Table Detection in Noisy Off-line Handwritten Documents

Table detection can be a valuable step in the analysis of unstructured documents. Although much work has been conducted in the domain of machine-print including books, scientific papers, etc., little has been done to address the case of handwritten inputs. In this paper, we study table detection in scanned handwritten documents subject to challenging artifacts and noise. First, we separate text components (machine-print, handwriting) from the rest of the page using an SVM classifier. We then employ a correlation-based approach to measure the coherence between adjacent text lines which may be part of the same table, solving the resulting page decomposition problem using dynamic programming. A report of preliminary results from ongoing experiments concludes the paper.