Exploring Interest Points and local description for Word Spotting Application on Historical Handwriting images

Christine Largeron 1 Véronique Eglin 2 Christophe Garcia 2 Antony Mckenna 3 Peng Wang 2
1 LHC - Laboratoire Hubert Curien [Saint Etienne]
2 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
3 IHPC - Institut d'Histoire de la Pensée Classique
Abstract : Recently, local features especially point descriptors have re- ceived lots of interest in the computer vision and image processing com- munities. SIFT and SURF descriptors have shown their powerful useful- ness on natural object recognition and classi cation. However, the use of local descriptors such as SIFT and SURF is still not very common in handwritten document image analysis now. In this paper, we propose an investigation on the description of handwriting by applying di erent interest points and local descriptors on historical handwritten images in the context of a coarse-to- ne segmentation-free word spotting method. The observation and analysis based on the experimental results can help optimizing the description of handwriting according to di erent applica- tions.
Keywords : word spotting historical handwritten document interest points Shape Context SIFT SURF
Document type :
Conference papers
Complete list of metadatas
https://hal-ujm.archives-ouvertes.fr/ujm-00870695
Contributor : Christine Largeron <>
Submitted on : Monday, October 7, 2013 - 7:46:17 PM
Last modification on : Friday, January 11, 2019 - 5:08:47 PM

Identifiers

  • HAL Id : ujm-00870695, version 1

Collections

UNIV-ST-ETIENNE | ENS-LYON | UNIV-LYON2 | EC-LYON | LIRIS | LAHC | PRES_CLERMONT | IHPC | INSA-LYON | UNIV-LYON1 | CERHAC | IOGS | PARISTECH | INSA-GROUPE | LABEXIMU

Citation

Christine Largeron, Véronique Eglin, Christophe Garcia, Antony Mckenna, Peng Wang. Exploring Interest Points and local description for Word Spotting Application on Historical Handwriting images. International Conference on Computer Analysis on Images and Patterns, CAIP 2013, Aug 2013, york, United Kingdom. pp.408-415. ⟨ujm-00870695⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

294

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD