Efficient Wheat Head Segmentation with Minimal Annotation: A Generative Approach

Deep learning models have been used for a variety of image processing tasks. However, most of these models are developed through supervised learning approaches, which rely heavily on the availability of large-scale annotated datasets. Developing such datasets is tedious and expensive. In the absence...

Full description

Saved in:
Bibliographic Details
Published in:Journal of imaging 2024-06, Vol.10 (7), p.152
Main Authors: Myers, Jaden, Najafian, Keyhan, Maleki, Farhad, Ovens, Katie
Format: Article
Language:English
Subjects:
Adaptation
Annotations
data synthesis
Datasets
Deep learning
Generative adversarial networks
Image processing
Image segmentation
Performance evaluation
segmentation
Semantic segmentation
Semantics
Supervised learning
Synthetic data
Wheat
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep learning models have been used for a variety of image processing tasks. However, most of these models are developed through supervised learning approaches, which rely heavily on the availability of large-scale annotated datasets. Developing such datasets is tedious and expensive. In the absence of an annotated dataset, synthetic data can be used for model development; however, due to the substantial differences between simulated and real data, a phenomenon referred to as domain gap, the resulting models often underperform when applied to real data. In this research, we aim to address this challenge by first computationally simulating a large-scale annotated dataset and then using a generative adversarial network (GAN) to fill the gap between simulated and real images. This approach results in a synthetic dataset that can be effectively utilized to train a deep-learning model. Using this approach, we developed a realistic annotated synthetic dataset for wheat head segmentation. This dataset was then used to develop a deep-learning model for semantic segmentation. The resulting model achieved a Dice score of 83.4% on an internal dataset and Dice scores of 79.6% and 83.6% on two external datasets from the Global Wheat Head Detection datasets. While we proposed this approach in the context of wheat head segmentation, it can be generalized to other crop types or, more broadly, to images with dense, repeated patterns such as those found in cellular imagery.
ISSN:2313-433X
2313-433X
DOI:10.3390/jimaging10070152