Generic object detection in image using SIFT, GIST and SURF descriptors

This paper compares generic object detection method using three different feature extraction schemes. The query image could be of different types such as a real image or a hand-drawn sketch. The method operates using a single example of the target object. The feature descriptors emphasizes the edge parts and their distribution structures, so it is very robust and can deal with virtual images or hand-drawn sketches. The approach is extended to account for large variations in rotation. Good performance is demonstrated on several data sets, indicating that the object was successfully detected under different imaging conditions.