DCO-DS Boundary Activity: Data Extraction from Tables and Plots in Scanned PDF Publications

Printer-friendly version

Presented at the DCO-EPC workshop 2014


Reusability of data is a point of major importance in scientific research. There are many occasions when we would like to reuse the data in the old publications in the 1960’s or even older. However, the data in those old publications are normally not ready for direct reuse as they are not in the machine readable formats yet. It is very common that the document formats used are not geared toward reusability. A particularly difficult format to reuse is the Portable Document Format (PDF) as it was never designed for this purpose. This DCO boundary activity focused on the task of retrieving data from tables and plots in the scanned pdf publications as efficiently and accurately as possible. Optical character recognition (OCR) is the key technique for this task. It refers to the process of extracting machine characters from input images (usually in the form of scanned documents). A variety of open source programs have been tested for different use cases. There are also some issues remained to be improved which have been listed below.


DateCreated ByLink
October 7, 2014
Xiaogang MaDownload
October 7, 2014
Xiaogang MaDownload
September 22, 2014
Congrui LiDownload

Related Projects:

DCO-DS LogoDeep Carbon Observatory Data Science (DCO-DS)
Principal Investigator: Peter Fox
Co Investigator: John S. Erickson and Jim Hendler
Description: Given this increasing data deluge, it is clear that each of the Directorates in the Deep Carbon Observatory face diverse data science and data management needs to fulfill both their decadal strategic objectives and their day-to-day tasks. This project will assess in detail the data science and data management needs for each DCO directorate and for the DCO as a whole, using a combination of informatics methods; use case development, requirements analysis, inventories and interviews.

Related Research Areas:

Data Frameworks
Lead Professor: Peter Fox
Description: None.
Data Science
Lead Professor: Peter Fox
Description: Science has fully entered a new mode of operation. Data science is advancing inductive conduct of science driven by the greater volumes, complexity and heterogeneity of data being made available over the Internet. Data science combines of aspects of data management, library science, computer science, and physical science using supporting cyberinfrastructure and information technology. As such it is changing the way all of these disciplines do both their individual and collaborative work.

Data science is helping scienists face new global problems of a magnitude, complexity and interdisciplinary nature whose progress is presently limited by lack of available tools and a fully trained and agile workforce.

At present, there is a lack formal training in the key cognitive and skill areas that would enable graduates to become key participants in escience collaborations. The need is to teach key methodologies in application areas based on real research experience and build a skill-set.

At the heart of this new way of doing science, especially experimental and observational science but also increasingly computational science, is the generation of data.

Lead Professor: Peter Fox
Description: In the last 2-3 years, Informatics has attained greater visibility across a broad range of disciplines, especially in light of great successes in bio- and biomedical-informatics and significant challenges in the explosion of data and information resources. Xinformatics is intended to provide both the common informatics knowledge as well as how it is implemented in specific disciplines, e.g. X=astro, geo, chem, etc. Informatics' theoretical basis arises from information science, cognitive science, social science, library science as well as computer science. As such, it aggregates these studies and adds both the practice of information processing, and the engineering of information systems.
Concepts: ,