Projects per year
Abstract
A current bottleneck of state-of-the-art machine learning methods for image segmentation in agriculture, e.g. convolutional neural networks (CNNs), is the requirement of large manually annotated datasets on a per-pixel level. In this paper, we investigated how related synthetic images can be used to bootstrap CNNs for successful learning as compared to other learning strategies. We hypothesise that a small manually annotated empirical dataset is sufficient for fine-tuning a synthetically bootstrapped CNN. Furthermore we investigated (i) multiple deep learning architectures, (ii) the correlation between synthetic and empirical dataset size on part segmentation performance, (iii) the effect of post-processing using conditional random fields (CRF) and (iv) the generalisation performance on other related datasets. For this we have performed 7 experiments using the Capsicum annuum (bell or sweet pepper) dataset containing 50 empirical and 10,500 synthetic images with 7 pixel-level annotated part classes. Results confirmed our hypothesis that only 30 empirical images were required to obtain the highest performance on all 7 classes (mean IOU = 0.40) when a CNN was bootstrapped on related synthetic data. Furthermore we found optimal empirical performance when a VGG-16 network was modified to include à trous spatial pyramid pooling. Adding CRF only improved performance on the synthetic data. Training binary classifiers did not improve results. We have found a positive correlation between dataset size and performance. For the synthetic dataset, learning stabilises around 3000 images. Generalisation to other related datasets proved possible.
Original language | English |
---|---|
Pages (from-to) | 291-304 |
Journal | Computers and Electronics in Agriculture |
Volume | 161 |
Early online date | 19 Dec 2017 |
DOIs | |
Publication status | Published - Jun 2019 |
Keywords
- Big data
- Bootstrapping
- Computer vision
- Semantic segmentation
- Synthetic dataset
Fingerprint
Dive into the research topics of 'Synthetic bootstrapping of convolutional neural networks for semantic plant part segmentation'. Together they form a unique fingerprint.Datasets
-
Synthetic and Empirical Capsicum Annuum Image Dataset
Barth, R. (Creator), Wageningen University & Research, 6 Dec 2016
DOI: 10.4121/uuid:884958f5-b868-46e1-b3d8-a0b5d91b02c0
Dataset
Projects
- 2 Finished
-
-
EU-2015-03 SWEEPER (BO-52-001-002, BO-25.06-002-003)
Balendonck, J. (Project Leader)
1/01/15 → 31/12/18
Project: LVVN project