Combining Focus Measure Operators to Predict OCR Accuracy in Mobile-Captured Document Images

Rusiñol, Marçal; Chazalon, Joseph; Ogier, Jean-Marc

doi:10.1109/das.2014.11

Cited by 30 publications

(29 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Table I, we compare the median LCC and SROCC of our method with the-state-of-the-art methods presented by [22] and CFMO presented in [14]. For metric-based methods, our results are better than to the ones of both Q [11] and ΔDoM [10] and compatible to the results of CFMO method [14] in terms of LCC. Since the image acquisition by mobile phones is being explored, metric-based methods are preferred to work with a single document image than learning-based methods such as CORNIA [15].…”

Section: B Performance Evaluationsupporting

confidence: 85%

“…Since the image acquisition by mobile phones is being explored, metric-based methods are preferred to work with a single document image than learning-based methods such as CORNIA [15]. The good metric-based method CFMO [14] has given a median LCC value of 0.9378 by combining several normalized existing focus measures. Our method with single blur feature has given the acceptable result of 0.9237.…”

Section: B Performance Evaluationmentioning

confidence: 99%

“…Nevertheless, the use of the bilateral filter may lead to a loss of information about blur in the original image. The Combining Focus Measure Operators (CFMO) (including Gradient-based, Laplacian-based, Wavelet-based, Statisticbased, and Miscellaneous operators) has been proposed in [14] to deal with out-of-focus blur. Such global focus measures are firstly normalized.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

OCR Accuracy Prediction Method Based on Blur Estimation

Kieu

Cloppet

Vincent

2016

2016 12th IAPR Workshop on Document Analysis Systems (DAS)

View full text Add to dashboard Cite

In this paper, we propose an OCR accuracy prediction method based on a local blur estimation since blur is one of the important factors that mostly damage OCR accuracy. First, we apply the blur estimation on synthetic blurred images by using Gaussian and motion blur in order to investigate the relation between blur effect and character size regarding OCR accuracy. This relation is considered as a blur-character size feature to define a classifier. Finally, the classifier can separate characters of a given document into three classes: readable, intermediate, and non-readable classes. Therefore, the quality score of the document is inferred from the three classes. The proposed method is evaluated on a published database and on an industrial one. The correlation with OCR accuracy is also given to compare with the state-of-the-art methods.

show abstract

Section: B Performance Evaluationsupporting

confidence: 85%

Section: B Performance Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

OCR Accuracy Prediction Method Based on Blur Estimation

Kieu

Cloppet

Vincent

2016

2016 12th IAPR Workshop on Document Analysis Systems (DAS)

View full text Add to dashboard Cite

show abstract

“…For a particular document dataset or application domain, a straightforward solution would be to learn the final quality score from feature vectors that contain values of the different metrics, or simply trying out different combinations as done in. 25 In our proposed system, we choose three character-based metrics, and produce a weighted sum of them to compute the desired image content quality metric.…”

Section: The Proposed Approachmentioning

confidence: 99%

Metric-based no-reference quality assessment of heterogeneous document images

Nayef¹,

Ogier²

2015

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

No-reference image quality assessment (NR-IQA) aims at computing an image quality score that best correlates with either human perceived image quality or an objective quality measure, without any prior knowledge of reference images. Although learning-based NR-IQA methods have achieved the best state-of-the-art results so far, those methods perform well only on the datasets on which they were trained. The datasets usually contain homogeneous documents, whereas in reality, document images come from different sources. It is unrealistic to collect training samples of images from every possible capturing device and every document type. Hence, we argue that a metric-based IQA method is more suitable for heterogeneous documents. We propose a NR-IQA method with the objective quality measure of OCR accuracy. The method combines distortion-specific quality metrics. The final quality score is calculated taking into account the proportions of, and the dependency among different distortions. Experimental results show that the method achieves competitive results with learning-based NR-IQA methods on standard datasets, and performs better on heterogeneous documents.

show abstract

“…Kumar et al [6] proposed the use of ΔDOM (change in slope) to model the changes in the direction of edges to estimate the sharpness in images, whereas Rusiñol et al [7] used different focus measure operators and combined their results to estimate the OCR accuracy in the image. Kai-Chieh et al [8] used machine learning approaches for blur estimation achieving promising results.…”

Section: Introductionmentioning

confidence: 99%

High Performance OCR for Camera-Captured Blurred Documents with LSTM Networks

Asad

Ul-Hasan

Dengel

2016

2016 12th IAPR Workshop on Document Analysis Systems (DAS)

View full text Add to dashboard Cite

Documents are routinely captured by digital cameras in today's age owing to the availability of high quality cameras in smart phones. However, recognition of camera-captured documents is substantially more challenging as compared to traditional flat bed scanned documents due to the distortions introduced by the cameras. One of the major performancelimiting artifacts is the motion and out-of-focus blur that is often induced in the document during the capturing process. Existing approaches try to detect presence of blur in the document to inform the user for re-capturing the image. This paper reports, for the first time, an Optical Character Recognition (OCR) system that can directly recognize blurred documents on which the stateof-the-art OCR systems are unable to provide usable results. Our presented system is based on the Long Short-Term Memory (LSTM) networks and has shown promising character recognition results on both the motion-blurred and out-of-focus blurred images. One important feature of this work is that the LSTM networks have been applied directly to the gray-scale document images to avoid error-prone binarization of blurred documents. Experiments are conducted on publicly available SmartDoc-QA dataset that contains a wide variety of image blur degradations. Our presented system achieves 12.3% character error rate on the test documents, which is an over three-fold reduction in the error rate (38.9%) of the best-performing contemporary OCR system (ABBYY Fine Reader) on the same data.

show abstract

Combining Focus Measure Operators to Predict OCR Accuracy in Mobile-Captured Document Images

Cited by 30 publications

References 8 publications

OCR Accuracy Prediction Method Based on Blur Estimation

OCR Accuracy Prediction Method Based on Blur Estimation

Metric-based no-reference quality assessment of heterogeneous document images

High Performance OCR for Camera-Captured Blurred Documents with LSTM Networks

Contact Info

Product

Resources

About