Enhancing OCR Accuracy with Super Resolution

Lat, Ankit; Jawahar, C. V.

doi:10.1109/icpr.2018.8545609

Cited by 32 publications

(19 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to its versatility, GAN-based super-resolution techniques can potentially improve poor quality of document images, which is attributed to low scanning quality and resolution. Lat and Jawahar [24] super-resolve the low resolution document images before passing them to the OCR engine and greatly improve OCR accuracy on test images. However, we found that existing approaches could not provide satisfactory segregation results.…”

Section: Related Workmentioning

confidence: 99%

Separating Chinese Character from Noisy Background Using GAN

Huang

Lin

Chen

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Separating printed or handwritten characters from a noisy background is valuable for many applications including test paper autoscoring. The complex structure of Chinese characters makes it difficult to obtain the goal because of easy loss of fine details and overall structure in reconstructed characters. This paper proposes a method for separating Chinese characters based on generative adversarial network (GAN). We used ESRGAN as the basic network structure and applied dilated convolution and a novel loss function that improve the quality of reconstructed characters. Four popular Chinese fonts (Hei, Song, Kai, and Imitation Song) on real data collection were tested, and the proposed design was compared with other semantic segmentation approaches. The experimental results showed that the proposed method effectively separates Chinese characters from noisy background. In particular, our methods achieve better results in terms of Intersection over Union (IoU) and optical character recognition (OCR) accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Separating Chinese Character from Noisy Background Using GAN

Huang

Lin

Chen

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…The exercise yielded specifications for the relative performance of three leading OCR products as well as the differential effects of commonly found noise types. The 1 For pre-processing see, e.g, [3,7,13,19,42], and [44]. For model training, see, e.g., [4,29,33], and [45].…”

Section: Introductionmentioning

confidence: 99%

OCR with Tesseract, Amazon Textract, and Google Document AI: a benchmarking experiment

Hegghammer

2021

J Comput Soc Sc

View full text Add to dashboard Cite

Optical Character Recognition (OCR) can open up understudied historical documents to computational analysis, but the accuracy of OCR software varies. This article reports a benchmarking experiment comparing the performance of Tesseract, Amazon Textract, and Google Document AI on images of English and Arabic text. English-language book scans (n = 322) and Arabic-language article scans (n = 100) were replicated 43 times with different types of artificial noise for a corpus of 18,568 documents, generating 51,304 process requests. Document AI delivered the best results, and the server-based processors (Textract and Document AI) performed substantially better than Tesseract, especially on noisy documents. Accuracy for English was considerably higher than for Arabic. Specifying the relative performance of three leading OCR products and the differential effects of commonly found noise types can help scholars identify better OCR solutions for their research needs. The test materials have been preserved in the openly available “Noisy OCR Dataset” (NOD) for reuse in future benchmarking studies.

show abstract

“…But OCR is a technology still in the making, and available software provides varying levels of accuracy. The best results are usually obtained with a tailored solution involving corpus-specific pre-processing (Bieniecki, Grabowski, and Rozenberg 2007;Dengel et al 1997;Holley 2009;Lat and Jawahar 2018;Volk, Furrer, and Sennrich 2011;Wemhoener, Yalniz, and Manmatha 2013), model training (Boiangiu et al 2016;Reul et al 2018;Springmann et al 2014;Wick, Reul, and Puppe 2018), or postprocessing (Kissos and Dershowitz 2016;Strohmaier et al 2003;Thompson, McNaught, and Ananiadou 2015), but such procedures can be labour-intensive. Pretrained, general OCR processors have a much higher potential for wide adoption in the scholarly community, and hence their out-of-the box performance is of scientific interest.…”

Section: Introductionmentioning

confidence: 99%

OCR with Tesseract, Amazon Textract, and Google Document AI: A Benchmarking Experiment

Hegghammer¹

2021

Preprint

View full text Add to dashboard Cite

Optical Character Recognition (OCR) can open up understudied historical documents to computational analysis, but the accuracy of OCR software varies. This article reports a benchmarking experiment comparing the performance of Tesseract, Amazon Textract, and Google Document AI on images of English and Arabic text. English-language book scans (n=322) and Arabic-language article scans (n=100) were replicated 43 times with different types of artificial noise for a corpus of 18,568 documents, generating 51,304 process requests. Document AI delivered the best results, and the server-based processors (Textract and Document AI) were substantially more accurate than Tesseract, especially on noisy documents. Accuracy for English was considerably better than for Arabic. Specifying the relative performance of three leading OCR products and the differential effects of commonly found noise types can help scholars identify better OCR solutions for their research needs. The test materials have been preserved in the openly available "Noisy OCR Dataset" (NOD).

show abstract

Enhancing OCR Accuracy with Super Resolution

Cited by 32 publications

References 15 publications

Separating Chinese Character from Noisy Background Using GAN

Separating Chinese Character from Noisy Background Using GAN

OCR with Tesseract, Amazon Textract, and Google Document AI: a benchmarking experiment

OCR with Tesseract, Amazon Textract, and Google Document AI: A Benchmarking Experiment

Contact Info

Product

Resources

About