2011 · 13 citations · 9 references
ComputingComputer ScienceComputational LinguisticsComputer VisionNatural Language ProcessingObject DetectionOptical Character RecognitionPattern RecognitionText ClusteringText MiningText SegmentationBenchmark DatasetsConditional Random FieldsHeuristicsText Detection
In this paper, a new hybrid method for text detection in natural scene is proposed. According the linguistics rules, this algorithm mainly consists of three parts. First, considering both unary property and binary relationship, the conditional random field (CRF) model is introduced for text region detection. Second, connected components (CCs) are extracted by similar stroke width, and filtered coarsely by stroke width analysis. Candidate CCs are then filtered by candidate regions. Finally, text CCs are clustered into words by geometry heuristics. Experiments on the public benchmark ICDAR 2003 dataset show that proposed algorithm can detect text with various font sizes in natural scene.
9
Predicting good probabilities with supervised learning
Alexandru Niculescu-Mizil, Rich Caruana · 2005 · 1.6K citations
Detecting text in natural scenes with stroke width transform
Boris Epshtein, Eyal Ofek, Yonatan Wexler · 2010 · 1.5K citations
Rick Szeliski, Ramin Zabih, Daniel Scharstein et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2008 · 981 citations · Full text
Detecting and reading text in natural scenes
Xiang-Rong Chen, Alan Yuille · 2004 · 635 citations
ICDAR 2003 robust reading competitions
Simon M. Lucas, Alex Panaretos, Luis Sosa et al. · 2005 · 565 citations