Assessment of image quality to predict readability of documents
Identifieur interne :
000A23 ( PascalFrancis/Curation );
précédent :
000A22;
suivant :
000A24
Assessment of image quality to predict readability of documents
Auteurs : V. Govindaraju [
États-Unis] ;
S. N. Srihari [
États-Unis]
Source :
-
SPIE proceedings series [ 1017-2653 ] ; 1996.
RBID : Pascal:97-0010335
Abstract
Determining the readability of documents is an important task. Human readability pertains to the scenario when a document image is ultimately presented to a human to read. Machine readability pertains to the scenario when the document is subjected to an OCR process. In either case, poor image quality might render a document un-readable. A document image which is human readable is often not machine readable. It is often advisable to filter out documents of poor image quality before sending them to either machine or human for reading. This paper is about the design of such a filter. We describe various factors which affect document image quality and the accuracy of predicting the extent of human and machine readability possible using metrics based on document image quality. We illustrate the interdependence of image quality measurement and enhancement by means of two applications that have been implemented : (i) reading handwritten addresses on mailpieces and (ii) reading handwritten US Census forms. We also illustrate the degradation of OCR performance as a function of image quality. On an experimental test set of 517 document images, the image quality metric (measuring fragmentation due to poor binarization) correctly predicted 90% of the time that certain documents were of poor quality (fragmented characters) and hence not machine readable.
pA |
A01 | 01 | 1 | | @0 1017-2653 |
---|
A05 | | | | @2 2660 |
---|
A08 | 01 | 1 | ENG | @1 Assessment of image quality to predict readability of documents |
---|
A09 | 01 | 1 | ENG | @1 Document recognition III : San Jose CA, 29-30 January 1996 |
---|
A11 | 01 | 1 | | @1 GOVINDARAJU (V.) |
---|
A11 | 02 | 1 | | @1 SRIHARI (S. N.) |
---|
A12 | 01 | 1 | | @1 VINCENT (Luc M.) @9 ed. |
---|
A12 | 02 | 1 | | @1 HULL (Jonathan J.) @9 ed. |
---|
A14 | 01 | | | @1 Center of Excellence for Document Analysis and Recognition, State University of New York at Buffalo @2 Buffalo, NY 14260 @3 USA @Z 1 aut. @Z 2 aut. |
---|
A18 | 01 | 1 | | @1 International Society for Optical Engineering @2 Bellingham WA @3 USA @9 patr. |
---|
A20 | | | | @1 333-342 |
---|
A21 | | | | @1 1996 |
---|
A23 | 01 | | | @0 ENG |
---|
A43 | 01 | | | @1 INIST @2 21760 @5 354000060667820300 |
---|
A44 | | | | @0 0000 @1 © 1996 INIST-CNRS. All rights reserved. |
---|
A45 | | | | @0 5 ref. |
---|
A47 | 01 | 1 | | @0 97-0010335 |
---|
A60 | | | | @1 P @2 C |
---|
A61 | | | | @0 A |
---|
A64 | 01 | 1 | | @0 SPIE proceedings series |
---|
A66 | 01 | | | @0 USA |
---|
C01 | 01 | | ENG | @0 Determining the readability of documents is an important task. Human readability pertains to the scenario when a document image is ultimately presented to a human to read. Machine readability pertains to the scenario when the document is subjected to an OCR process. In either case, poor image quality might render a document un-readable. A document image which is human readable is often not machine readable. It is often advisable to filter out documents of poor image quality before sending them to either machine or human for reading. This paper is about the design of such a filter. We describe various factors which affect document image quality and the accuracy of predicting the extent of human and machine readability possible using metrics based on document image quality. We illustrate the interdependence of image quality measurement and enhancement by means of two applications that have been implemented : (i) reading handwritten addresses on mailpieces and (ii) reading handwritten US Census forms. We also illustrate the degradation of OCR performance as a function of image quality. On an experimental test set of 517 document images, the image quality metric (measuring fragmentation due to poor binarization) correctly predicted 90% of the time that certain documents were of poor quality (fragmented characters) and hence not machine readable. |
---|
C02 | 01 | X | | @0 001D04A05C |
---|
N21 | | | | @1 365 |
---|
|
pR |
A30 | 01 | 1 | ENG | @1 Document recognition. Conference @2 3 @3 San Jose CA USA @4 1996-01-29 |
---|
|
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: Pour aller vers cette notice dans l'étape Curation :000975
Links to Exploration step
Pascal:97-0010335
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Assessment of image quality to predict readability of documents</title>
<author><name sortKey="Govindaraju, V" sort="Govindaraju, V" uniqKey="Govindaraju V" first="V." last="Govindaraju">V. Govindaraju</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Center of Excellence for Document Analysis and Recognition, State University of New York at Buffalo</s1>
<s2>Buffalo, NY 14260</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
</affiliation>
</author>
<author><name sortKey="Srihari, S N" sort="Srihari, S N" uniqKey="Srihari S" first="S. N." last="Srihari">S. N. Srihari</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Center of Excellence for Document Analysis and Recognition, State University of New York at Buffalo</s1>
<s2>Buffalo, NY 14260</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">97-0010335</idno>
<date when="1996">1996</date>
<idno type="stanalyst">PASCAL 97-0010335 INIST</idno>
<idno type="RBID">Pascal:97-0010335</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000975</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000A23</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Assessment of image quality to predict readability of documents</title>
<author><name sortKey="Govindaraju, V" sort="Govindaraju, V" uniqKey="Govindaraju V" first="V." last="Govindaraju">V. Govindaraju</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Center of Excellence for Document Analysis and Recognition, State University of New York at Buffalo</s1>
<s2>Buffalo, NY 14260</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
</affiliation>
</author>
<author><name sortKey="Srihari, S N" sort="Srihari, S N" uniqKey="Srihari S" first="S. N." last="Srihari">S. N. Srihari</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Center of Excellence for Document Analysis and Recognition, State University of New York at Buffalo</s1>
<s2>Buffalo, NY 14260</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">SPIE proceedings series</title>
<idno type="ISSN">1017-2653</idno>
<imprint><date when="1996">1996</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">SPIE proceedings series</title>
<idno type="ISSN">1017-2653</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass></textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Determining the readability of documents is an important task. Human readability pertains to the scenario when a document image is ultimately presented to a human to read. Machine readability pertains to the scenario when the document is subjected to an OCR process. In either case, poor image quality might render a document un-readable. A document image which is human readable is often not machine readable. It is often advisable to filter out documents of poor image quality before sending them to either machine or human for reading. This paper is about the design of such a filter. We describe various factors which affect document image quality and the accuracy of predicting the extent of human and machine readability possible using metrics based on document image quality. We illustrate the interdependence of image quality measurement and enhancement by means of two applications that have been implemented : (i) reading handwritten addresses on mailpieces and (ii) reading handwritten US Census forms. We also illustrate the degradation of OCR performance as a function of image quality. On an experimental test set of 517 document images, the image quality metric (measuring fragmentation due to poor binarization) correctly predicted 90% of the time that certain documents were of poor quality (fragmented characters) and hence not machine readable.</div>
</front>
</TEI>
<inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>1017-2653</s0>
</fA01>
<fA05><s2>2660</s2>
</fA05>
<fA08 i1="01" i2="1" l="ENG"><s1>Assessment of image quality to predict readability of documents</s1>
</fA08>
<fA09 i1="01" i2="1" l="ENG"><s1>Document recognition III : San Jose CA, 29-30 January 1996</s1>
</fA09>
<fA11 i1="01" i2="1"><s1>GOVINDARAJU (V.)</s1>
</fA11>
<fA11 i1="02" i2="1"><s1>SRIHARI (S. N.)</s1>
</fA11>
<fA12 i1="01" i2="1"><s1>VINCENT (Luc M.)</s1>
<s9>ed.</s9>
</fA12>
<fA12 i1="02" i2="1"><s1>HULL (Jonathan J.)</s1>
<s9>ed.</s9>
</fA12>
<fA14 i1="01"><s1>Center of Excellence for Document Analysis and Recognition, State University of New York at Buffalo</s1>
<s2>Buffalo, NY 14260</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</fA14>
<fA18 i1="01" i2="1"><s1>International Society for Optical Engineering</s1>
<s2>Bellingham WA</s2>
<s3>USA</s3>
<s9>patr.</s9>
</fA18>
<fA20><s1>333-342</s1>
</fA20>
<fA21><s1>1996</s1>
</fA21>
<fA23 i1="01"><s0>ENG</s0>
</fA23>
<fA43 i1="01"><s1>INIST</s1>
<s2>21760</s2>
<s5>354000060667820300</s5>
</fA43>
<fA44><s0>0000</s0>
<s1>© 1996 INIST-CNRS. All rights reserved.</s1>
</fA44>
<fA45><s0>5 ref.</s0>
</fA45>
<fA47 i1="01" i2="1"><s0>97-0010335</s0>
</fA47>
<fA60><s1>P</s1>
<s2>C</s2>
</fA60>
<fA64 i1="01" i2="1"><s0>SPIE proceedings series</s0>
</fA64>
<fA66 i1="01"><s0>USA</s0>
</fA66>
<fC01 i1="01" l="ENG"><s0>Determining the readability of documents is an important task. Human readability pertains to the scenario when a document image is ultimately presented to a human to read. Machine readability pertains to the scenario when the document is subjected to an OCR process. In either case, poor image quality might render a document un-readable. A document image which is human readable is often not machine readable. It is often advisable to filter out documents of poor image quality before sending them to either machine or human for reading. This paper is about the design of such a filter. We describe various factors which affect document image quality and the accuracy of predicting the extent of human and machine readability possible using metrics based on document image quality. We illustrate the interdependence of image quality measurement and enhancement by means of two applications that have been implemented : (i) reading handwritten addresses on mailpieces and (ii) reading handwritten US Census forms. We also illustrate the degradation of OCR performance as a function of image quality. On an experimental test set of 517 document images, the image quality metric (measuring fragmentation due to poor binarization) correctly predicted 90% of the time that certain documents were of poor quality (fragmented characters) and hence not machine readable.</s0>
</fC01>
<fC02 i1="01" i2="X"><s0>001D04A05C</s0>
</fC02>
<fN21><s1>365</s1>
</fN21>
</pA>
<pR><fA30 i1="01" i2="1" l="ENG"><s1>Document recognition. Conference</s1>
<s2>3</s2>
<s3>San Jose CA USA</s3>
<s4>1996-01-29</s4>
</fA30>
</pR>
</standard>
</inist>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/PascalFrancis/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000A23 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Curation/biblio.hfd -nk 000A23 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= PascalFrancis
|étape= Curation
|type= RBID
|clé= Pascal:97-0010335
|texte= Assessment of image quality to predict readability of documents
}}
| This area was generated with Dilib version V0.6.32. Data generation: Sat Nov 11 16:53:45 2017. Site generation: Mon Mar 11 23:15:16 2024 | |