Title | ||
---|---|---|
Scene Text Recognition Using Structure-Guided Character Detection and Linguistic Knowledge |
Abstract | ||
---|---|---|
Scene text recognition has inspired great interests from the computer vision community in recent years. In this paper, we propose a novel scene text-recognition method integrating structure-guided character detection and linguistic knowledge. We use part-based tree structure to model each category of characters so as to detect and recognize characters simultaneously. Since the character models make use of both the local appearance and global structure informations, the detection results are more reliable. For word recognition, we combine the detection scores and language model into the posterior probability of character sequence from the Bayesian decision view. The final word-recognition result is obtained by maximizing the character sequence posterior probability via Viterbi algorithm. Experimental results on a range of challenging public data sets (ICDAR 2003, ICDAR 2011, SVT) demonstrate that the proposed method achieves state-of-the-art performance both for character detection and word recognition. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/TCSVT.2014.2302522 | IEEE Trans. Circuits Syst. Video Techn. |
Keywords | Field | DocType |
character sequence,part-based tree-structured models (tsms),cropped word recognition,bayes methods,linguistic knowledge,posterior probability,character recognition,part-based tree-structured models,scene text recognition,integrating structure guided character detection,part based tree structure,word recognition,text analysis,global structure informations,handwriting recognition,word spotting,structure guided character detection,bayesian decision view,computer vision community,object recognition,feature extraction,image recognition | Computer science,Feature (machine learning),Artificial intelligence,Natural language processing,Intelligent word recognition,Language model,3D single-object recognition,Pattern recognition,Intelligent character recognition,Word recognition,Document processing,Sketch recognition,Linguistics | Journal |
Volume | Issue | ISSN |
24 | 7 | 1051-8215 |
Citations | PageRank | References |
10 | 0.48 | 35 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Cunzhao Shi | 1 | 272 | 19.31 |
Chunheng Wang | 2 | 639 | 58.68 |
Baihua Xiao | 3 | 377 | 40.56 |
Song Gao | 4 | 209 | 8.15 |
Jinlong Hu | 5 | 35 | 4.08 |