Plant leaf classification and retrieval using multi‐scale shape descriptor
Abstract Plant leaf classification is a significant and challenging research problem in computer vision area. In this study, an original multi‐scale shape descriptor is presented to perform leaf classification and retrieval. Firstly, a novel iterative rule is proposed as scales generation method, wh...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-08-01
|
| Series: | The Journal of Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/tje2.12050 |
| _version_ | 1818531621791334400 |
|---|---|
| author | Guoqing Xu Chen Li |
| author_facet | Guoqing Xu Chen Li |
| author_sort | Guoqing Xu |
| collection | DOAJ |
| description | Abstract Plant leaf classification is a significant and challenging research problem in computer vision area. In this study, an original multi‐scale shape descriptor is presented to perform leaf classification and retrieval. Firstly, a novel iterative rule is proposed as scales generation method, which is parameter free. Secondly, leaf contour points are represented by angle information which is calculated using their neighbour points under each scale. The angle information representation is invariant to image rotation, translation and scaling. More importantly, it can describe leaf in a hierarchical way by capturing leaf features from global to local variations. Then Fast Fourier Transform operation is applied to make the representation more compact and independent from starting point. Subsequently, for leaf retrieval the dissimilarity of each pair of leaf under each scale is computed using city block metric. And support vector machine is used as classifier for leaf classification. Finally, experiments and comparisons with multiple state‐of‐the‐art approaches are performed. The classification accuracy was 96.85% and 93.56% respectively on Swedish and Flavia leaf datasets. The mean average precision score was 66.42%, 76.69% and 44.14% respectively on Flavia, Swedish and MEW2012 leaf datasets. The results demonstrate that the proposed method has excellent performance. |
| first_indexed | 2024-12-11T17:34:50Z |
| format | Article |
| id | doaj.art-55934127e2d546eaaa2bd73f92d936dd |
| institution | Directory Open Access Journal |
| issn | 2051-3305 |
| language | English |
| last_indexed | 2024-12-11T17:34:50Z |
| publishDate | 2021-08-01 |
| publisher | Wiley |
| record_format | Article |
| series | The Journal of Engineering |
| spelling | doaj.art-55934127e2d546eaaa2bd73f92d936dd2022-12-22T00:56:42ZengWileyThe Journal of Engineering2051-33052021-08-012021846747510.1049/tje2.12050Plant leaf classification and retrieval using multi‐scale shape descriptorGuoqing Xu0Chen Li1School of Information Engineering Nanyang Institute of Technology NO.80 ChangJiang Road Nanyang ChinaSchool of Computer Science North China University of Technology No.5 Jinyuanzhuang Road Beijing ChinaAbstract Plant leaf classification is a significant and challenging research problem in computer vision area. In this study, an original multi‐scale shape descriptor is presented to perform leaf classification and retrieval. Firstly, a novel iterative rule is proposed as scales generation method, which is parameter free. Secondly, leaf contour points are represented by angle information which is calculated using their neighbour points under each scale. The angle information representation is invariant to image rotation, translation and scaling. More importantly, it can describe leaf in a hierarchical way by capturing leaf features from global to local variations. Then Fast Fourier Transform operation is applied to make the representation more compact and independent from starting point. Subsequently, for leaf retrieval the dissimilarity of each pair of leaf under each scale is computed using city block metric. And support vector machine is used as classifier for leaf classification. Finally, experiments and comparisons with multiple state‐of‐the‐art approaches are performed. The classification accuracy was 96.85% and 93.56% respectively on Swedish and Flavia leaf datasets. The mean average precision score was 66.42%, 76.69% and 44.14% respectively on Flavia, Swedish and MEW2012 leaf datasets. The results demonstrate that the proposed method has excellent performance.https://doi.org/10.1049/tje2.12050Optical, image and video signal processingImage recognitionOther topics in statisticsComputer vision and image processing techniquesInformation retrieval techniquesBiology and medical computing |
| spellingShingle | Guoqing Xu Chen Li Plant leaf classification and retrieval using multi‐scale shape descriptor The Journal of Engineering Optical, image and video signal processing Image recognition Other topics in statistics Computer vision and image processing techniques Information retrieval techniques Biology and medical computing |
| title | Plant leaf classification and retrieval using multi‐scale shape descriptor |
| title_full | Plant leaf classification and retrieval using multi‐scale shape descriptor |
| title_fullStr | Plant leaf classification and retrieval using multi‐scale shape descriptor |
| title_full_unstemmed | Plant leaf classification and retrieval using multi‐scale shape descriptor |
| title_short | Plant leaf classification and retrieval using multi‐scale shape descriptor |
| title_sort | plant leaf classification and retrieval using multi scale shape descriptor |
| topic | Optical, image and video signal processing Image recognition Other topics in statistics Computer vision and image processing techniques Information retrieval techniques Biology and medical computing |
| url | https://doi.org/10.1049/tje2.12050 |
| work_keys_str_mv | AT guoqingxu plantleafclassificationandretrievalusingmultiscaleshapedescriptor AT chenli plantleafclassificationandretrievalusingmultiscaleshapedescriptor |