What is the current state-of-the art within document layout analysis?

I.e. detecting columns, separating images from text, distinguishing between page numbering and text and so on.

I am looking for papers and algorithms on the topic.

  • $\begingroup$ have you find some implementation of the paper that won the competition? I'm working on that but seems not working $\endgroup$ Commented Nov 6, 2017 at 15:54

2 Answers 2


After some research, I came across ICDAR (International Conference on Document Analysis and Recognition), which is taking place biannually and seems to be the most complete and up-to-date source for state-of-the-art document analysis algorithms.

ICDAR is hosting a competition in different subfields each year. At the time of this writing, the latest results from ICDAR 2015 have been published as Competition on Recognition of Documents with Complex Layouts – RDCL2015. (Search online for a PDF version.) This paper describes state-of-the-art document layout analysis algorithms, and compares their performance to both open-source and commercial solutions.


see also the paper LAREX – A semi-automatic open-source Tool for Layout Analysis and Region Extraction on Early Printed Books and the accompanying open-source solution OCR4all:

A semi-automatic open-source tool for layout analysis on early printed books is presented. LAREX uses a rule based connected components approach which is very fast, easily comprehensible for the user and allows an intuitive manual correction if necessary. The PageXML format is used to support integration into existing OCR workflows. Evaluations showed that LAREX provides an efficient and flexible way to segment pages of early printed books.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.