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

Direct link
BETA
Publications (10 of 50) 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
Hast, A., Sablina, V. A., Sintorn, I.-M. & Kylberg, G. (2018). A fast Fourier based feature descriptor and a cascade nearest neighbour search with an efficient matching pipeline for mosaicing of microscopy images. Pattern Recognition and Image Analysis, 28(2), 261-272
Open this publication in new window or tab >>A fast Fourier based feature descriptor and a cascade nearest neighbour search with an efficient matching pipeline for mosaicing of microscopy images
2018 (English)In: Pattern Recognition and Image Analysis, ISSN 1054-6618, Vol. 28, no 2, p. 261-272Article in journal (Refereed) Published
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-354147 (URN)10.1134/S1054661818020050 (DOI)
Available from: 2018-06-16 Created: 2018-06-19 Last updated: 2018-06-20Bibliographically approved
Hast, A. & Vats, E. (2018). An intelligent user interface for efficient semi-automatic transcription of historical handwritten documents. In: Proc. 23rd International Conference on Intelligent User Interfaces Companion: . Paper presented at IUI 2018, March 7–11, Tokyo, Japan. New York: ACM Press, Article ID 48.
Open this publication in new window or tab >>An intelligent user interface for efficient semi-automatic transcription of historical handwritten documents
2018 (English)In: Proc. 23rd International Conference on Intelligent User Interfaces Companion, New York: ACM Press, 2018, article id 48Conference paper, Published paper (Refereed)
Abstract [en]

Transcription of large-scale historical handwritten document images is a tedious task. Machine learning techniques, such as deep learning, are popularly used for quick transcription, but often require a substantial amount of pre-transcribed word examples for training. Instead of line-by-line word transcription, this paper proposes a simple training-free gamification strategy where all occurrences of each arbitrarily selected word is transcribed once, using an intelligent user interface implemented in this work. The proposed approach offers a fast and user-friendly semi-automatic transcription that allows multiple users to work on the same document collection simultaneously.

Place, publisher, year, edition, pages
New York: ACM Press, 2018
National Category
Computer and Information Sciences
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-345637 (URN)10.1145/3180308.3180357 (DOI)000458680100048 ()978-1-4503-5571-1 (ISBN)
Conference
IUI 2018, March 7–11, Tokyo, Japan
Projects
eSSENCE
Funder
Riksbankens Jubileumsfond, NHS14-2068:1eSSENCE - An eScience Collaboration
Available from: 2018-03-05 Created: 2018-03-12 Last updated: 2019-03-11Bibliographically 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
Singh, P., Vats, E. & Hast, A. (2018). Learning surrogate models of document image quality metrics for automated document image processing. In: Proc. 13th IAPR Workshop on Document Analysis Systems: . Paper presented at DAS 2018, April 24–27, Austria, Vienna (pp. 67-72). IEEE
Open this publication in new window or tab >>Learning surrogate models of document image quality metrics for automated document image processing
2018 (English)In: Proc. 13th IAPR Workshop on Document Analysis Systems, IEEE, 2018, p. 67-72Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
IEEE, 2018
National Category
Computer Sciences
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-351317 (URN)10.1109/DAS.2018.14 (DOI)978-1-5386-3346-5 (ISBN)
Conference
DAS 2018, April 24–27, Austria, Vienna
Projects
eSSENCE
Available from: 2018-06-25 Created: 2018-05-23 Last updated: 2018-07-09Bibliographically approved
Hast, A. & Vats, E. (2018). Radial line Fourier descriptor for historical handwritten text representation. Journal of WSCG, 26(1), 31-40
Open this publication in new window or tab >>Radial line Fourier descriptor for historical handwritten text representation
2018 (English)In: Journal of WSCG, ISSN 1213-6972, E-ISSN 1213-6964, Vol. 26, no 1, p. 31-40Article in journal (Refereed) Published
National Category
Computer Sciences
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-357248 (URN)10.24132/JWSCG.2018.26.1.4 (DOI)
Projects
eSSENCE
Available from: 2018-08-14 Created: 2018-08-14 Last updated: 2018-08-19Bibliographically 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
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-1054-2754

Search in DiVA

Show all publications