AVALIAÇÃO DE COMPRIMENTO E DIÂMETRO RADICULAR DO MILHO POR TÉCNICAS DE PROCESSAMENTO DIGITAL DE IMAGENS

Abstract

The study of roots is used to monitor and optimize the uptake of water and nutrients. The evaluation of the plant root system by traditional methods is slow, exhaustive, complex and in many cases does not provide the required accuracy. This research aimed to develop a computational method to assist in the assessing of the average diameter and length of root maize. It was developed using Java programming language, JavaCV interface, and OpenCV library, subsequently its accuracy was compared to the traditional methods and the macro IJ_Rhizo accuracy, for measuring the average diameter and length of roots. The tests were performed using images of maize roots with 300 dpi and using images of nylon threads with resolutions of 300 dpi and 600 dpi. The method validation was performed using nylon thread samples with known lengths and diameters. For length measurements, the proposed method obtained coefficients of variation from 0.05% to 3.80% and 0.06% to 9,27%, with 300 dpi and 600 dpi images, respectively. For diameter measurements, the proposed method obtained coefficients of variation from 0.23% to 77.49% and 0.54% to 96,61%, with 300 dpi and 600 dpi images, respectively. The proposed method obtained coefficients of variation lower than traditional methods for length and diameter measurements, and the macro IJ_Rhizo in more than 95% of test cases. Thus, the presented method is shown to be the most appropriate, and with greater accuracy for measurement of average diameter and length of root, among the assessed methods.