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

Direct link
BETA
Publications (10 of 46) Show all publications
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., 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, 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-368705 (URN)10.1134/S1054661818020050 (DOI)
Available from: 2018-12-06 Created: 2018-12-06 Last updated: 2018-12-06
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)
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)978-1-4503-5571-1 (ISBN)
Conference
IUI 2018, March 7–11, Tokyo, Japan
Projects
eSSENCE
Available from: 2018-03-05 Created: 2018-03-12 Last updated: 2018-03-16Bibliographically approved
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
Hast, A., Cullhed, P. & Vats, E. (2018). TexT – Text extractor tool for handwritten document transcription and annotation. In: Digital Libraries and Multimedia Archives: . Paper presented at 14th Italian Research Conference on Digital Libraries (IRCDL) 2018, January 25–26, Udine, Italy (pp. 81-92). Springer
Open this publication in new window or tab >>TexT – Text extractor tool for handwritten document transcription and annotation
2018 (English)In: Digital Libraries and Multimedia Archives, Springer, 2018, p. 81-92Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents a framework for semi-automatic transcription of large-scale historical handwritten documents and proposes a simple user-friendly text extractor tool, TexT for transcription. The proposed approach provides a quick and easy transcription of text using computer assisted interactive technique. The algorithm finds multiple occurrences of the marked text on-the-fly using a word spotting system. TexT is also capable of performing on-the-fly annotation of handwritten text with automatic generation of ground truth labels, and dynamic adjustment and correction of user generated bounding box annotations with the word being perfectly encapsulated. The user can view the document and the found words in the original form or with background noise removed for easier visualization of transcription results. The effectiveness of TexT is demonstrated on an archival manuscript collection from well-known publicly available dataset.

Place, publisher, year, edition, pages
Springer, 2018
Series
Communications in Computer and Information Science ; 806
Keywords
Handwritten text recognition, Transcription Annotation, TexT, Word spotting, Historical documents
National Category
Computer and Information Sciences
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-343160 (URN)10.1007/978-3-319-73165-0_8 (DOI)000434481000008 ()978-3-319-73164-3 (ISBN)978-3-319-73165-0 (ISBN)
Conference
14th Italian Research Conference on Digital Libraries (IRCDL) 2018, January 25–26, Udine, Italy
Projects
eSSENCE
Funder
Riksbankens Jubileumsfond, NHS14-2068:1eSSENCE - An eScience Collaboration
Available from: 2017-12-21 Created: 2018-02-26 Last updated: 2018-10-22Bibliographically approved
Matuszewski, D. J., Hast, A., Wählby, C. & Sintorn, I.-M. (2017). A short feature vector for image matching: The Log-Polar Magnitude feature descriptor. PLoS ONE, 12(11), Article ID e0188496.
Open this publication in new window or tab >>A short feature vector for image matching: The Log-Polar Magnitude feature descriptor
2017 (English)In: PLoS ONE, ISSN 1932-6203, E-ISSN 1932-6203, Vol. 12, no 11, article id e0188496Article in journal (Refereed) Published
Abstract [en]

The choice of an optimal feature detector-descriptor combination for image matching often depends on the application and the image type. In this paper, we propose the Log-Polar Magnitude feature descriptor—a rotation, scale, and illumination invariant descriptor that achieves comparable performance to SIFT on a large variety of image registration problems but with much shorter feature vectors. The descriptor is based on the Log-Polar Transform followed by a Fourier Transform and selection of the magnitude spectrum components. Selecting different frequency components allows optimizing for image patterns specific for a particular application. In addition, by relying only on coordinates of the found features and (optionally) feature sizes our descriptor is completely detector independent. We propose 48- or 56-long feature vectors that potentially can be shortened even further depending on the application. Shorter feature vectors result in better memory usage and faster matching. This combined with the fact that the descriptor does not require a time-consuming feature orientation estimation (the rotation invariance is achieved solely by using the magnitude spectrum of the Log-Polar Transform) makes it particularly attractive to applications with limited hardware capacity. Evaluation is performed on the standard Oxford dataset and two different microscopy datasets; one with fluorescence and one with transmission electron microscopy images. Our method performs better than SURF and comparable to SIFT on the Oxford dataset, and better than SIFT on both microscopy datasets indicating that it is particularly useful in applications with microscopy images.

National Category
Other Engineering and Technologies
Identifiers
urn:nbn:se:uu:diva-335460 (URN)10.1371/journal.pone.0188496 (DOI)000416841900060 ()
Funder
EU, European Research Council, ERC-CoG-2015Swedish Research Council, 2014-6075
Available from: 2017-12-05 Created: 2017-12-05 Last updated: 2018-03-09Bibliographically approved
Hast, A., Kylberg, G. & Sintorn, I.-M. (2017). An efficient descriptor based on radial line integration for fast non invariant matching and registration of microscopy images. In: Advanced Concepts for Intelligent Vision Systems: . Paper presented at ACIVS 2017, September 18–21, Antwerp, Belgium (pp. 723-734). Springer
Open this publication in new window or tab >>An efficient descriptor based on radial line integration for fast non invariant matching and registration of microscopy images
2017 (English)In: Advanced Concepts for Intelligent Vision Systems, Springer, 2017, p. 723-734Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
Springer, 2017
Series
Lecture Notes in Computer Science ; 10617
National Category
Computer Sciences
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-335366 (URN)10.1007/978-3-319-70353-4_61 (DOI)978-3-319-70352-7 (ISBN)
Conference
ACIVS 2017, September 18–21, Antwerp, Belgium
Available from: 2017-11-23 Created: 2017-12-04 Last updated: 2018-01-13Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-1054-2754

Search in DiVA

Show all publications