Scene Text Recognition and Retrieval for Large Lexicons - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2015

Scene Text Recognition and Retrieval for Large Lexicons


In this paper we propose a framework for recognition and retrieval tasks in the context of scene text images. In contrast to many of the recent works, we focus on the case where an image-specific list of words, known as the small lexicon setting, is unavailable. We present a conditional random field model defined on potential character locations and the interactions between them. Observing that the interaction potentials computed in the large lexicon setting are less effective than in the case of a small lexicon, we propose an iterative method, which alternates between finding the most likely solution and refining the interaction po-tentials. We evaluate our method on public datasets and show that it improves over baseline and state-of-the-art approaches. For example, we obtain nearly 15% improvement in recognition accuracy and precision for our retrieval task over baseline methods on the IIIT-5K word dataset, with a large lexicon containing 0.5 million words.
Fichier principal
Vignette du fichier
roy14.pdf (637.94 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-01088739 , version 1 (28-11-2014)



Udit Roy, Anand Mishra, Karteek Alahari, C.V. Jawahar. Scene Text Recognition and Retrieval for Large Lexicons. ACCV - Asian Conference on Computer Vision, Nov 2014, Singapore, Singapore. pp.494-508, ⟨10.1007/978-3-319-16865-4_32⟩. ⟨hal-01088739⟩
284 View
480 Download



Gmail Mastodon Facebook X LinkedIn More