Beruflich Dokumente
Kultur Dokumente
Prénom Nom
Outline
Objectives
Typology
Processing chain
Methodology
Character recognition
Word recognition
An OCR experiment
Conclusion
Variability in style
single scriber, omni-scriber
mono-font, multi-font, omni-font
Geometrical variability
in size
in orientation (rotated)
in transformations (slanted, perspective view, ...)
Image resolution
binary images, starting at 200 dpi
grey-level images starting at 150 dpi
Image quality
degraded support (historical documents)
acquisition conditions (bad illumination, optical aberration,
noise, ...)
10
line segmentation
word segmentation
character segmentation
normalization normalization
identification identification
post-analysis
recognized word
11
Performance depends on
size of alphabet (number of classes)
image quality
12
13
14
Hamming distance
Warping distance
15
16
µ pq = ∑x ∑y ( x − x) p ( y − y) q f ( x, y)
m10 m01
with x= y= mpq = ∑x ∑y x p y q f ( x, y)
m00 m00
17
19
20
21
shape similarity ("0" and "O", "1", "I" and "l", "5" and "S", ...)
small shapes : punctuation, accents, superscripts ("er", "ème")
special characters ("©", "½", "±", ...) or bullets
22
23
24
25
= ∑π
q1 ,... qT
q bq1 (o1 )aq1q2 bq2 (o2 ) ... aqT −1qT bqT (oT )
26
27
28
29
30
31
32