Shape descriptor extracting method

A method of extracting a shape descriptor, which describes shape features of an image, from an image is provided. The shape extracting method includes (a) extracting a skeleton from an input image, (b) obtaining a first list of straight lines by connecting pixels based on the extracted skeleton, and (c) determining a second list of straight lines obtained by normalizing the first list of straight lines as a shape descriptor. A shape descriptor so extracted possesses information relating to a shape included in an image. Therefore, the shape descriptor extracting method can be used to effectively extract local motion in a data collection of the same category, and the number of extracted shapes is not limited to the number of objects.