Pixel and object-based classification methods have been used for the determination of land cover. Pixel based classification methods suffer from salt and pepper effect. So pixel based classification methods cannot reach the accuracy of the object based classification. In order to eliminate the salt and pepper effect on the remote sensing classification accuracy and improve the result maps created as a result of the classification and further improve the classification accuracy in pixel based classification, it is recommended that the sieve class, clump class and majority analyses -which are ordinarily applied to high resolution images in this study by using the pixel based classification method. So the effect of these analyzes on low and medium resolution satellite images are unknown. With the SPOT 5 satellite image, this study will investigate how much this analysis affects the accuracy of classification. The classification includes the following categories: sun flowers, corns, peanuts, trees, roads, residential areas and water resources. In this study, the object based classification method was compared with three pixel based classification methods, namely the support vector machines, maximum likelihood method and spectral angle mapper method. The following general accuracy and kappa values were obtained from the methods in question: Object based classification method (96% accuracy, kappa value of 0,949), maximum likelihood method (90.99% accuracy, kappa value of 0,67), support vector machines (92.06 accuracy, kappa value of 0.70), spectral angle mapper method (93.88% accuracy, kappa value of 0,78). Following the pixel based classification process, the total accuracy and kappa values of the classified image was improved through the application of sieve class, clump class and majority analyses. As a result of the analyses conducted on the pixel based classification methods, the following general accuracy and kappa values were obtained for the following pixel based classification methods: maximum likelihood method (92.91% accuracy, kappa value of 0,73), support vector machines (93.13% accuracy, kappa value of 0.74) and spectral angle mapper method (95.62% accuracy, kappa value of 0,88). As a result of the analyses applied to the pixel based classification method, the classification accuracy produced similar results to that of the object based classification accuracy. To the best knowledge our author this is the first study dealing with this study area. So the authors think that this paper present a different point of view for interested researchers in this study area.