ICFHR2014 Competition on Handwritten Document Image Binarization (H-DIBCO 2014)

Ntirogiannis, Konstantinos; Gatos, Basilis; Pratikakis, Ioannis

doi:10.1109/icfhr.2014.141

Cited by 95 publications

(84 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is also reflected in the numerous binarization competitions, in which the execution time is either not reported [12,39] or not used as evaluation criterium [30,38]. Nevertheless, there have been a few implementations of common binarization algorithms utilizing the parallel computing capabilities of GPUs.…”

Section: Efficient Image Binarizationmentioning

confidence: 99%

“…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%

“…The document image binarization contest datasets from DIBCO 2009 [12], H-DIBCO 2010 [36], DIBCO 2011 [37], H-DIBCO 2012 [38], DIBCO 2013 [39], H-DIBCO 2014 [30] and H-DIBCO 2016 [40], were used in all experiments. These datasets contain 86 images in total, of which 65 images are handwritten and 21 images are printed documents.…”

Section: Experiments Setupmentioning

confidence: 99%

See 3 more Smart Citations

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In the context of historical document analysis, image binarization is a first important step, which separates foreground from background, despite common image degradations, such as faded ink,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

Section: Efficient Image Binarizationmentioning

confidence: 99%

Section: Experiments Setupmentioning

confidence: 99%

Section: Image Binarizationmentioning

confidence: 99%

Section: Experiments Setupmentioning

confidence: 99%

See 2 more Smart Citations

Efficient document image binarization using heterogeneous computing and parameter tuning

Westphal

Grahn

Lavesson

2018

IJDAR

View full text Add to dashboard Cite

show abstract

“…Such databases provide standard benchmarks that can be used in evaluating the performance of different DIAR systems [6]. For Latin and Asian languages, many standard databases have been collected.…”

Section: Introductionmentioning

confidence: 99%

A Printed PAW Image Database of Arabic Language for Document Analysis and Recognition

Bataineh¹

2017

J. ICT Res. Appl.

View full text Add to dashboard Cite

Abstract. Document image analysis and recognition are important topics in the field of artificial intelligence. In this context, the availability of a database with good script samples is an important requirement for machine-learning processes. For Latin and Asian languages many suitable databases exist. However, there is a shortage of databases with Arabic samples. In this work, a new database of printed Arabic text is introduced. The new concept of collecting sub-words (PAWs) instead of words or individual character samples was adopted. These PAWs constitute all words in the Arabic language. The collected database consists of 83,056 images of PAWs extracted from approximately 550,000 different words. Each sample is presented in the database in five font types: Thuluth, Naskh, Andalusi, Typing Machine, and Kufi. In total, the database consists of 415,280 images. Moreover, ground truth information is included with each PAW image to describe its occurrence number, occurrence frequency, positions and the shapes of the characters. This paper presents a statistical analysis of the frequency of each PAW in the Arabic language.

show abstract

Simultaneous Detection of Regular Patterns in Ancient Manuscripts Using GAN-Based Deep Unsupervised Segmentation

Tamrin

Cheriet

2021

Pattern Recognition. ICPR International Workshops and Challenges

View full text Add to dashboard Cite

ICFHR2014 Competition on Handwritten Document Image Binarization (H-DIBCO 2014)

Cited by 95 publications

References 12 publications

Efficient document image binarization using heterogeneous computing and parameter tuning

Efficient document image binarization using heterogeneous computing and parameter tuning

A Printed PAW Image Database of Arabic Language for Document Analysis and Recognition

Simultaneous Detection of Regular Patterns in Ancient Manuscripts Using GAN-Based Deep Unsupervised Segmentation

Contact Info

Product

Resources

About