Combination of multiple classifiers for automatic recognition of diseases and damages on plant leaves
- PDF / 1,301,410 Bytes
- 8 Pages / 595.276 x 790.866 pts Page_size
- 88 Downloads / 199 Views
ORIGINAL PAPER
Combination of multiple classifiers for automatic recognition of diseases and damages on plant leaves Ismail El Massi1
· Youssef Es-saady1 · Mostafa El Yassa1 · Driss Mammass1
Received: 4 June 2018 / Revised: 30 September 2020 / Accepted: 3 October 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract In this paper, we present an automatic recognition system of diseases and damages on plant leaves. The proposed system is based on classifiers combination technique, in which we have two variants of combination: serial combination of two classifiers, and hybrid combination of three classifiers including a serial combination of two classifiers in parallel with an individual classifier. Three types of features are adopted including color, texture and shape. The tests of this study to evaluate the three variants of combination are carried out on a database of 600 images of six classes (Leaf miners, Tuta absoluta and Thrips, Early blight, Late blight and powdery mildew). The comparison of results between the two methods serial and hybrid of the proposed system indicates that significant performances were obtained by applying the hybrid method for the recognition of diseases and damages on plant leaves. Keywords Combination of classifiers · Identification · Plant leaves · Diseases · Damages · Image
1 Introduction The agricultural sector in Morocco plays an important socioeconomic role. Basically, thanks to greenhouse cultivation, Morocco has experienced in recent years a significant increase in production of vegetables (especially tomatoes) to conquer several international markets. All of this has pushed the exporting producers to better develop the agricultural sector to make it more strategic in the national economy. Despite this rigorous vigilance from producers, the agriculture in Morocco suffers from several problems, in which major of them include pest damage (insects and mites) and symptoms of parasitic diseases (fungi, bacteria, viruses, etc.) that have a significant impact on the profitability of the farm business [1]. The protection against these diseases is a challenge for the producers both in terms of cost and their management. The methods currently used for diagnosis of plant diseases/damages include the eye observation of the agricultural expert and technicians. However, these methods are not totally satisfied to obtain an efficient diagnosis of plant diseases. For this purpose, the use of new technologies
B 1
Ismail El Massi [email protected] IRF-SIC Laboratory, Ibn Zohr University, B.P. 80000, Agadir, Morocco
of computer science, especially the computer vision (image processing and pattern recognition), allow proposing an automatic system to help in diagnosis phase [2]. The goal of our research is to propose a machine vision system in order to help the farms of our region Souss-Massa (located in the south of Morocco) in the identification of plant diseases. In recent years, several approaches have been proposed in the literature concerning the recognition o
Data Loading...
