Extracting Root System Architecture from X-ray Micro Computed Tomography Images

Speaker: Stefan Mairhofer

Abstract: X-ray micro Computed Tomography (µCT) allows non-destructive visualization of plant root systems within their soil environment and thus offers an alternative to other commonly used destructive methodologies for the examination of plant roots and their interaction with the surrounding soil. The recovery of root system architectures requires the segmentation of µCT data to identify root material. However, variations in the x-ray attenuation values of root material and the overlap in attenuation values between roots and soil caused by water and organic matter content represent major challenges to data recovery. We present a new method capable of separating root material from soil in µCT images, using a level-set approach and a model-guided search arising from the adoption of a visual-tracking framework.