In this thesis, the quasi-supervised statistical learning algorithm has been applied for texture recognitioning analysis. The main objective of the proposed method is to detect man-made objects or differences on the terrain as a result of habitating. From this point of view, gaining information about human presence in a region of interest using aerial imagery is of vital importance. This task is adressed using a machine learning paradigm in a quasi-supervised learning. Eigthteen different sized aerial images were used in all computations and analysis. The available data was divided into a reference control set which consist of normalcy condition samples with no human presence, and a mixed testing data set which consisting images of habitate and cultivated terrain. Grey level co-occurrence matrices were then computed for each block and .Haralick Features. were extracted and organized into a texture vector. The quasi-supervised learning was then applied to the collection of texture vectors to identify those image blocks which show human presence in the test data set. In the performance evaluatian part, detected abnormal areas were compared with manually labeled data to determine the corresponding reciever operating characteristic curve. The results showed that the quasi-supervised learning algorithm is able to identify the indicators of human presence in a region such as houses, roads and objects that are not likely to be observed in areas free from human habitation.