uu.seUppsala University Publications
Change search
Link to record
Permanent link

Direct link
BETA
Publications (8 of 8) Show all publications
Hast, A., Mårtensson, L., Vats, E. & Heil, R. (2019). Creating an Atlas over Handwritten Script Signs. In: Digital Humanities in the Nordic Countries: . Paper presented at DHN 2019, March 6–8, Copenhagen, Denmark.
Open this publication in new window or tab >>Creating an Atlas over Handwritten Script Signs
2019 (English)In: Digital Humanities in the Nordic Countries, 2019Conference paper, Poster (with or without abstract) (Refereed)
National Category
Computer Sciences
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-373517 (URN)
Conference
DHN 2019, March 6–8, Copenhagen, Denmark
Available from: 2019-01-15 Created: 2019-01-15 Last updated: 2019-01-17
Mårtensson, L., Vats, E., Hast, A. & Fornés, A. (2019). In search of the scribe: Letter spotting as a tool for identifying scribes in large handwritten text corpora. Human IT, 14(2), 95-120
Open this publication in new window or tab >>In search of the scribe: Letter spotting as a tool for identifying scribes in large handwritten text corpora
2019 (English)In: Human IT, ISSN 1402-1501, E-ISSN 1402-151X, Vol. 14, no 2, p. 95-120Article in journal (Refereed) Published
National Category
Computer Sciences
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-373929 (URN)
Available from: 2019-01-17 Created: 2019-01-17 Last updated: 2019-01-17Bibliographically approved
Hast, A., Cullhed, P., Vats, E. & Abrate, M. (2019). Making large collections of handwritten material easily accessible and searchable. In: Digital Libraries: Supporting Open Science. Paper presented at IRCDL 2019, January 31 – February 1, Pisa, Italy (pp. 18-28). Springer
Open this publication in new window or tab >>Making large collections of handwritten material easily accessible and searchable
2019 (English)In: Digital Libraries: Supporting Open Science, Springer, 2019, p. 18-28Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
Springer, 2019
Series
Communications in Computer and Information Science ; 988
National Category
Computer and Information Sciences
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-373515 (URN)10.1007/978-3-030-11226-4_2 (DOI)978-3-030-11225-7 (ISBN)
Conference
IRCDL 2019, January 31 – February 1, Pisa, Italy
Available from: 2019-01-15 Created: 2019-01-15 Last updated: 2019-01-17Bibliographically approved
Heil, R., Vats, E. & Hast, A. (2018). Exploring the Applicability of Capsule Networks for WordSpotting in Historical Handwritten Manuscripts. In: : . Paper presented at Swedish Symposium on Deep Learning 2018.
Open this publication in new window or tab >>Exploring the Applicability of Capsule Networks for WordSpotting in Historical Handwritten Manuscripts
2018 (English)Conference paper, Oral presentation only (Other academic)
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-373512 (URN)
Conference
Swedish Symposium on Deep Learning 2018
Available from: 2019-01-15 Created: 2019-01-15 Last updated: 2019-01-17
Vats, E., Hast, A. & Mårtensson, L. (2018). Extracting script features from a large corpus of handwritten documents. In: Digital Humanities in the Nordic Countries: Book of Abstracts. Paper presented at DHN 2018, March 7–9, Helsinki, Finland.
Open this publication in new window or tab >>Extracting script features from a large corpus of handwritten documents
2018 (English)In: Digital Humanities in the Nordic Countries: Book of Abstracts, 2018Conference paper, Oral presentation with published abstract (Refereed)
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-356773 (URN)
Conference
DHN 2018, March 7–9, Helsinki, Finland
Available from: 2018-08-06 Created: 2018-08-06 Last updated: 2018-11-10Bibliographically approved
Hast, A. & Vats, E. (2018). Radial line Fourier descriptor for historical handwritten text representation. In: Proc. 26th International Conference on Computer Graphics: Visualization and Computer Vision. Paper presented at WSCG 2018, May 28 – June 1, Pilsen, Czech Republic.
Open this publication in new window or tab >>Radial line Fourier descriptor for historical handwritten text representation
2018 (English)In: Proc. 26th International Conference on Computer Graphics: Visualization and Computer Vision, 2018Conference paper, Published paper (Other academic)
Abstract [en]

Automatic recognition of historical handwritten manuscripts is a daunting task due to paper degradation over time. Recognition-free retrieval or word spotting is popularly used for information retrieval and digitization of the historical handwritten documents. However, the performance of word spotting algorithms depends heavily on feature detection and representation methods. Although there exist popular feature descriptors such as Scale Invariant Feature Transform (SIFT) and Speeded Up Robust Features (SURF), the invariant properties of these descriptors amplify the noise in the degraded document images, rendering them more sensitive to noise and complex characteristics of historical manuscripts. Therefore, an efficient and relaxed feature descriptor is required as handwritten words across different documents are indeed similar, but not identical. This paper introduces a Radial Line Fourier (RLF) descriptor for handwritten word representation, with a short feature vector of 32 dimensions. A segmentation-free and training-free handwritten word spotting method is studied herein that relies on the proposed RLF descriptor, takes into account different keypoint representations and uses a simple preconditioner-based feature matching algorithm. The effectiveness of the RLF descriptor for segmentation-free handwritten word spotting is empirically evaluated on well-known historical handwritten datasets using standard evaluation measures.

National Category
Computer Sciences Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-351943 (URN)
Conference
WSCG 2018, May 28 – June 1, Pilsen, Czech Republic
Available from: 2018-05-31 Created: 2018-05-31 Last updated: 2018-09-20Bibliographically approved
Heil, R., Vats, E. & Hast, A. (2018). Word Spotting in Historical Handwritten Manuscripts using Capsule Networks. In: : . Paper presented at Bibliotheca Baltica Symposium.
Open this publication in new window or tab >>Word Spotting in Historical Handwritten Manuscripts using Capsule Networks
2018 (English)Conference paper, Poster (with or without abstract) (Other academic)
Abstract [en]

Word spotting is popularly used for digitisation and transcription of historical handwritten documents. Recently, deep learning based methods have dominated the current state-of-the-art in learning-based word spotting. However, deep learning architectures such as Convolutional Neural Networks (CNNs) require a large amount of training data, and suffer from translation invariance. Capsule Networks (CapsNet) have been recently introduced as a data-efficient alternative to CNNs. This work explores the applicability of CapsNets for segmentation-based word spotting, and is the first such effort in the Handwritten Text Recognition (HTR) community to the best of authors' knowledge. The effectiveness of CapsNets will be empirically evaluated on well-known historical handwritten datasets using standard evaluation measures. The impact of varying amounts of training data on the recognition performance will be investigated, along with a comparison with the state-of-the-art methods.

National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-373514 (URN)
Conference
Bibliotheca Baltica Symposium
Available from: 2019-01-15 Created: 2019-01-15 Last updated: 2019-01-17
Vats, E. & Hast, A. (2017). On-the-fly historical handwritten text annotation. In: 14th IAPR International Conference on Document Analysis and Recognition (ICDAR): . Paper presented at 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, Japan, November 09-15, 2017 (pp. 10-14). IEEE
Open this publication in new window or tab >>On-the-fly historical handwritten text annotation
2017 (English)In: 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), IEEE, 2017, p. 10-14Conference paper, Published paper (Refereed)
Abstract [en]

The performance of information retrieval algorithms depends upon the availability of ground truth labels annotated by experts. This is an important prerequisite, and difficulties arise when the annotated ground truth labels are incorrect or incomplete due to high levels of degradation. To address this problem, this paper presents a simple method to perform on-the-fly annotation of degraded historical handwritten text in ancient manuscripts. The proposed method aims at quick generation of ground truth and correction of inaccurate annotations such that the bounding box perfectly encapsulates the word, and contains no added noise from the background or surroundings. This method will potentially be of help to historians and researchers in generating and correcting word labels in a document dynamically. The effectiveness of the annotation method is empirically evaluated on an archival manuscript collection from well-known publicly available datasets.

Place, publisher, year, edition, pages
IEEE, 2017
Series
Proceedings of the International Conference on Document Analysis and Recognition, E-ISSN 2379-2140
National Category
Computer Sciences
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-334296 (URN)10.1109/ICDAR.2017.374 (DOI)000428139100002 ()978-1-5386-3586-5 (ISBN)
Conference
14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, Japan, November 09-15, 2017
Funder
Riksbankens Jubileumsfond, NHS14-2068:1eSSENCE - An eScience Collaboration
Available from: 2018-01-29 Created: 2017-11-22 Last updated: 2019-02-28Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-4480-3158

Search in DiVA

Show all publications