Document Image Analysis
abbreviation(s): DIA
definition: Document image analysis is the theory and practice of recovering the logical structure of digital images scanned from documents or produced by computer. It includes optical character recognition as one of its subfields, but has more ambitious tasks, both in the breadth (understand diagrams, music scores, images ...), and depth (e.g. the correct interpretation of a scanned mathematical formula).
See also the corresponding HLT Survey chapter: http://www.lt-world.org/hlt_survey/ltw-chapter2-2.pdf
related person(s):
- Henry S. Baird
relevant source(s):