism |
| title_short | Semantic Segmentation of Plant Leaves Based on Generative Adversarial Network and Attention Mechanism |
| title_sort | semantic segmentation of plant leaves based on generative adversarial network and attention mechanism |
| topic | Semantic segmentation attention mechanism generative adversarial network Segnet phenotypic characteristics |
| url | https://ieeexplore.ieee.org/document/9828400/ |
| work_keys_str_mv | AT liyingcao semanticsegmentationofplantleavesbasedongenerativeadversarialnetworkandattentionmechanism AT hongdali semanticsegmentationofplantleavesbasedongenerativeadversarialnetworkandattentionmechanism AT xueruiliu semanticsegmentationofplantleavesbasedongenerativeadversarialnetworkandattentionmechanism AT guifenchen semanticsegmentationofplantleavesbasedongenerativeadversarialnetworkandattentionmechanism AT helongyu semanticsegmentationofplantleavesbasedongenerativeadversarialnetworkandattentionmechanism |