A Method of Extracting Similar Figures Using Polar Features
Tomoharu Nagao, Takeshi Agui, Masayuki Nakajima · Systems and Computers in Japan · 1990
Abstract Recently, there has been active research on image recognition technology using computers. It is necessary for image recognition to extract some elements automatically, such as straight lines, circles, numerical letters and symbols from a picture. There are many cases where the extraction of such elements is not easy because some overlap others. This paper describes a method of extracting overlapped elements separately from a binary picture. The method can extract an element which has a constant shape with arbitrary size or rotation angle, or with both an arbitrary size and an arbitrary angle. Also, it uses both a single key point and several feature points on the model of a figure to be processed. The extraction is carried out by checking if there are several pixels corresponding to the feature points, when each pixel is regarded as a key point of the model. This paper describes the algorithm of the method, a method of extracting some important straight lines and circles in the picture using the algorithm, and experimental applications of the method to mechanical drawings. The results of the experiments demonstrate a successful extraction of straight lines, circles, arrows, and numerical letters, and this confirms the usefulness of the proposed method.