Hierarchical Recognition of Mixed Documents Consisting of the Korean/Alphanumeric Texts and Graphic Images

mCT In this paper, we propose an efficient algorithm which recognizes the mixed document consisting of the Korean/alphanumeric texts and graphic images. In the preprocessing step. we separate graphic image parts from the text parts by considering chain codes of cmected components. In the recognition step of the Korean/alphanumeric characters. we recognize the characters hierarchically using several features such as end points. branch points, cross points. partial projections. and distance features. Computer simulation shows that the proposed algorithm recognizes the mixed document effectively.