25.4.9 OCR Evaluations

Chapter Contents (Back)
OCR. Evaluation. Character Recognition.

Mullin, J.K.,
Reliable Indexing Using Unreliable Recognition Devices,
PAMI(3), No. 3, May 1981, pp. 347-350. BibRef 8105

Mullin, J.K.[James K.],
Interfacing criteria for recognition logic used with a context post-processor,
PR(15), No. 3, 1982, pp. 271-273.
Elsevier DOI 0309
BibRef

Evangelisti, C.J.,
Some Experiments In The Evaluation Of A Character Recognition Scanner,
PR(16), No. 3, 1983, pp. 273-287.
Elsevier DOI 9611
Evaluation, OCR. BibRef

Tung, C.H., Chen, Y.J., Lee, H.J.,
Performance Analysis of an OCR System Via an Artificial Handwritten Chinese Character Generator,
PR(27), No. 2, February 1994, pp. 221-232.
Elsevier DOI Evaluation, OCR. BibRef 9402

Rice, S.V.[Stephen V.], Kanai, J.[Junichi], and Nartker, T.A.[Thomas A.],
A Report on the Accuracy of OCR Devices,
SDAIR92(xx). BibRef 9200

Rice, S.V.[Stephen V.], Kanai, J.[Junichi], Nartker, T.A.[Thomas A.],
An Evaluation of OCR Accuracy',
SDAIR93(xx). BibRef 9300

Nartker, T.A.[Thomas A.], Rice, S.V.[Stephen V.], Kanai, J.[Junichi],
OCR Accuracy: UNLV's Second Annual Test,
INFORM(8), No. 1, January 1994, pp. 40-45. Evaluation, OCR. BibRef 9401

Rice, S.V.[Steve V.], Kanai, J.[Junichi], Nartker, T.A.[Thomas A.],
The Third Annual Test of OCR Accuracy,
SDAIR94(xx). April 1994. BibRef 9404

Nartker, T.A.[Thomas A.], Rice, S.V.[Stephen V.],
OCR Accuracy: UNLV's Third Annual Test,
INFORM(8), No. 8, September 1994, pp. 30-36. BibRef 9409

Rice, S.V., Jenkins, F.R., Nartker, T.A.,
The Fouth Annual Test of OCR Accuracy,
SDAIR95or ISRI TR-95-04, April 1995. BibRef 9504

Rice, S.V.[Steve V.],
The Fifth Annual Test of OCR Accuracy,
SDAIR96(XX) Information Science Research Institute. BibRef 9600

Rice, S.V., Jenkins, F.R., Nartker, T.A.,
OCR Accuracy: UNLV's Fifth Annual Test,
INFORM(10), No. 8, September 1996, pp. xx-yy. BibRef 9609

Kanugo, T., Haralick, R.M., Phillips, I.T.,
Nonlinear Local and Global Document Degradation Models,
IJIST(5), No. 4, Fall 1994, pp. 220-30. BibRef 9400
Earlier:
Global And Local Document Degradation Models,
ICDAR93(730-734). And the evaluation of edges:
See also Methodology for Quantitative Performance Evaluation of Detection Algorithms, A. BibRef

Kanungo, T.[Tapas], Haralick, R.M.[Robert M.], Baird, H.S.[Henry S.], Stuezle, W.[Werner], Madigan, D.[David],
A Statistical, Nonparametric Methodology for Document Degradation Model Validation,
PAMI(22), No. 11, November 2000, pp. 1209-1223.
IEEE DOI 0012
Evaluation, Document Analysis. BibRef
And: UMD--TR3982, January 1999.
WWW Link. BibRef
Earlier:
Document Degradation Models: Parameter Estimation and Model Validation,
MVA94(552-7). Kawasaki, Japan. Printing, photocopying, and scanning processes. Models to predict performance. BibRef

Baird, H.S.[Henry S.],
Document Image Defect Models,
SDIA92(xx-yy). 0905
BibRef

Kanungo, T., Haralick, R.M.,
Receiver Operating Curves and Optimal Bayesian Operating Points,
ICIP95(III: 256-259).
IEEE DOI 9510
BibRef

Kanungo, T., Haralick, R.M.,
Estimation of Morphological Degradation Parameters,
SPIE(2424), 1995, pp. 86-95. San Jose, California, USA. BibRef 9500

Kanungo, T., Haralick, R.M., Baird, H.S.,
Power Functions and Their Use in Selecting Distance Functions for Document Degradation Model Validation,
ICDAR95(734-9). Montreal, Canada. BibRef 9500

Kanungo, T., Haralick, R.M.,
An Automatic Closed-Loop Methodology for Generating Character Groundtruth for Scanned Documents,
PAMI(21), No. 2, February 1999, pp. 179-183.
IEEE DOI Evaluation, OCR. BibRef 9902
And: A1 only: UMD--TR3959, December 1998.
WWW Link. BibRef

Kanungo, T., Haralick, R.M.,
Automatic Generation of Character Groundtruth for Scanned Documents: A Closed-Loop Approach,
ICPR96(III: 669-675).
IEEE DOI 9608
(Univ. of Washington, USA) BibRef

Kanungo, T.[Tapas], Resnik, P.[Philip],
The Bible, Truth, and Multilingual OCR Evaluation,
UMD--TR3967, December 1998.
WWW Link. BibRef 9812

Kanungo, T.[Tapas], Marton, G.A.[Gregory A.], Bulbul, O.[Osama],
Paired Model Evaluation of OCR Algorithms,
UMD--TR3972, December 1998.
WWW Link. BibRef 9812

Ho, T.K.[Tin Kam], Baird, H.S.,
Large-Scale Simulation Studies in Image Pattern Recognition,
PAMI(19), No. 10, October 1997, pp. 1067-1079.
IEEE DOI 9710
Evaluation. Irregular cluster shapes. BibRef

Kanai, J., Rice, S.V., Nartker, T.A., Nagy, G.,
Automated Evaluation of OCR Zoning,
PAMI(17), No. 1, January 1995, pp. 86-90.
IEEE DOI BibRef 9501

Jung, D.M., Krishnamoorthy, M.S., Nagy, G., Shapira, A.,
N-Tuple Features for OCR Revisited,
PAMI(18), No. 7, July 1996, pp. 734-745.
IEEE DOI 9608
Generate N points that should be in a character and use for matching. Finding a good set is NP, but usually runs quickly on current hardware. BibRef

Jung, D.M.,
Joint Feature and Classifier Design for OCR Based on a Small Training Set,
Ph.D.Thesis, RPI, May 1995. BibRef 9505

Kanai, J., Rice, S.V., Nartker, T.A.,
A Preliminary Evaluation of Automatic Zoning,
ISRITR-93-02, April 1993. BibRef 9304

Mao, J.C., Mohiuddin, K.M.,
Improving OCR Performance Using Character Degradation Models and Boosting Algorithm,
PRL(18), No. 11-13, November 1997, pp. 1415-1419. 9806
Evaluation, OCR. BibRef

Micó, L.[Luisa], Oncina, J.[Jose],
Comparison of Fast Nearest Neighbor Classifiers for Handwritten Character Recognition,
PRL(19), No. 3-4, March 1998, pp. 351-356. 9807
BibRef

Junker, M., Hoch, R.,
An Experimental Evaluation of OCR Text Representations for Learning Document Classifiers,
IJDAR(1), No. 2, 1998, pp. 319-330. Evaluation, OCR. BibRef 9800

Govindaraju, V.[Venu], Slavik, P.[Petr], Xue, H.H.[Han-Hong],
Use of Lexicon Density in Evaluating Word Recognizers,
PAMI(24), No. 6, June 2002, pp. 789-800.
IEEE DOI 0206
Word Level Recognition. Rather than just number of words, the distribution of words matters. (I.e. get the common words right, miss the occasional rare word.) BibRef

Xue, H.H.[Han-Hong], Govindaraju, V.[Venu],
On the Dependence of Handwritten Word Recognizers on Lexicons,
PAMI(24), No. 12, December 2002, pp. 1553-1564.
IEEE Abstract. 0212
Analysis of how recognition depends on lexicon (size, similar words). Model fits well. Five word recognizers Oversegmentation
See also Lexicon Driven Approach to Handwritten Word Recognition for Real-Time Applications, A. Oversegmentation
See also Overview of Run-Length Encoding of Handwritten Word Images, An. Grapheme
See also Building Skeletal Graphs for Structural Feature Extraction on Handwriting Images. Character model
See also Character Model Word Recognition. Continuous modles
See also Variable Duration Hidden Markov Model and Morphological Segmentation for Handwritten Word Recognition. BibRef

Govindaraju, V.[Venu], Xue, H.,
Fast handwriting recognition for indexing historical documents,
DIAL04(314-320).
IEEE DOI 0404
BibRef

Kim, D.W.[Doe-Wan], Kanungo, T.[Tapas],
Attributed point matching for automatic groundtruth generation,
IJDAR(5), No. 1, 2002, pp. 47-66.
Springer DOI 0211
BibRef
And:
A Point Matching Algorithm for Automatic Groundtruth Generation,
UMD--TR4217, February 2001.
WWW Link. OCR evaluation groundtruth generation. BibRef

Lee, C.H.[Chang Ha], Kanungo, T.[Tapas],
The architecture of TrueViz: A groundTRUth/metadata editing and VIsualiZing ToolKit,
PR(36), No. 3, March 2003, pp. 811-825.
Elsevier DOI 0301
BibRef
Earlier: UMD--TR4212, February 2001.
WWW Link. Document analysis tools for creating groundtruth. BibRef

NIST OCR Databases,
2005.
WWW Link. Dataset, OCR. Dataset, Documents. A series of datasets for OCR and document analysis.


Luyen, D.T.[Do Thi], Carel, E.[Elodie], Ogier, J.M.[Jean-Marc], Burie, J.C.[Jean-Christophe],
A character degradation model for color document images,
ICDAR15(806-810)
IEEE DOI 1511
BibRef

Chen, Z.G.[Zhen-Gang], Ding, X.Q.[Xiao-Qing],
Rejection algorithm for mis-segmented characters in multilingual document recognition,
ICDAR03(746-749).
IEEE DOI 0311
BibRef

Takasu, A., Aihara, K.,
DVHMM: variable length text recognition error model,
ICPR02(III: 110-114).
IEEE DOI 0211
BibRef

Hallouli, K., Likforman-Sulem, L., Sigelle, M.,
A comparative study between decision fusion and data fusion in Markovian printed character recognition,
ICPR02(III: 147-150).
IEEE DOI 0211
BibRef

Allan, J., Allen, T., Sherkat, N.,
Confident assessment of children's handwritten responses,
FHR02(508-512).
IEEE Top Reference. 0209
BibRef
And:
Automated assessment: How confident are we?,
FHR02(419-423).
IEEE Top Reference. 0209
BibRef

Allan, J., Allen, T., Sherkat, N., Halstead, P.,
Automated assessment: it's assessment Jim but not as we know it,
ICDAR01(926-930).
IEEE DOI 0109
BibRef

Rowley, H.A., Goyal, M., Bennett, J.,
The effect of large training set sizes on online japanese kanji and english cursive recognizers,
FHR02(36-40).
IEEE Top Reference. 0209
BibRef

Klink, S., Jäger, T.,
MergeLayouts: A Comprehensive Voting of Commercial OCR Devices,
SCIA99(Pattern Recognition). BibRef 9900

Benedetti, A., Kovacs-Vajna, Z.M.,
Confidence Computation Improvement in an Optical Field Reading System,
ICDAR97(836-841).
IEEE DOI 9708
BibRef

Lefevre, P.[Philippe],
Histograms to Evaluate OCR Accuracy and OCR Coupling,
SDAIR96(XX) EDF-Direction des Etudes et Recherches. BibRef 9600

Junker, M., Hoch, R.,
Evaluating OCR and Non-OCR Text Representations for Learning Document Classifiers,
ICDAR97(1060-1066).
IEEE DOI 9708
BibRef

Grother, P.J., Candela, G.T.,
Comparison of Handprinted Digit Classifiers,
NISTIR5209, June 1993
HTML Version. BibRef 9306

Phillips, I.T., Ha, J.,
The Implementation Methodology for a CD-Rom English Document Database,
ICDAR93(484-7). BibRef 9300

Garris, M.D.,
Evaluating Spatial Correspondence of Zones in Document Recognition Systems,
ICIP95(III: 304-307).
IEEE DOI
WWW Link. 9510
BibRef

Garris, M.D.,
Method and Evaluation of Character Stroke Preservation on Handprint Recognition,
SPIE(2660), 1996, pp. 321-332. BibRef 9600
And: NISTIR5687, NIST, July 1995
HTML Version. BibRef

Randriamasy, S.,
A Set-Based Benchmarking Method for Address Block Location on Arbitrarily Complex Grey Level Images,
ICDAR95(619-622) document/OCR BibRef 9500

Nartker, T.A.,
Need for Information Metrics: With Examples from Document Analysis,
SPIE(2181), 1994, pp. 184-193. San Jose, California, USA. BibRef 9400

Kanai, J.[Junichi], Nartker, T.A.[Thomas A.], Rice, S.V.[Stephen V.], Nagy, G.[George],
Performance Metrics For Document Understanding Systems,
SDAIR93 1993(424-427). University of Nevada Las Vegas BibRef 9300

Jenkins, F., Kanai, J., Nartker, T.A.,
Using Ideal Images to Establish a Baseline of OCR Performance,
ISRITR-93-013, April 1993. BibRef 9304

Kanai, J.[Junichi], Liu, Y.C.[Yu-Cheng], Rice, S.V.[Stephen V.], Nartker, T.A.[Thomas A.],
A Preliminary Evaluation of Chinese OCR Systems,
ISRITR-94-04, April 1994. BibRef 9404

Taghva, K.[Kazem], Condit, A.[Allen], Borsack, J.[Julie],
An Evaluation of an Automatic Markup System,
SPIE(2422), 1995, pp. 317-327.
HTML Version. BibRef 9500

Taghva, K.[Kazem], Borsack, J.[Julie], Condit, A.[Allen], Inaparthy, P.[Padma],
The Effects of OCR Errors on Short Documents,
ISRITR-94-10, February 1994. BibRef 9402

Croft, W.B., Harding, S., Taghva, K., Borsack, J.,
An Evaluation of Information Retrieval Accuracy with Simulated OCR Output,
SDAIR94(115-126). University of Nevada, Las Vegas
HTML Version. BibRef 9400

Jenkins, F., Kanai, J.,
The Use of Synthesized Images to Evaluate the Performance of Optical Character Recognition Devices and Algorithms,
SPIE(2181), 1994, pp. 194-203. BibRef 9400

Chapter on OCR, Document Analysis and Character Recognition Systems continues in
Bar Code Readers, Reading .


Last update:Mar 16, 2024 at 20:36:19