Image-based plant phenotyping with incremental learning and active contours
- Submitting institution
-
Birmingham City University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11Z_OP_D2019
- Type
- D - Journal article
- DOI
-
10.1016/j.ecoinf.2013.07.004
- Title of journal
- Ecological Informatics
- Article number
- -
- First page
- 35-48
- Volume
- 23
- Issue
- -
- ISSN
- 1574-9541
- Open access status
- Out of scope for open access requirements
- Month of publication
- September
- Year of publication
- 2014
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
-
- Research group(s)
-
-
- Citation count
- 61
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- A new incremental-learning method is proposed for the segmentation and the automated analysis of real time-lapse plant images from phenotyping experiments in a general laboratory setting. For accurate segmentation, a vector-valued level set formulation has been developed in a way to incorporate features of colour, texture, and prior knowledge. The proposed method featured by the ease of deployment for the study of different plant species in a variety of laboratory settings. Additionally, the acquired dataset has become almost a benchmark in multi-instance segmentation, which is publicly realised to the community through the Computer Vision Problems in Plant Phenotyping (CVPPP) workshops.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -