Tampere University of Technology

TUTCRIS Research Portal

Towards visual words to words

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


Original languageEnglish
Title of host publication2015 13th International Conference on Document Analysis and Recognition (ICDAR)
Number of pages5
ISBN (Print)978-1-4799-1805-8
Publication statusPublished - 1 Aug 2015
Publication typeA4 Article in a conference publication
EventInternational Conference on Document Analysis and Recognition -
Duration: 1 Jan 1900 → …


ConferenceInternational Conference on Document Analysis and Recognition
Period1/01/00 → …


We address the problem of text localization and retrieval in real world images. We are first to study the retrieval of text images, i.e. the selection of images containing text in large collections at high speed. We propose a novel representation, textual visual words, which describe text by generic visual words that geometrically consistently predict bottom and top lines of text. The visual words are discretized SIFT descriptors of Hessian features. The features may correspond to various structures present in the text - character fragments, individual characters or their arrangements. The textual words representation is invariant to affine transformation of the image and local linear change of intensity. Experiments demonstrate that the proposed method outperforms the state-of-the-art on the MS dataset. The proposed method detects blurry, small font, low contrast, noisy text from real world images.


  • image representation, image retrieval, text detection, transforms, Hessian features, MS dataset, bag of words representation, discretized SIFT descriptors, text localization, text retrieval, text-character fragments, textual visual words, textual words representation, Databases, Robustness, Silicon, Yttrium

Publication forum classification

Field of science, Statistics Finland