Paper Info
Title
Text Localization in Real-World Images Using Efficiently Pruned Exhaustive Search
Abstract
An efficient method for text localization and recognition in real-world images is proposed. Thanks to effective pruning, it is able to exhaustively search the space of all character sequences in real time (200ms on a 640 × 480 image). The method exploits higher-order properties of text such as word text lines. We demonstrate that the grouping stage plays a key role in the text localization performance and that a robust and precise grouping stage is able to compensate errors of the character detector. The method includes a novel selector of Maximally Stable Extremal Regions (MSER) which exploits region topology. Experimental validation shows that 95.7% characters in the ICDAR dataset are detected using the novel selector of MSERs with a low sensitivity threshold. The proposed method was evaluated on the standard ICDAR 2003 dataset where it achieved state-of-the-art results in both text localization and recognition.
Year
DOI
Venue
2011
10.1109/ICDAR.2011.144
Document Analysis and Recognition
Keywords
Field
DocType
object recognition,text analysis,ICDAR dataset,character detector,error compensation,grouping stage,maximally stable extremal regions,pruned exhaustive search,real-world images,region topology,text localization,text recognition,word text lines,real-world images,text localization,text-in-the-wild
Computer vision,Text mining,Brute-force search,Character recognition,Pattern recognition,Computer science,Robustness (computer science),Maximally stable extremal regions,Artificial intelligence,Detector,Text recognition,Cognitive neuroscience of visual object recognition
Conference
ISSN
ISBN
Citations 
1520-5363 E-ISBN : 978-0-7695-4520-2
978-0-7695-4520-2
78
PageRank 
References 
Authors
2.86
11
2
Name
Order
Citations
PageRank
Lukas Neumann155518.65
Jiri Matas228314.03