The impact of the image processing in the indexation system

Abstract

This paper presents an efficient word spotting system applied to handwritten Arabic documents, where images are represented with bag-of-visual-SIFT descriptors and a sliding window approach is used to locate the regions that are most similar to the query by following the query-by-example paragon. First, a pre-processing step is used to produce a better representation of the most informative features. Secondly, a region-based framework is deployed to represent each local region by a bag-of-visual-SIFT descriptors. Afterward, some experiments are in order to demonstrate the codebook size influence on the efficiency of the system, by analyzing the curse of dimensionality curve. In the end, to measure the similarity score, a floating distance based on the descriptor’s number for each query is adopted. The experimental results prove the efficiency of the proposed processing steps in the word spotting system.

Diacritic segmentation technique for arabic handwritten using region-based

“…All these words have same writing style, but they differ in terms of diacritical marks, if one of these words got any missed placed diacritics mark definitely the whole meaning will turn out which will increase the ambiguousness of the word. This is the main challenges in Arabic handwritten document how to recognize the meaning of the word when there is no diacritics placed in the word, it will be ambiguous and hard to recognize for non-natives Arabs and as well as it could affect the originality of document of Arabic language that contains many diacritics marks [18], if any missing or missed placed diacritics it will affect its holiness and as well as its originality. However, in this research the segmentation process will be used to prepare image for extraction process.…”