An image processing apparatus is provided. The apparatus includes: a processor configured to process an image according to a preset process in response to receiving the image; and a controller configured to control the processor in order to detect a figure of a human within a video frame based on a feature vector data value according to histograms of oriented gradients (HOG) algorithm of the video frame of the image input to the processor, wherein the controller divides the video frame into a foreground corresponding to a region which includes a moving object and a background corresponding to a region which excludes the foreground, removes the background, converts a target region having a preset area including at least a part of the foreground without the background into a binary image, and derives the feature vector data value from the binary image using a lookup table.