Detecting and Measuring Fine Roots in Minirhizotron Images Using Matched Filtering and Local Entropy Thresholding

Abstract

An approach to automate the extraction and measurement of roots in minirhizotron images is presented. Two-dimensional matched filtering is followed by local entropy thresholding to produce binarized images from which roots are detected. After applying a root classifier to discriminate fine roots from unwanted background objects, a root labeling method is implemented to identify each root in the image. Once a root is detected, its length and diameter are measured using Dijkstra’s algorithm for obtaining the central curve and the Kimura–Kikuchi–Yamasaki method for measuring the length of the digitized path. Experimental results from a collection of peach (Prunus persica) root images demonstrate the effectiveness of the approach.