Overlapped-character separation and reconstruction for table-form documents

In this paper, we detect the character strokes overlapped by table lines and then reconstruct the broken strokes after character/line separation. The work is a part of our proposed table-form document analysis system. Tracking models are firstly defined according to the skew angle of a table form to find overlapped strokes. Cut-points are found and paired using a 3×3 mask along tracking models. Each cut-point pair indicates a broken stroke. The direction of a broken stroke is detected using several decision rules. Finally, broken strokes are connected after character/line separation by means of stroke directions and cut-point pairs of the broken strokes. Several experiments are tested to evaluate the performance of the proposed method.