Prediction of OCR accuracy using simple image features

Blando, Luis Ricardo; Kanai, Junichi; Nartker, Thomas A.

doi:10.1109/icdar.1995.599003

Cited by 44 publications

(24 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It also eases the burden of hand segmenting and labeling data. Models of the degradation process, along with estimates of the parameters for these models, can be combined to make a decision on whether a given document should be entered by hand or sent to an Optical Character Recognition (OCR) routine [8,14,15]. A model will allow researchers to conduct controlled experiments to improve OCR performance.…”

Section: Introductionmentioning

confidence: 99%

Statistical image differences, degradation features, and character distance metrics

Smith

Qiu

2003

International Journal on Document Analysis and Recognition

View full text Add to dashboard Cite

Abstract. Document image quality is degraded through processes such as scanning, printing, and photocopying. The resulting bilevel image degradations can be categorized based either on observable degradation features or on degradation model parameters. The image degradation features can be related mathematically to model parameters. In this paper we statistically compare pairs of populations of degraded character images created with different model parameters. The probability that the character populations were degraded by the same model parameters correlates with the relationship between observable degradation features and the model parameters. Two metrics of character difference are used: Hamming distance and moment feature distance. Knowledge of under which conditions characters will be similar and when they will be different can influence the choice of parameters for future experiments.

show abstract

Section: Introductionmentioning

confidence: 99%

Statistical image differences, degradation features, and character distance metrics

Smith

Qiu

2003

International Journal on Document Analysis and Recognition

View full text Add to dashboard Cite

show abstract

“…This can increase recognition accuracy. Models of the degradation process, along with estimates of the parameters for these models, can be combined to make a decision on whether a given document should be entered by hand or sent to an OCR routine [8,13,14]. A model will allow researchers to conduct controlled experiments to improve OCR and DIA performance.…”

Section: Introductionmentioning

confidence: 99%

Relating Statistical Image Differences and Degradation Features

Smith

Qiu

2002

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Document images are degraded through bilevel processes such as scanning, printing, and photocopying. The resulting image degradations can be categorized based either on observable degradation features or on degradation model parameters. The degradation features can be related mathematically to model parameters. In this paper we statistically compare pairs of populations of degraded character images created with different model parameters. The changes in the probability that the characters are from different populations when the model parameters vary correlate with the relationship between observable degradation features and the model parameters. The paper also shows which features have the largest impact on the image.

show abstract

“…Factors such as white spot and collapsing of characters have been introduced and used to predict OCR accuracy 14) .…”

Section: Quality Evaluation Of Character Imagementioning

confidence: 99%

[Paper] An Encoding Method for Images Containing Textual Information for Very Low-Bandwidth Transmission

Kaneko

Sugaya

Omachi

2016

MTA

View full text Add to dashboard Cite

Essential information contained in an original image may be deteriorated if the image is highly compressed without considering the importance of each region in the image. Assuming that textual information contained in an image is important, we propose a method for image compression while maintaining the readability of characters by automatic evaluation for character readability. The proposed automatic evaluation classifies character images into either readable or unreadable images by using machine learning, and the proposed evaluation is used in quantization table optimization in order to ensure character readability while minimizing the overall image data size. In addition, less important information in view of image recognition in the background region is reduced. By several subjective experiments, we confirm that the proposed method maintains character readability relative to the standard JPEG compression method while retaining the required image quality of background regions in order to maintain sufficient recognition of content and situations.

show abstract

Prediction of OCR accuracy using simple image features

Cited by 44 publications

References 4 publications

Statistical image differences, degradation features, and character distance metrics

Statistical image differences, degradation features, and character distance metrics

Relating Statistical Image Differences and Degradation Features

[Paper] An Encoding Method for Images Containing Textual Information for Very Low-Bandwidth Transmission

Contact Info

Product

Resources

About