---
_id: '18394'
abstract:
- lang: eng
  text: In this paper we present a novel approach for fast search of handwritten Arabic
    word-parts within large lexicons. The algorithm runs through three steps to achieve
    the required results. First it warps multiple appearances of each word-part in
    the lexicon for embedding into the same euclidean space. The embedding is done
    based on the warping path produced by the Dynamic Time Warping (DTW) process while
    calculating the similarity distance. In the next step, all samples of different
    word-parts are resampled uniformly to the same size. The kd-tree structure is
    used to store all shapes representing word parts in the lexicon. Fast approximation
    of k-nearest neighbors generates a short list of candidates to be presented to
    the next step. In the third step, the Active-DTW [15] algorithm is used to examine
    each sample in the short list and give final accurate results. We demonstrate
    our method on a database of 23,500 images of word-parts extracted from the IFN/ENIT
    database [6] and 22,000 images collected from 93 writers. Our method achieves
    a speedup of 5 orders of magnitude over the exact method, at the cost of only
    a 3.8% reduction in accuracy.
article_number: '6065278'
article_processing_charge: No
author:
- first_name: Raid
  full_name: Saabni, Raid
  last_name: Saabni
- first_name: Alexander
  full_name: Bronstein, Alexander
  id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
  last_name: Bronstein
  orcid: 0000-0001-9699-8730
citation:
  ama: 'Saabni R, Bronstein AM. Fast key-word searching via embedding and active-DTW.
    In: <i>2011 International Conference on Document Analysis and Recognition</i>.
    IEEE; 2011. doi:<a href="https://doi.org/10.1109/icdar.2011.23">10.1109/icdar.2011.23</a>'
  apa: 'Saabni, R., &#38; Bronstein, A. M. (2011). Fast key-word searching via embedding
    and active-DTW. In <i>2011 International Conference on Document Analysis and Recognition</i>.
    Beijing, China: IEEE. <a href="https://doi.org/10.1109/icdar.2011.23">https://doi.org/10.1109/icdar.2011.23</a>'
  chicago: Saabni, Raid, and Alex M. Bronstein. “Fast Key-Word Searching via Embedding
    and Active-DTW.” In <i>2011 International Conference on Document Analysis and
    Recognition</i>. IEEE, 2011. <a href="https://doi.org/10.1109/icdar.2011.23">https://doi.org/10.1109/icdar.2011.23</a>.
  ieee: R. Saabni and A. M. Bronstein, “Fast key-word searching via embedding and
    active-DTW,” in <i>2011 International Conference on Document Analysis and Recognition</i>,
    Beijing, China, 2011.
  ista: Saabni R, Bronstein AM. 2011. Fast key-word searching via embedding and active-DTW.
    2011 International Conference on Document Analysis and Recognition. 11th International
    Conference on Document Analysis and Recognition, 6065278.
  mla: Saabni, Raid, and Alex M. Bronstein. “Fast Key-Word Searching via Embedding
    and Active-DTW.” <i>2011 International Conference on Document Analysis and Recognition</i>,
    6065278, IEEE, 2011, doi:<a href="https://doi.org/10.1109/icdar.2011.23">10.1109/icdar.2011.23</a>.
  short: R. Saabni, A.M. Bronstein, in:, 2011 International Conference on Document
    Analysis and Recognition, IEEE, 2011.
conference:
  end_date: 2011-09-21
  location: Beijing, China
  name: 11th International Conference on Document Analysis and Recognition
  start_date: 2011-09-18
date_created: 2024-10-15T11:20:54Z
date_published: 2011-11-03T00:00:00Z
date_updated: 2024-12-04T12:08:48Z
day: '03'
doi: 10.1109/icdar.2011.23
extern: '1'
language:
- iso: eng
month: '11'
oa_version: None
publication: 2011 International Conference on Document Analysis and Recognition
publication_identifier:
  eissn:
  - 2379-2140
  isbn:
  - '9781457713507'
publication_status: published
publisher: IEEE
quality_controlled: '1'
scopus_import: '1'
status: public
title: Fast key-word searching via embedding and active-DTW
type: conference
user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87
year: '2011'
...