Touching component segmentation for Arabic manuscript recognition

Abstract EN

This Segmentation of manuscripts into text-lines and words is an important step to make recognition systems more efficient and accurate.

One of the problems making this task crucial is the presence of touching components which are connections between characters of successive text-lines, words of the same text-line or characters of a word.

This work proposes an automatic system for Arabic manuscript recognition.

The proposed system is based on a stochastic model of type HMM (Hidden Markov Model).

First, it segments the manuscript into text-lines and words while solving the touching component problem using the shape context descriptor.

Then, it extracts some structural features from word images and trains a Markovian classifier to recognize them.

The performance of the proposed system is assessed using samples extracted from historical handwritten documents.

The obtained results are encouraging.

We achieved an average rate of recognition of 87%.