Automatically diagnosing leaf scorching and disease symptoms in trees/shrubs by using RGB image computation with a common statistical algorithm

•The knowledge on characteristics of plant is the key for better computation.•“Λ” and “V” type symptoms were automatically diagnosed by using RGB image computation.•The common statistical algorithms were used in the discrimination of the symptoms.•More than 80% sample cases were correctly classified with our developed program.

Better computation and auto-identification of plant and tree characteristics is usually based on the direct use of knowledge about them. With the background of our previous study about manual image measurement of leaf scorch symptoms, we try to automatically diagnose leaf scorching and the inward spread of leaf disease symptoms by using RGB image computation to increase the mechanical utilization and improve the identification efficiency in the future. The special characteristics of the symptoms made them easy to identify automatically. In the process of performing the computation, common statistical algorithms, such as quadratic functional regression and variance analysis, were used to obtain proper parameters for the final discrimination of the symptoms. By using our program, more than 80% of sample cases were correctly classified.