ICFHR2016 Handwritten Document Image Binarization Contest (H-DIBCO 2016)

Pratikakis, Ioannis; Zagoris, Konstantinos; Barlas, George; Gatos, Basilis

doi:10.1109/icfhr.2016.0118

Cited by 87 publications

(75 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TM are the results from another CNN based approach developed by Tensmeyer and Martinez (2017), which augments the segmentation result with relative darkness feature Wu et al (2015), to aid in binarization. DBC are results from winning entries in DIBCO competitions using various classical approaches in as given in Ntirogiannis et al (2014), Pratikakis et al (2016).…”

Section: Trainingmentioning

confidence: 99%

PDNet: Semantic segmentation integrated with a primal-dual network for document binarization

Ayyalasomayajula

Malmberg

Brun

2019

Pattern Recognition Letters

View full text Add to dashboard Cite

Binarization of digital documents is the task of classifying each pixel in an image of the document as belonging to the background (parchment/paper) or foreground (text/ink). Historical documents are often subjected to degradations, that make the task challenging. In the current work a deep neural network architecture is proposed that combines a fully convolutional network with an unrolled primal-dual network that can be trained end-to-end to achieve state of the art binarization on four out of seven datasets. Document binarization is formulated as an energy minimization problem. A fully convolutional neural network is trained for semantic segmentation of pixels that provides labeling cost associated with each pixel. This cost estimate is refined along the edges to compensate for any over or under estimation of the foreground class using a primal-dual approach. We provide necessary overview on proximal operator that facilitates theoretical underpinning required to train a primal-dual network using a gradient descent algorithm. Numerical instabilities encountered due to the recurrent nature of primal-dual approach are handled. We provide experimental results on document binarization competition dataset along with network changes and hyperparameter tuning required for stability and performance of the network. The network when pre-trained on synthetic dataset performs better as per the competition metrics.Accepted in PRL

show abstract

Section: Trainingmentioning

confidence: 99%

PDNet: Semantic segmentation integrated with a primal-dual network for document binarization

Ayyalasomayajula

Malmberg

Brun

2019

Pattern Recognition Letters

View full text Add to dashboard Cite

show abstract

“…There is a need for more sophisticated methods to assess image quality. Popular document quality evaluation measures [6], [7] include the F-Measure, the Peak-Signal-to-Noise Ratio (PSNR), the Distance Reciprocal Distortion metric (DRD) [8], and the Negative Rate Metric (NRM). Computation of such metrics requires a corresponding distortion-free ground truth reference image for any given document image.…”

Section: Introductionmentioning

confidence: 99%

Learning Surrogate Models of Document Image Quality Metrics for Automated Document Image Processing

Singh

Vats

Hast

2018

2018 13th IAPR International Workshop on Document Analysis Systems (DAS)

View full text Add to dashboard Cite

Computation of document image quality metrics often depends upon the availability of a ground truth image corresponding to the document. This limits the applicability of quality metrics in applications such as hyperparameter optimization of image processing algorithms that operate on-the-fly on unseen documents. This work proposes the use of surrogate models to learn the behavior of a given document quality metric on existing datasets where ground truth images are available. The trained surrogate model can later be used to predict the metric value on previously unseen document images without requiring access to ground truth images. The surrogate model is empirically evaluated on the Document Image Binarization Competition (DIBCO) and the Handwritten Document Image Binarization Competition (H-DIBCO) datasets.

show abstract

“…We measure the binarization performance using F-Measure, pseudo-F-Measure (F ps ), the peak-signal-tonoise ratio (PSNR) and the distance reciprocal distortion metric (DRD), which are commonly used in binarization competitions [30,[38][39][40]. While F-Measure assesses binarization quality in terms of misclassified pixels regardless of the pixels' location, F ps weights pixel misclassifications differently to emphasize readability.…”

Section: Experiments Setupmentioning

confidence: 99%

“…These algorithms are commonly used as baseline for comparison with new algorithms, for example, in competitions, such as the Document Image Binarization Contest (DIBCO) held at the International Conference on Document Analysis and Recognition (ICDAR) [12,37,39] or the Competition on Handwritten Document Image Binarization (H-DIBCO) held at the International Conference on Frontiers in Handwriting Recognition (ICFHR) [30,36,38,40]. In the last two binarization competitions, in 2014 and 2016, the binarization algorithm by Howe [19] and derivations thereof using different preprocessing steps have won these contests.…”

Section: Image Binarizationmentioning

confidence: 99%

See 1 more Smart Citation

Efficient document image binarization using heterogeneous computing and parameter tuning

Westphal

Grahn

Lavesson

2018

IJDAR

View full text Add to dashboard Cite

In the context of historical document analysis, image binarization is a first important step, which separates foreground from background, despite common image degradations, such as faded ink, stains, or bleed-through. Fast binarization has great significance when analyzing vast archives of document images, since even small inefficiencies can quickly accumulate to years of wasted execution time. Therefore, efficient binarization is especially relevant to companies and government institutions, who want to analyze their large collections of document images. The main challenge with this is to speed up the execution performance without affecting the binarization performance. We modify a state-of-the-art binarization algorithm and achieve on average a 3.5 times faster execution performance by correctly mapping this algorithm to a heterogeneous platform, consisting of a CPU and a GPU. Our proposed parameter tuning algorithm additionally improves the execution time for parameter tuning by a factor of 1.7, compared to previous parameter tuning algorithms. We see that for the chosen algorithm, machine learning-based parameter tuning improves the execution performance more than heterogeneous computing, when comparing absolute execution times.

show abstract

ICFHR2016 Handwritten Document Image Binarization Contest (H-DIBCO 2016)

Cited by 87 publications

References 15 publications

PDNet: Semantic segmentation integrated with a primal-dual network for document binarization

PDNet: Semantic segmentation integrated with a primal-dual network for document binarization

Learning Surrogate Models of Document Image Quality Metrics for Automated Document Image Processing

Efficient document image binarization using heterogeneous computing and parameter tuning

Contact Info

Product

Resources

About