Line detection in binary document scans: A case study with the international tracing service archives

In this short paper, I present my in-progress work on a method of line detection in binary document scans that is capable of differentiating solid and dotted lines. This method entails post-processing candidate lines detected using the progressive probabilistic Hough line transform by filtering out false positives. Solid lines are identified by performing a cut on the average pixel value of the pixels along each candidate line, and dotted lines are identified by performing a cut on the dominant frequency of the Fast Fourier Transform of the same pixel values along each candidate line. I demonstrate the efficacy of this method by running this algorithm on a subset of binary TIF images from the International Tracing Service digitized archives, one of the world's largest collections of Holocaust-related documents. In the case of the International Tracing Service archive, classifying documents based on line structure provides an effective method of extracting information from the documents in an automated fashion, an otherwise intractable endeavor due to low scan quality and the prevalence of handwritten text throughout the archive. My proposed method of identifying line structure represents the first step in this proposed pipeline of classifying International Tracing Service documents by line structure.