A novel algorithm for semi-automatic segmentation of plant leaf disease symptoms using digital image processing

Abstract

A new computer algorithm is proposed to differentiate signs and symptoms of plant disease from asymptomatic tissues in plant leaves. The simple algorithm manipulates the histograms of the H (from HSV color space) and a (from the L*a*b* color space) color channels. All steps in the algorithmic process are automatic, with the exception of the final step in which the user decides which channel (H or a) provides the better differentiation. An in-depth analysis of the problem of disease symptom differentiation is also presented, in which issues such as lesion delimitation, illumination, leaf venation interference, leaf ruggedness, among others, are thoroughly discussed. The proposed algorithm was tested under a wide variety of conditions, which included 19 plant species, 82 diseases, and images gathered under controlled and uncontrolled environmental conditions. The algorithm proved useful for a wide variety of plant diseases and conditions, although some situations may require alternative solutions.