Parallel Line Detection Algorithm Based on HMM Decoding

摘要

The detection of groups of parallel lines is important in applications such as form processing and text (handwriting) extraction in rule lined paper. These tasks can be very challenging in degraded documents where the lines are severely broken. In this paper we propose a novel model-based method which incorporates high level context to detect these lines. After preprocessing and skew correction, we used trained Hidden Markov Models (HMM) to locate the optimal positions of all lines simultaneously, based on the Viterbi decoding. The algorithm is trainable, therefore, it can easily be adapted to different application scenarios. The experiments conducted on known form processing and rule detection show our method is robust, and achieved better results than other widely used line detection methods, such as the Hough transform, projection or vectorization-based methods.