Towards A Distributed Arabic OCR Based on the DTW Algorithm: Performance Analysis

In spite of the diversity of printed Arabic optical character recognition products and proposals, the problem seemsto be not yet well solved. The complex morphology and calligraphy of the Arabic writing on one hand and the use of some lightapproaches on the other hand are behind the poorness of these products. However, some strong proposed approaches didn’tfind the opportunity to be commercialised because of generally their corresponding complex computing. The dynamic timewarping algorithm is considered as one among these strong approaches. In fact, several studies and experiments have shownand confirmed that the printed Arabic optical character recognition based on dynamic time warping algorithm provides a veryinteresting recognition rate especially for large and huge vocabularies. One of the attractive sides of the dynamic timewarping algorithm is its ability to recognize properly connected or cursive characters (words or sub words) without priorsegmentation. Furthermore, this algorithm performs the recognition process from within a reference library of isolatedcharacters and owns a very good immunity against noises. Unfortunately, the big amount of its computing during therecognition process makes its execution time very slow and, hence, restricts its utilization. Many researchers attempted tospeedup the execution time of this algorithm. Unfortunately, the corresponding proposed solutions require generally specifichigh cost architectures. Loosely coupled architectures such as grapes or grid computing can provide enough power withoutadditional cost to distribute the complexity of some greedy applications. Consequently, we report in this paper theperformance analysis of an analytical and an experimental study of a distributed Arabic optical character recognition basedon the dynamic time warping algorithm within loosely coupled architectures. Obtained results confirm that loosely coupledarchitectures and more specifically grid computing present a very interesting framework to speedup the Arabic opticalcharacter recognition based on the dynamic time warping algorithm