Seybold Report ISSN: 1533-9211
Greeshma O S1, Dr. P Sasikala2, Dr. S G Balakrishnan3
1Assistant Professor, Department of Computer Science, Sree Sankara Vidyapeetom College, Nagaroor.
2Professor & Head, Department of Mathematics,VMKV Engineering College, Salem.
3Associate Professor, Department of CSE, Mahendra Engineering College, Namakkal.
Corresponding Author Email: osgreeshma@gmail.com
Vol 17, No 10 ( 2022 ) | Licensing: CC 4.0 | Pg no:2245-2252 | Published on: 31-10-2022
Abstract
Multiple microbes can alter a plant's development and agricultural productivity, which has significant implications for the ecosystem and human life. As a result, timely identification, prevention, and prompt treatment are required. Fundamental methods have some drawbacks to plant disease identification like more time-consuming, accuracy, doesn't support multiple plant detection. This paper introduces a hybrid model that uses a random forest classifier combined with the AdaBoost Classifier to classify plant diseases to overcome the above-said drawbacks. So as to individualize normal and abnormal leaves from data sets, the suggested methodology employs the Random Forest with AdaBoost algorithm. The operational processes in our suggested study are preprocessing, segmentation, feature extraction, training the classifier, and classification. The produced datasets of infected and uninfected leaves are combined and processed using the Random Forest classifier to categorize the infected and uninfected photos. Color Histogram is used to gather features from imagery. KNN, Naive Bayes, and SVM are all used to evaluate our suggested technique.
Keywords:
: Random forest, Color histogram, Classification, Feature extraction.