Seite - 141 - in Document Image Processing
Bild der Seite - 141 -
Text der Seite - 141 -
J. Imaging 2018,4, 15
16.5%
17.0%
17.5%
18.0%
18.5%
19.0%
19.5%
20.0%
20.5%
21.0%
21.5%
Word 3-gram LM Character 10-gram LM
Open voc.
Open voc. with val.
Closed voc.
Closed voc. with val.
Figure11.CERresultsobtainedbythebestword-basedHMMsystemandthebest character-based
HMMsystemwithopenandclosedvocabulary,withandwithoutusing thevalidationsamples for
trainingtheLM.
0%
5%
10%
15%
20%
25%
30%
35%
40%
45%
Word 3-gram LM Character 10-gram LM
Open voc.
Open voc. with val.
Closed voc.
Closed voc. with val.
Figure12.RecognitionaccuracyrateforOOVwordsbythebestword-basedHMMsystemandthebest
character-basedHMMsystemwithopenandclosedvocabulary,withandwithoutusing thevalidation
samples for trainingtheLM.
37%
38%
39%
40%
41%
42%
43%
44%
Word 3-gram LM Character 10-gram LM
Open voc.
Open voc. with val.
Closed voc.
Closed voc. with val.
Figure13.WERresultsobtainedbythebestword-basedHMMsystemandthebestcharacter-based
HMMsystemwithopenandclosedvocabulary,withandwithoutusing thevalidationsamples for
trainingtheLM.
141
zurück zum
Buch Document Image Processing"
Document Image Processing
- Titel
- Document Image Processing
- Autoren
- Ergina Kavallieratou
- Laurence Likforman-Sulem
- Herausgeber
- MDPI
- Ort
- Basel
- Datum
- 2018
- Sprache
- deutsch
- Lizenz
- CC BY-NC-ND 4.0
- ISBN
- 978-3-03897-106-1
- Abmessungen
- 17.0 x 24.4 cm
- Seiten
- 216
- Schlagwörter
- document image processing, preprocessing, binarizationl, text-line segmentation, handwriting recognition, indic/arabic/asian script, OCR, Video OCR, word spotting, retrieval, document datasets, performance evaluation, document annotation tools
- Kategorie
- Informatik