A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit <a rel="external noopener" href="http://thescipub.com/PDF/ajassp.2007.857.864.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
<i title="Science Publications">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/myyqjkgwizb57p75zpb2nhqvpe" style="color: black;">American Journal of Applied Sciences</a>
Despite of the decent development of the pattern recognition science applications in the last decade of the twentieth century and this century, text recognition remains one of the most important problems in pattern recognition. To the best of our knowledge, little work has been done in the area of Arabic text recognition compared with those for Latin, Chins and Japanese text. The main difficulty encountered when dealing with Arabic text is the cursive nature of Arabic writing in both printed<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3844/ajassp.2007.857.864">doi:10.3844/ajassp.2007.857.864</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pjtztapn2rgf5aakgxggdfiyvq">fatcat:pjtztapn2rgf5aakgxggdfiyvq</a> </span>
more »... handwritten forms. An Automatic Arabic Hand-Written Text Recognition (AHTR) System is proposed. An efficient segmentation stage is required in order to divide a cursive word or sub-word into its constituting characters. After a word has been extracted from the scanned image, it is thinned and its base line is calculated by analysis of horizontal density histogram. The pattern is then followed through the base line and the segmentation points are detected. Thus after the segmentation stage, the cursive word is represented by a sequence of isolated characters. The recognition problem thus reduces to that of classifying each character. A set of features extracted from each individual characters. A minimum distance classifier is used. Some approaches are used for processing the characters and post processing added to enhance the results. Recognized characters will be appended directly to a word file which is editable form.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170814200441/http://thescipub.com/PDF/ajassp.2007.857.864.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3e/4a/3e4a4010c89311ad4726dd5eabadce05063eb34a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3844/ajassp.2007.857.864"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>