Plant phenotyping concerns the study of plant traits resulted from their interaction with their environment. Computer vision (CV) techniques represent promising, non-invasive approaches for leaf segmentation, leaf counting, and tracking plant growth. This paper discusses an interesting aspect of the recent best-performing deep learning works: the fact that main contribution comes from novel data augmentation  techniques. Experiments are set to highlight the significance of data augmentation practices for limited data sets with narrow  distributions. This paper reviews the ingenious techniques to generate synthetic data to augment training and performs experiments to attest of their potential importance.
Original languageEnglish
Title of host publicationIEEE Explore
Number of pages8
Publication statusE-pub ahead of print - 20 Sep 2020
Event2020 Digital Image Computing: Techniques and Applications: DICTA 2020 - Virtual, Australia
Duration: 30 Nov 202002 Dec 2020


Conference2020 Digital Image Computing: Techniques and Applications
OtherThe International Conference on Digital Image Computing: Techniques and Applications (DICTA) is the flagship Australian Conference on computer vision, image processing, pattern recognition, and related areas.
Internet address


Dive into the research topics of 'Recent data augmentation strategies for deep learning in plant phenotyping and their significance'. Together they form a unique fingerprint.

Cite this