A Novel Preprocessing Method for Hectography Prints Based on Independent Component Analysis

Archives and cultural facilities consists of vast spectra of different document classes, many of which are not encountered today anymore. The digitization therefore calls for image enhancement and preprocessing solutions so far not required and hence unsolved. A prominent document class in this context is hectography, which was an inexpensive printing and duplication method, widely used throughout the 20th century. The major challenge with hectography is poor contrast on the one side and multiple degradation effects on the other side. In this paper a novel preprocessing method for hectography duplicates is proposed which leads to better Optical Character Recognition (OCR) results compared to traditional methods that operate on grayscale images. The proposed method is based on a linear mixing model used in independent component analysis. The problem of unwanted Gaussian noise components is considered as well.