Difference between revisions of "Known OCR, ML, NLP Issues"

From iDigBio
Jump to: navigation, search
m (Created page with "=== Specific Issues Needing Work === *how to get OCR to ignore a map (reduce OCR confusion) * <pre>...</pre> and <pre>___ </pre>present a challenge and confuse OCR and parsing. *...")
 
m (Specific Issues Needing Work)
Line 1: Line 1:
 
=== Specific Issues Needing Work ===
 
=== Specific Issues Needing Work ===
*how to get OCR to ignore a map (reduce OCR confusion)
+
:::how to get OCR to ignore a map (reduce OCR confusion)
* <pre>...</pre> and <pre>___ </pre>present a challenge and confuse OCR and parsing.
+
:::... and ___ present a challenge and confuse OCR and parsing.
* figure out an algorithm that would separate images into sets with no handwriting, little handwriting (mostly text typed or printed), lots of handwriting
+
:::figure out an algorithm that would separate images into sets with no handwriting, little handwriting (mostly text typed or printed), lots of handwriting

Revision as of 22:38, 10 January 2013

Specific Issues Needing Work

how to get OCR to ignore a map (reduce OCR confusion)
... and ___ present a challenge and confuse OCR and parsing.
figure out an algorithm that would separate images into sets with no handwriting, little handwriting (mostly text typed or printed), lots of handwriting