uu.seUppsala universitets publikasjoner
Endre søk
Link to record
Permanent link

Direct link
BETA
Publikasjoner (10 av 12) Visa alla publikasjoner
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.
Åpne denne publikasjonen i ny fane eller vindu >>Creating an Atlas over Handwritten Script Signs
2019 (engelsk)Inngår i: Digital Humanities in the Nordic Countries, 2019Konferansepaper, Poster (with or without abstract) (Fagfellevurdert)
HSV kategori
Forskningsprogram
Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-373517 (URN)
Konferanse
DHN 2019, March 6–8, Copenhagen, Denmark
Tilgjengelig fra: 2019-01-15 Laget: 2019-01-15 Sist oppdatert: 2019-01-17
Hast, A., Lind, M. & Vats, E. (2019). Embedded Prototype Subspace Classification: A subspace learning framework. In: Computer Analysis of Images and Patterns: . Paper presented at CAIP 2019, September 2–6, Salerno, Italy. Springer
Åpne denne publikasjonen i ny fane eller vindu >>Embedded Prototype Subspace Classification: A subspace learning framework
2019 (engelsk)Inngår i: Computer Analysis of Images and Patterns, Springer, 2019Konferansepaper, Oral presentation with published abstract (Fagfellevurdert)
sted, utgiver, år, opplag, sider
Springer, 2019
Serie
Lecture Notes in Computer Science
HSV kategori
Identifikatorer
urn:nbn:se:uu:diva-389452 (URN)
Konferanse
CAIP 2019, September 2–6, Salerno, Italy
Tilgjengelig fra: 2019-07-14 Laget: 2019-07-14 Sist oppdatert: 2019-07-22
Hast, A., Lind, M. & Vats, E. (2019). Embedded Prototype Subspace Classification: A subspace learning framework. In: Computer Analysis of Images and Patterns: . Paper presented at CAIP 2019, September 2–6, Salerno, Italy (pp. 581-592). Springer
Åpne denne publikasjonen i ny fane eller vindu >>Embedded Prototype Subspace Classification: A subspace learning framework
2019 (engelsk)Inngår i: Computer Analysis of Images and Patterns, Springer, 2019, s. 581-592Konferansepaper, Publicerat paper (Fagfellevurdert)
sted, utgiver, år, opplag, sider
Springer, 2019
Serie
Lecture Notes in Computer Science
HSV kategori
Identifikatorer
urn:nbn:se:uu:diva-393257 (URN)
Konferanse
CAIP 2019, September 2–6, Salerno, Italy
Tilgjengelig fra: 2019-09-18 Laget: 2019-09-18 Sist oppdatert: 2019-09-18
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
Åpne denne publikasjonen i ny fane eller vindu >>In search of the scribe: Letter spotting as a tool for identifying scribes in large handwritten text corpora
2019 (engelsk)Inngår i: Human IT, ISSN 1402-1501, E-ISSN 1402-151X, Vol. 14, nr 2, s. 95-120Artikkel i tidsskrift (Fagfellevurdert) Published
HSV kategori
Forskningsprogram
Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-373929 (URN)
Tilgjengelig fra: 2019-01-17 Laget: 2019-01-17 Sist oppdatert: 2019-01-17bibliografisk kontrollert
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
Åpne denne publikasjonen i ny fane eller vindu >>Making large collections of handwritten material easily accessible and searchable
2019 (engelsk)Inngår i: Digital Libraries: Supporting Open Science, Springer, 2019, s. 18-28Konferansepaper, Publicerat paper (Fagfellevurdert)
sted, utgiver, år, opplag, sider
Springer, 2019
Serie
Communications in Computer and Information Science ; 988
HSV kategori
Forskningsprogram
Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-373515 (URN)10.1007/978-3-030-11226-4_2 (DOI)978-3-030-11225-7 (ISBN)
Konferanse
IRCDL 2019, January 31 – February 1, Pisa, Italy
Tilgjengelig fra: 2019-01-15 Laget: 2019-01-15 Sist oppdatert: 2019-01-17bibliografisk kontrollert
Hast, A., Lind, M. & Vats, E. (2019). Subspace Learning and Classification. In: Proc. 3rd Swedish Symposium on Deep Learning: . Paper presented at SSDL 2019, June 10–11, Norrköping, Sweden.
Åpne denne publikasjonen i ny fane eller vindu >>Subspace Learning and Classification
2019 (engelsk)Inngår i: Proc. 3rd Swedish Symposium on Deep Learning, 2019Konferansepaper, Poster (with or without abstract) (Annet vitenskapelig)
HSV kategori
Identifikatorer
urn:nbn:se:uu:diva-389451 (URN)
Konferanse
SSDL 2019, June 10–11, Norrköping, Sweden
Tilgjengelig fra: 2019-07-14 Laget: 2019-07-14 Sist oppdatert: 2019-07-22
Vats, E., Hast, A. & Fornés, A. (2019). Training-Free and Segmentation-Free Word Spotting using Feature Matching and Query Expansion. In: Proc. 15th International Conference on Document Analysis and Recognition: . Paper presented at ICDAR 2019, September 20–25, Sydney, Australia.
Åpne denne publikasjonen i ny fane eller vindu >>Training-Free and Segmentation-Free Word Spotting using Feature Matching and Query Expansion
2019 (engelsk)Inngår i: Proc. 15th International Conference on Document Analysis and Recognition, 2019Konferansepaper, Oral presentation with published abstract (Fagfellevurdert)
HSV kategori
Forskningsprogram
Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-389453 (URN)
Konferanse
ICDAR 2019, September 20–25, Sydney, Australia
Tilgjengelig fra: 2019-07-14 Laget: 2019-07-14 Sist oppdatert: 2019-07-22
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.
Åpne denne publikasjonen i ny fane eller vindu >>Exploring the Applicability of Capsule Networks for WordSpotting in Historical Handwritten Manuscripts
2018 (engelsk)Konferansepaper, Oral presentation only (Annet vitenskapelig)
HSV kategori
Forskningsprogram
Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-373512 (URN)
Konferanse
Swedish Symposium on Deep Learning 2018
Tilgjengelig fra: 2019-01-15 Laget: 2019-01-15 Sist oppdatert: 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.
Åpne denne publikasjonen i ny fane eller vindu >>Extracting script features from a large corpus of handwritten documents
2018 (engelsk)Inngår i: Digital Humanities in the Nordic Countries: Book of Abstracts, 2018Konferansepaper, Oral presentation with published abstract (Fagfellevurdert)
HSV kategori
Forskningsprogram
Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-356773 (URN)
Konferanse
DHN 2018, March 7–9, Helsinki, Finland
Tilgjengelig fra: 2018-08-06 Laget: 2018-08-06 Sist oppdatert: 2018-11-10bibliografisk kontrollert
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.
Åpne denne publikasjonen i ny fane eller vindu >>Radial line Fourier descriptor for historical handwritten text representation
2018 (engelsk)Inngår i: Proc. 26th International Conference on Computer Graphics: Visualization and Computer Vision, 2018Konferansepaper, Publicerat paper (Annet vitenskapelig)
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.

HSV kategori
Forskningsprogram
Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-351943 (URN)
Konferanse
WSCG 2018, May 28 – June 1, Pilsen, Czech Republic
Tilgjengelig fra: 2018-05-31 Laget: 2018-05-31 Sist oppdatert: 2018-09-20bibliografisk kontrollert
Organisasjoner
Identifikatorer
ORCID-id: ORCID iD iconorcid.org/0000-0003-4480-3158