A method and apparatus for detecting an object is provided. The method includes recognizing a predetermined object from at least one of an image and a video and determining a position of the recognized object, displaying on the image or the video a location of a predetermined part of the recognized object, rearranging the displayed location of the predetermined part of the recognized object based on an input signal, and renewing the position of the recognized object based on a result of the rearranging of the displayed location of the predetermined part of the recognized object.