Trainable multiscript orientation detection

Abstract

Detecting the correct orientation of document images is an important step in large scale digitization processes, as mostsubsequent document analysis and optical character recognition methods assume upright position of the document page.Many methods have been proposed to solve the problem, most of which base on ascender to descender ratio computation.Unfortunately, this cannot be used for scripts having no descenders nor ascenders. Therefore, we present a trainablemethod using character similarity to compute the correct orientation. A connected component based distance measure iscomputed to compare the characters of the document image to characters whose orientation is known. This allows to detectthe orientation for which the distance is lowest as the correct orientation. Training is easily achieved by exchanging thereference characters by characters of the script to be analyzed. Evaluation of the proposed approach showed accuracy ofabove 99% for Latin and Japanese script from the public UW-III and UW-II datasets. An accuracy of 98.9% was obtainedfor Fraktur on a non-public dataset. Comparison of the proposed method to two methods using ascender / descender ratiobased orientation detection shows a significant improvement.