Root Image Processing

Dr Jinhai Cai, Dr Josh Chopin, Professor Stan Miklavcic

PBRC Research RootsPhenotyping of plant root growth by image processing and analysis of plant root images. In this research automated algorithms for localization and identification of root features in image sequences of different cereal plants are being developed. The plant roots are grown in a transparent gellan gum medium and imaged daily at different rotation angles. Feature extraction and feature selection techniques are employed to extract phenotyping features in root images.  Features are matched and tracked across spatially separated images to extract 3D information of the phenotyping feature. Furthermore, a time series of these 3D features are obtained by temporal tracking. The project will involve the development of:

  • Feature extraction algorithms for plant root images
  • Feature selection and classification algorithms
  • Data fusion
  • Correspondence matching within root images
  • Tracking algorithms


J. Cai, Z. Zeng, J.N. Connor, C.Y. Huang, V. Melino, P. Kumar, S.J. Miklavcic (2015) RootGraph: A graphic optimization tool for automated image analysis of plant roots, Journal of Experimental Botany, online, p1-12.

J. Chopin, H. Laga, C.Y. Huang, S. Heuer, S.J. Miklavcic (2015) RootAnalyzer: a cross-section image analysis tool for automated characterization of root cells and tissues, PLOS One (doi: 10.1371/journal.pone.0137655).

P. Kumar, S.J. Miklavcic, Integrated self-calibration of single axis motion for three-dimensional reconstruction of roots, IET Computer Vision.

P. Kumar, J. Cai, S.J. Miklavcic  A complete system for 3D reconstruction of roots for phenotypic analysis , Signal and Image Analysis for Biomedical and Life Sciences, Book Series: Advances in Experimental Medicine and Biology, Editors: C. Sun, T. Bednarz, T.D. Pham, P. Vallotton, and D. Wang, Springer.

Areas of study and research

+ Click to minimise