Insights to the State-of-the-Art PDF Extraction Techniques

Digitized documents have become the omnipresent medium of information. A plethora of scholarly documents on the web is excessively being increased. Various digital libraries such as Google scholar, Citeseer, MAS etc. store this plethora in different formats. Most of the scientific literature is stored in Portal Document Format (PDF). PDF documents hold a complex structure due to which their comprehension and extraction of useful information from them is a challenging task. In this regard, research community has been proposing different rule based and machine learning based techniques in the past several years. We believe that accurate and efficient information extraction form the PDF files is an important issue as major portion of scholarly literature is stored in PDF. This study presents a rigorous analysis of the contemporary state-of-the-art in PDF data extraction. The contemporary approaches from the window of past few years are recapitulated with the primary objective to assist the scientific community by providing them knowledge about current trend in PDF extraction techniques. The study also presents critical analysis and suggests future dimensions of some of the approaches.