The “ScribbleLens” Dutch Historical Handwriting Corpus

Dolfing, Hans; Bellegarda, Jerome R.; Chorowski, Jan; Marxer, Ricard; Laurent, Antoine

doi:10.1109/icfhr2020.2020.00023

Cited by 9 publications

(16 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [39], a corpus for automatic manuscript transcription was presented. This dataset contains 1K pages from early modern Dutch manuscripts spanning over 150 years with line, character, year, and writer ground truth.…”

Section: Scribblelensmentioning

confidence: 99%

A Survey of Historical Document Image Datasets

Nikolaidou¹,

Seuret²,

Mokayed³

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper presents a systematic literature review of image datasets for document image analysis, focusing on historical documents, such as handwritten manuscripts and early prints. Finding appropriate datasets for historical document analysis is a crucial prerequisite to facilitate research using different machine learning algorithms. However, because of the very large variety of the actual data (e.g., scripts, tasks, dates, support systems, and amount of deterioration), the different formats for data and label representation, and the different evaluation processes and benchmarks, finding appropriate datasets is a difficult task. This work fills this gap, presenting a meta-study on existing datasets. After a systematic selection process (according to PRISMA guidelines), we select 56 studies that are chosen based on different factors, such as the year of publication, number of methods implemented in the article, reliability of the chosen algorithms, dataset size, and journal outlet. We summarize each study by assigning it to one of three pre-defined tasks: document classification, layout structure, or semantic analysis. We present the statistics, document type, language, tasks, input visual aspects, and ground truth information for every dataset. In addition, we provide the benchmark tasks and results from these papers or recent competitions. We further discuss gaps and challenges in this domain. We advocate for providing conversion tools to common formats (e.g., COCO format for computer vision tasks) and always providing a set of evaluation metrics, instead of just one, to make results comparable across studies.

show abstract

Section: Scribblelensmentioning

confidence: 99%

A Survey of Historical Document Image Datasets

Nikolaidou¹,

Seuret²,

Mokayed³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…To benchmark the proposed system, we use three off-line handwritten corpora summarized in Table I. These are Scrib-bleLens [22], [15] in early Modern Dutch from the 16-17th century, the 16th century Spanish RODRIGO manuscript [14], [36], and IAM [13], [37] in modern English. All segmented lines and whole pages are binarized with black background and white signal.…”

Section: Corporamentioning

confidence: 99%

“…In this paper, we investigate a segmentation-free inference approach for whole pages of handwritten historical manuscripts such as in Figure 1. With the goal of a simple and effective recognition system, we prototype our approach on the IAM [13], RODRIGO [14] and ScribbleLens [15] corpora.…”

Section: Introductionmentioning

confidence: 99%

“…Last year, we published the ScribbleLens [22], [15] corpus with historical, handwritten, Dutch manuscripts. We investigated supervised and unsupervised representation learning [23].…”

Section: Introductionmentioning

confidence: 99%

“…As a first example, [24] consists of a combination of CNNs and BLSTMs similar to the CNNs plus Transformers and BLSTMs in this work and [15]. The system [24] is tested on images of sheet music, street views and word images.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Whole page recognition of historical handwriting

Dolfing¹

2020

Preprint

View full text Add to dashboard Cite

Historical handwritten documents guard an important part of human knowledge only within reach of a few scholars and experts. Recent developments in machine learning and handwriting research have the potential of rendering this information accessible and searchable to a larger audience. To this end, we investigate an end-to-end inference approach without text localization which takes a handwritten page and transcribes its full text. No explicit character, word or line segmentation is involved which is why we call this approach "segmentation free". We explore its robustness and accuracy compared to a line-by-line segmented approach based on the IAM, RODRIGO and ScribbleLens corpora, in three languages with handwriting styles spanning 400 years. We concentrate on model types and sizes which can be deployed on a hand-held or embedded device. We conclude that a whole page inference approach without text localization and segmentation is competitive.

show abstract