Please use this identifier to cite or link to this item:
|Type:||Artigo de periódico|
|Title:||SnooperText: A text detection system for automatic scenes indexing of urban scenes|
|Abstract:||We describe SNOOPERTEXT, an original detector for textual information embedded in photos of building facades (such as names of stores, products and services) that we developed for the iTowns urban geographic information project. SNOOPERTEXT locates candidate characters by using toggle-mapping image segmentation and character/non-character classification based on shape descriptors. The candidate characters are then grouped to form either candidate words or candidate text lines. These candidate regions are then validated by a text/non-text classifier using a HOG-based descriptor specifically tuned to single-line text regions. These operations are applied at multiple image scales in order to suppress irrelevant detail in character shapes and to avoid the use of overly large kernels in the segmentation. We show that SNOOPERTEXT outperforms other published state-of-the-art text detection algorithms on standard image benchmarks. We also describe two metrics to evaluate the end-to-end performance of text extraction systems, and show that the use of SNOOPERTEXT as a pre-filter significantly improves the performance of a general-purpose OCR algorithm when applied to photos of urban scenes. (C) 2013 Elsevier Inc. All rights reserved.|
Text region classification
Histogram of oriented gradients for text
Textual indexing in urban scene images
|Editor:||Academic Press Inc Elsevier Science|
|Citation:||Computer Vision And Image Understanding. Academic Press Inc Elsevier Science, v. 122, n. 92, n. 104, 2014.|
|Appears in Collections:||Unicamp - Artigos e Outros Documentos|
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.