Mechanism of Character Region Detection Using Structural Features of Hangul Vowels
Jong-Cheon Park · The Smart Computing Review · 2012
This paper proposes a method to detect the Hangul character region from natural images using the topological structural features of Hangul graphemes. First, I transform a natural image to a gray-scale image. Second, feature extraction is performed with the edge and connected component based method. The edge-based method uses a canny-edge detector and the connected component based method applies local range filtering. Next, if features are not corresponding to the heuristic rule of Hangul characters, extracted features are filtered out and selected candidates of the character region are identified. Next, candidates of the Hangul character region are merged into one Hangul character using a Hangul character merging algorithm. Finally, we detect the final character region by a Hangul character class decision algorithm. The experimental results show that the proposed method could detect character regions effectively in images that contain a complex background and various environments. As a result of the performance evaluation, the proposed method shows advanced results about the detection of Hangul character regions from a mobile image.