Progress in Computing Applications Ali Samei, Alireza Tvakoli Talrghi, Mohammad Mahdi Dehshibi 4 2 2015 http://www.dline.info/pca/fulltext/v4n2/v4n2_3.pdf This paper presents an automatic document processing system for the extraction of data which are illustrated in medical laboratory results printed on a paper. The final goal of the research is to make the collection of medical data automatic and to enable an efficient management and description of the information in a way that a patient or a senior medicine student can understand the document just like an expert physician. In order to reach the mentioned goals, following the forthcoming steps was necessary in the proposed method. (i) Image pre-preprocessing, (ii) layout analysis for the identification of the tables’ data contained in the document’ (iii) extraction and classification of the laboratory results using template matching and HoG features in combination with a Support Vector Machine (SVM). Providing information for the application user need to constructing a knowledge base in which the relevant information of Wikipedia is used. The proposed approach has been tested on several document formats and performance analysis shows its superiority as well as simplicity.