Weed/Plant Classification Using Evolutionary Optimised Ensemble Based On Local Binary Patterns
This thesis presents a novel pixel-level weed classification through rotation-invariant uniform local binary pattern (LBP) features for precision weed control. Based on two-level optimisation structure; First, Genetic Algorithm (GA) optimisation to select the best rotation-invariant uniform LBP conf...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
Curtin University
2022
|
| Online Access: | http://hdl.handle.net/20.500.11937/88106 |
| _version_ | 1848764961863499776 |
|---|---|
| author | Lease, Basil Andy |
| author_facet | Lease, Basil Andy |
| author_sort | Lease, Basil Andy |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | This thesis presents a novel pixel-level weed classification through rotation-invariant uniform local binary pattern (LBP) features for precision weed control. Based on two-level optimisation structure; First, Genetic Algorithm (GA) optimisation to select the best rotation-invariant uniform LBP configurations; Second, Covariance Matrix Adaptation Evolution Strategy (CMA-ES) in the Neural Network (NN) ensemble to select the best combinations of voting weights of the predicted outcome for each classifier. The model obtained 87.9% accuracy in CWFID public benchmark. |
| first_indexed | 2025-11-14T11:27:41Z |
| format | Thesis |
| id | curtin-20.500.11937-88106 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T11:27:41Z |
| publishDate | 2022 |
| publisher | Curtin University |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-881062022-03-14T07:34:00Z Weed/Plant Classification Using Evolutionary Optimised Ensemble Based On Local Binary Patterns Lease, Basil Andy This thesis presents a novel pixel-level weed classification through rotation-invariant uniform local binary pattern (LBP) features for precision weed control. Based on two-level optimisation structure; First, Genetic Algorithm (GA) optimisation to select the best rotation-invariant uniform LBP configurations; Second, Covariance Matrix Adaptation Evolution Strategy (CMA-ES) in the Neural Network (NN) ensemble to select the best combinations of voting weights of the predicted outcome for each classifier. The model obtained 87.9% accuracy in CWFID public benchmark. 2022 Thesis http://hdl.handle.net/20.500.11937/88106 Curtin University fulltext |
| spellingShingle | Lease, Basil Andy Weed/Plant Classification Using Evolutionary Optimised Ensemble Based On Local Binary Patterns |
| title | Weed/Plant Classification Using Evolutionary Optimised
Ensemble Based On Local Binary Patterns |
| title_full | Weed/Plant Classification Using Evolutionary Optimised
Ensemble Based On Local Binary Patterns |
| title_fullStr | Weed/Plant Classification Using Evolutionary Optimised
Ensemble Based On Local Binary Patterns |
| title_full_unstemmed | Weed/Plant Classification Using Evolutionary Optimised
Ensemble Based On Local Binary Patterns |
| title_short | Weed/Plant Classification Using Evolutionary Optimised
Ensemble Based On Local Binary Patterns |
| title_sort | weed/plant classification using evolutionary optimised
ensemble based on local binary patterns |
| url | http://hdl.handle.net/20.500.11937/88106 |