Automatic Table Recognition and Extraction from Heterogeneous Documents  

作　　者：Florence Folake Babatunde Bolanle Adefowoke Ojokoh Samuel Adebayo Oluwadare 

机构地区：[1]Department of Computer Science, Osun State College of Education, Ila-Orangun, Nigeria [2]Department of Computer Science, Federal University of Technology, Akure, Nigeria

出　　处：《Journal of Computer and Communications》2015年第12期100-110,共11页电脑和通信（英文）

摘　　要：This paper examines automatic recognition and extraction of tables from a large collection of het-erogeneous documents. The heterogeneous documents are initially pre-processed and converted to HTML codes, after which an algorithm recognises the table portion of the documents. Hidden Markov Model (HMM) is then applied to the HTML code in order to extract the tables. The model was trained and tested with five hundred and twenty six self-generated tables (three hundred and twenty-one (321) tables for training and two hundred and five (205) tables for testing). Viterbi algorithm was implemented for the testing part. The system was evaluated in terms of accuracy, precision, recall and f-measure. The overall evaluation results show 88.8% accuracy, 96.8% precision, 91.7% recall and 88.8% F-measure revealing that the method is good at solving the problem of table extraction.This paper examines automatic recognition and extraction of tables from a large collection of het-erogeneous documents. The heterogeneous documents are initially pre-processed and converted to HTML codes, after which an algorithm recognises the table portion of the documents. Hidden Markov Model (HMM) is then applied to the HTML code in order to extract the tables. The model was trained and tested with five hundred and twenty six self-generated tables (three hundred and twenty-one (321) tables for training and two hundred and five (205) tables for testing). Viterbi algorithm was implemented for the testing part. The system was evaluated in terms of accuracy, precision, recall and f-measure. The overall evaluation results show 88.8% accuracy, 96.8% precision, 91.7% recall and 88.8% F-measure revealing that the method is good at solving the problem of table extraction.

关 键 词：Hidden MARKOV Model Table Recognition and EXTRACTION HYPERTEXT MARKUP Language HETEROGENEOUS DOCUMENTS 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]