Super Resolution for Root Imaging
This work addresses the challenge of acquiring high-resolution root imagery for plant phenotyping, but it is incremental as it applies existing CNN methods to a specific domain with minor training variations.
The paper tackled the problem of enhancing low-resolution images of plant roots for phenotyping by proposing a super-resolution framework using convolutional neural networks, demonstrating that models outperform bicubic interpolation even when trained on non-root datasets and achieve high segmentation performance independently of SNR.
High-resolution cameras have become very helpful for plant phenotyping by providing a mechanism for tasks such as target versus background discrimination, and the measurement and analysis of fine-above-ground plant attributes. However, the acquisition of high-resolution (HR) imagery of plant roots is more challenging than above-ground data collection. Thus, an effective super-resolution (SR) algorithm is desired for overcoming resolution limitations of sensors, reducing storage space requirements, and boosting the performance of later analysis, such as automatic segmentation. We propose a SR framework for enhancing images of plant roots by using convolutional neural networks (CNNs). We compare three alternatives for training the SR model: i) training with non-plant-root images, ii) training with plant-root images, and iii) pretraining the model with non-plant-root images and fine-tuning with plant-root images. We demonstrate on a collection of publicly available datasets that the SR models outperform the basic bicubic interpolation even when trained with non-root datasets. Also, our segmentation experiments show that high performance on this task can be achieved independently of the SNR. Therefore, we conclude that the quality of the image enhancement depends on the application.