Digital documents present knowledge in most areas of study, exchanging and communicating information in a portable way. These digital repositories help in providing efficient retrieval of the stored data thus making it an important tool. Systematic extraction of data from digital document helps in mitigating the tedious work of manual data entry and facilitates effective analysis of generated structured data. The proposed system aims to extract a student's final result from the digital copy of the result sheet (PDF file) and then storing it in a centralized database which reduces the tiresome manual work needed to store records of each and every student. It provides a novel method of detecting text which is organized in tabular format and retaining the structural information after text recognition with good accuracy