Fast key-word searching via embedding and active-DTW

Raid Saabni, Alex Bronstein

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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 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.

Original languageEnglish
Title of host publicationProceedings - 11th International Conference on Document Analysis and Recognition, ICDAR 2011
Pages68-72
Number of pages5
DOIs
StatePublished - 2011
Externally publishedYes
Event11th International Conference on Document Analysis and Recognition, ICDAR 2011 - Beijing, China
Duration: 18 Sep 201121 Sep 2011

Publication series

NameProceedings of the International Conference on Document Analysis and Recognition, ICDAR

Conference

Conference11th International Conference on Document Analysis and Recognition, ICDAR 2011
Country/TerritoryChina
CityBeijing
Period18/09/1121/09/11

Keywords

  • Dynamic Time Warping
  • Embedding
  • Handwriting Recognition
  • Nearest Neighbor
  • Word Searching

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this