KeyWord Spotting using Siamese Triplet Deep Neural Networks - Archive ouverte HAL Access content directly
Conference Papers Year :

KeyWord Spotting using Siamese Triplet Deep Neural Networks

Yasmine Serdouk
  • Function : Author
  • PersonId : 1048825

Abstract

Deep neural networks has shown great success incomputer vision fields by achieving considerable state-of-the-artresults and are beginning to arouse big interest in the documentanalysis community. In this paper, we present a novel siamesedeep network of three inputs that allows retrieving the mostsimilar words to a given query. The proposed system followsa query-by-example approach according to a segmentation-based technique and aims to learn suitable representations ofhandwritten word images, for which a simple Euclidean distancecould perform the matching. The results obtained for the GeorgeWashington dataset show the potential and the effectiveness ofthe proposed keyword spotting system
Not file

Dates and versions

hal-02155381 , version 1 (13-06-2019)

Identifiers

Cite

Véronique Eglin, Yasmine Serdouk, Stéphane Bres, Mylène Pardoen. KeyWord Spotting using Siamese Triplet Deep Neural Networks. International Conference on Document Analysis and Recognition, ICDAR, Sep 2019, Sydney, Australia. ⟨10.1109/ICDAR.2019.00187⟩. ⟨hal-02155381⟩
337 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More