Classifier ensample for improvement land cover classification
March 06, 2022

Project Code:

0700/SR/SUR/2021


Field of Study :

Damietta Governorate

Accurate and timely collection of urban land use and land cover information is crucial for many aspects of urban development and environment protection. Accurate land covers classification is challenging. Improving land cover classification is a hot topic. It is needed for many applications such as land use land cover mapping environmental monitoring, natural resource management, urban planning, and management and change detection. The aim of this study is the development of classifier ensample using majority voting technique and investigating its performance compared with the performance of three base classifiers Naïve Bayes, support vector machine, K-nearest neighbor and Random Forest algorithm as a classifier ensample. Firstly, four base classifiers were selected and implemented, respectively. During the research procedure, the same labeled training and testing samples were used as inputs. Secondly, based on the output of the three base classifiers, the classification results by major voting (MV), was obtained. Finally, the performance of all classification methods was evaluated including base classifiers and MCS. Accuracy assessment was evaluated by the confusion matrix as well as the overall accuracy and Kappa index.


Principal Investigator

Lamiaa Taha


Team Work of Project

Lamiaa Taha, Rania Elsayed Ibrahim, Asmaa Mandoh, AbdelRahman Wahba, Mai Mahmod, Amany Samir, Moamen Adel, Wael Khedr

Division : Aviation and Aerial Photography

  • Share This: