Super resolution for root imaging
| Autor: | Alina Zare, José Francisco Ruiz-Muñoz, Jyothier K. Nimmagadda, James E. Baciak, Tyler G. Dowd |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
0106 biological sciences 0301 basic medicine Application Article Boosting (machine learning) root phenotyping Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Plant Science Biology super resolution Quantitative Biology - Quantitative Methods 010603 evolutionary biology 01 natural sciences Convolutional neural network 03 medical and health sciences plant phenotyping lcsh:Botany convolutional neural networks Preprocessor Segmentation Application Articles lcsh:QH301-705.5 Quantitative Methods (q-bio.QM) Ecology Evolution Behavior and Systematics Data collection Invited Special Article business.industry Deep learning For the Special Issue: Machine Learning in Plant Biology: From Genomics to Field Studies Pattern recognition lcsh:QK1-989 Data set 030104 developmental biology lcsh:Biology (General) FOS: Biological sciences Bicubic interpolation Artificial intelligence generative adversarial networks business |
| Zdroj: | Applications in Plant Sciences, Vol 8, Iss 7, Pp n/a-n/a (2020) Applications in Plant Sciences |
| ISSN: | 2168-0450 |
| Popis: | 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. Under review. Submitted to Applications in Plant Sciences (APPS) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |