Computer-Aided Information Retrieval and Management System from Scientific Documents

This dissertation proposes and develops a data retrieval system for chemistry, the system consists of (1) ChemScanner a software library that can be used for the extraction of chemical information from scientific documents that contain ChemDraw sketches, (2) the ChemScanner User Interface visualizes sketches and provides an interface for data management, and (3) the integration of the ChemScanner library into the Open-source Electronic Lab Notebook, which would make the software easier to use via the web application user interface, and a better management mechanism for the information retrieval system. The research project contributes to the development of chemical databases, facilitates and accelerate users in building chemical datasets from accessible documents.