Land use and land cover maps are required for various purposes in scientific, administrative and commercial domains. Such maps can be efficiently derived by supervised classification. As the spatial resolution of remotely sensed images increased, geographic object based analysis (GEOBIA) approaches became more suitable concerning the demand for faster and more accurate classification. Multi-class supervised classification requires the collection of reference samples of all available classes in the study area, which is a costly and time consuming process. However in many case users may only be interested in a specific land class such as extracting urban areas, detection of cars, or retrieving trees. This could be referred to as a one-class classification problem, which allows for the learning of a classification model from labeled reference data for the class of interest only. In this case there is no need for a representative dataset for the counter-class which consists of all other classes. One common solution to deal with one-class classification problem is based on One-class SVM. This method has proved useful in document classification, texture segmentation, and image retrieval. Moreover, deep learning through convolutional neural networks (CNN) has been intensively used in remote sensing field. CNNs are now commonly used for land cover/land use classification and semantic labeling tasks in large image archives while achieving the state-of-the-art performances In this study, we propose to extract examples of classes of interest from high spatial resolution images by integrating one-class Support Vector Machines (SVMs), Deep features from pre-trained CNN and object-based image analysis approach. We also compared the performance from the proposed method with the supervised multi-class classification. The results indicate that the proposed method achieve similar performances the multi-class method, and could be a promising way to provide relatively quick and efficient way in extracting a specific land class from high spatial resolution images.