LeMuR: Plant Root Phenotyping via Learned Multi-resolution Image Segmentation
Current root image analysis tools are extremely brittle. Each is custom-built to suit the image acquisition and experimental methods of a given laboratory. Translating a tool to even a slightly different environment or problem often requires a significant portion of the software to be re-written. LeMuR will exploit the common structure of root image analysis tasks and recent advances in deep machine learning to produce a flexible plant root phenotyping tool that can be easily adapted, without re-writing code, to new laboratory and imaging techniques.
LeMuRoot will bring together i) a novel, learned multi-resolution root image segmentation method based on a convolutional neural net, ii) optimal path finding to identify the root skeleton, and iii) RSML format description of root architectures. LeMuRoot will be broadly applicable to any common 2D, image-based, root system architecture phenotyping task, subsuming previous tools. When necessary, users will adapt the tool to their own experiment by further training of the convolutional net, a process that will not require specialist knowledge. Training will be conducted via the LeMuRLearn learning framework, which will both allow biologist users to produce their own training data and automatically update the network.