An approximation based algorithm for minimum bounding rectangle computation

Shape extraction and analysis is one of the most important task in image processing. The accuracy of the shape features extraction process increases the object recognition rate. Minimum Bounding Rectangle (MBR) is a tool that contributes to the increase of the accuracy of the shape features extraction, particularly it can be used to determine the real aspect ratio. This paper focuses on the improvement of the existing method. This is focused around the determination of the MBR's edges points, using a series of approximations. The proposed method gives more accurate MBR in all the tested situations. In order to demonstrate the accuracy of the proposed method, an experiment is setup based on the comparison of the manually drawn MBR and the ones generated by each of the methods. Results achieved showed that the proposed method outperforms existing method as it consistently produced results closest to the manually drawn MBR.