Evaluation of pixel-based and object-oriented classification methods in preparing land cover maps using Landsat satellite images in Idrisi Terrset software (Case study: Doviraj region of Ilam Province)
Volume 7, Issue 1, Spring 2026, Pages 209-223
Saleh Arekhi
Abstract Background and Objective: In recent years, the preparation of land cover maps through digital classification of remote sensing data has been considered as a suitable alternative for the preparation of this type of maps. Remote sensing is one of the new and efficient technologies in extracting land cover, updating maps, and detecting land cover changes. In this dirction, the aim of present study is to compare two methods of pixel-based and object-oriented classification in land cover mapping with using OLI image in Doviraj region, Ilam province using Idrisi Teerrset software.
Research Method: After the supply of related image and implementing geometric and radiometric corrections on image, we applied two classification methods to land cover mapping. To assess the accuracy of classification methods, we used of indices of overall accuracy, kappa coefficient, producer accuracy and user accuracy. The results show that the object-oriented classification method has more resolution than the pixel-based classification method.
Findings and Conclusion: The results of accuracy show that method of object-oriented in two indices of overall accuracy and kappa coefficient with (respectively) 94 percent and 0/93 percent was more accuracy then to pixel-based classification method with overall and Kappa coefficient 88 percent and 0/87 percent. The result of this study suggests that from object-oriented classification method use to production of land ucover map.
