메뉴 건너뛰기




Volumn 25, Issue 6, 2016, Pages 2789-2802

Strokelets: A Learned Multi-Scale Mid-Level Representation for Scene Text Recognition

Author keywords

midlevel representation; multi scale representation; natural images; scene text detection; Scene text recognition

Indexed keywords

IMAGE PROCESSING; MATHEMATICAL MODELS;

EID: 84968644486     PISSN: 10577149     EISSN: None     Source Type: Journal    
DOI: 10.1109/TIP.2016.2555080     Document Type: Article
Times cited : (99)

References (86)
  • 3
    • 84904325195 scopus 로고    scopus 로고
    • Content based lecture video retrieval using speech and video text information
    • Apr.
    • H. Yang and C. Meinel, "Content based lecture video retrieval using speech and video text information," IEEE Trans. Learn. technol., vol. 7, no. 2, pp. 142-154, Apr. 2014.
    • (2014) IEEE Trans. Learn. Technol. , vol.7 , Issue.2 , pp. 142-154
    • Yang, H.1    Meinel, C.2
  • 4
    • 84866651203 scopus 로고    scopus 로고
    • Mobile product search with bag of hash bits and boundary reranking
    • J. Feng, "Mobile product search with bag of hash bits and boundary reranking," in Proc. CVPR, 2012, pp. 3005-3012.
    • (2012) Proc. CVPR , pp. 3005-3012
    • Feng, J.1
  • 5
    • 35649000286 scopus 로고    scopus 로고
    • Vision-based target geo-location using a fixed-wing miniature air vehicle
    • D. B. Barber, J. D. Redding, T. W. McLain, R. W. Beard, and C. N. Taylor, "Vision-based target geo-location using a fixed-wing miniature air vehicle," J. Intell. Robot. Syst., vol. 47, no. 4, pp. 361-382, 2006.
    • (2006) J. Intell. Robot. Syst. , vol.47 , Issue.4 , pp. 361-382
    • Barber, D.B.1    Redding, J.D.2    McLain, T.W.3    Beard, R.W.4    Taylor, C.N.5
  • 6
    • 0036472942 scopus 로고    scopus 로고
    • Vision for mobile robot navigation: A survey
    • Feb.
    • G. N. DeSouza and A. C. Kak, "Vision for mobile robot navigation: A survey," IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, no. 2, pp. 237-267, Feb. 2002.
    • (2002) IEEE Trans. Pattern Anal. Mach. Intell. , vol.24 , Issue.2 , pp. 237-267
    • DeSouza, G.N.1    Kak, A.C.2
  • 7
    • 1842639051 scopus 로고
    • Recognition of raised characters for automatic classification of rubber tires
    • Y. K. Ham, M. S. Kang, H. K. Chung, R.-H. Park, and G.-T. Park, "Recognition of raised characters for automatic classification of rubber tires," Opt. Eng., vol. 34, no. 1, pp. 102-109, 1995.
    • (1995) Opt. Eng. , vol.34 , Issue.1 , pp. 102-109
    • Ham, Y.K.1    Kang, M.S.2    Chung, H.K.3    Park, R.-H.4    Park, G.-T.5
  • 8
    • 84898404913 scopus 로고    scopus 로고
    • Scene text recognition using higher order language priors
    • A. Mishra, K. Alahari, and C. V. Jawahar, "Scene text recognition using higher order language priors," in Proc. BMVC, 2012, pp. 1-11.
    • (2012) Proc. BMVC , pp. 1-11
    • Mishra, A.1    Alahari, K.2    Jawahar, C.V.3
  • 9
    • 77955991043 scopus 로고    scopus 로고
    • Detecting text in natural scenes with stroke width transform
    • B. Epshtein, E. Ofek, and Y. Wexler, "Detecting text in natural scenes with stroke width transform," in Proc. CVPR, 2010, pp. 2963-2970.
    • (2010) Proc. CVPR , pp. 2963-2970
    • Epshtein, B.1    Ofek, E.2    Wexler, Y.3
  • 10
    • 84863057818 scopus 로고    scopus 로고
    • End-to-end scene text recognition
    • K. Wang, B. Babenko, and S. Belongie, "End-to-end scene text recognition," in Proc. ICCV, 2011, pp. 1457-1464.
    • (2011) Proc. ICCV , pp. 1457-1464
    • Wang, K.1    Babenko, B.2    Belongie, S.3
  • 11
    • 84866640582 scopus 로고    scopus 로고
    • Detecting texts of arbitrary orientations in natural images
    • C. Yao, X. Bai, W. Liu, Y. Ma, and Z. Tu, "Detecting texts of arbitrary orientations in natural images," in Proc. CVPR, 2012, pp. 1083-1090.
    • (2012) Proc. CVPR , pp. 1083-1090
    • Yao, C.1    Bai, X.2    Liu, W.3    Ma, Y.4    Tu, Z.5
  • 12
    • 84866700071 scopus 로고    scopus 로고
    • Real-time scene text localization and recognition
    • L. Neumann and J. Matas, "Real-time scene text localization and recognition," in Proc. CVPR, 2012, pp. 3538-3545.
    • (2012) Proc. CVPR , pp. 3538-3545
    • Neumann, L.1    Matas, J.2
  • 13
    • 84867865679 scopus 로고    scopus 로고
    • Large-lexicon attribute-consistent text recognition in natural images
    • T. Novikova, O. Barinova, P. Kohli, and V. Lempitsky, "Large-lexicon attribute-consistent text recognition in natural images," in Proc. ECCV, 2012, pp. 752-765.
    • (2012) Proc. ECCV , pp. 752-765
    • Novikova, T.1    Barinova, O.2    Kohli, P.3    Lempitsky, V.4
  • 15
    • 84902180014 scopus 로고    scopus 로고
    • Scene text recognition in mobile applications by character descriptor and structure configuration
    • Jul.
    • C. Yi and Y. Tian, "Scene text recognition in mobile applications by character descriptor and structure configuration," IEEE Trans. Image Process., vol. 23, no. 7, pp. 2972-2982, Jul. 2014.
    • (2014) IEEE Trans. Image Process. , vol.23 , Issue.7 , pp. 2972-2982
    • Yi, C.1    Tian, Y.2
  • 16
    • 84939244993 scopus 로고    scopus 로고
    • Multi-orientation scene text detection with adaptive clustering
    • Sep.
    • X. C. Yin, W. Y. Pei, J. Zhang, and H. W. Hao, "Multi-orientation scene text detection with adaptive clustering," IEEE Trans. Pattern Anal. Mach. Intell., vol. 37, no. 9, pp. 1930-1937, Sep. 2015.
    • (2015) IEEE Trans. Pattern Anal. Mach. Intell. , vol.37 , Issue.9 , pp. 1930-1937
    • Yin, X.C.1    Pei, W.Y.2    Zhang, J.3    Hao, H.W.4
  • 17
    • 84881169489 scopus 로고    scopus 로고
    • Rotation-invariant features for multi-oriented text detection in natural images
    • C. Yao, X. Zhang, X. Bai, W. Liu, Y. Ma, and Z. Tu, "Rotation-invariant features for multi-oriented text detection in natural images," PLoS One, vol. 8, no. 8, p. e70173, 2013.
    • (2013) PLoS One , vol.8 , Issue.8
    • Yao, C.1    Zhang, X.2    Bai, X.3    Liu, W.4    Ma, Y.5    Tu, Z.6
  • 18
    • 82355164561 scopus 로고    scopus 로고
    • An MRF model for binarization of natural scene text
    • A. Mishra, K. Alahari, and C. V. Jawahar, "An MRF model for binarization of natural scene text," in Proc. ICDAR, 2011, pp. 11-16.
    • (2011) Proc. ICDAR , pp. 11-16
    • Mishra, A.1    Alahari, K.2    Jawahar, C.V.3
  • 19
    • 84887365560 scopus 로고    scopus 로고
    • Scene text recognition using part-based tree-structured character detection
    • C. Shi, C. Wang, B. Xiao, Y. Zhang, S. Gao, and Z. Zhang, "Scene text recognition using part-based tree-structured character detection," in Proc. CVPR, 2013, pp. 2961-2968.
    • (2013) Proc. CVPR , pp. 2961-2968
    • Shi, C.1    Wang, C.2    Xiao, B.3    Zhang, Y.4    Gao, S.5    Zhang, Z.6
  • 20
    • 84911448414 scopus 로고    scopus 로고
    • Region-based discriminative feature pooling for scene text recognition
    • C. Y. Lee, A. Bhardwaj, W. Di, V. Jagadeesh, and R. Piramuthu, "Region-based discriminative feature pooling for scene text recognition," in Proc. CVPR, 2014, pp. 4050-4057.
    • (2014) Proc. CVPR , pp. 4050-4057
    • Lee, C.Y.1    Bhardwaj, A.2    Di, W.3    Jagadeesh, V.4    Piramuthu, R.5
  • 21
    • 70450201402 scopus 로고    scopus 로고
    • Class-specific Hough forests for object detection
    • J. Gall and V. Lempitsky, "Class-specific Hough forests for object detection," in Proc. CVPR, 2009, pp. 1022-1029.
    • (2009) Proc. CVPR , pp. 1022-1029
    • Gall, J.1    Lempitsky, V.2
  • 22
    • 33745155436 scopus 로고    scopus 로고
    • A Bayesian hierarchical model for learning natural scene categories
    • L. Fei-Fei and P. Perona, "A Bayesian hierarchical model for learning natural scene categories," in Proc. CVPR, 2005, pp. 524-531.
    • (2005) Proc. CVPR , pp. 524-531
    • Fei-Fei, L.1    Perona, P.2
  • 23
    • 84887325186 scopus 로고    scopus 로고
    • Blocks that shout: Distinctive parts for scene classification
    • M. Juneja, A. Vedaldi, C. V. Jawahar, and A. Zisserman, "Blocks that shout: Distinctive parts for scene classification," in Proc. CVPR, 2013, pp. 923-930.
    • (2013) Proc. CVPR , pp. 923-930
    • Juneja, M.1    Vedaldi, A.2    Jawahar, C.V.3    Zisserman, A.4
  • 24
    • 84907568883 scopus 로고    scopus 로고
    • Strokelets: A learned multiscale representation for scene text recognition
    • C. Yao, X. Bai, B. Shi, and W. Liu, "Strokelets: A learned multiscale representation for scene text recognition," in Proc. CVPR, 2014, pp. 4042-4049.
    • (2014) Proc. CVPR , pp. 4042-4049
    • Yao, C.1    Bai, X.2    Shi, B.3    Liu, W.4
  • 26
    • 78149313522 scopus 로고    scopus 로고
    • Word spotting in the wild
    • K. Wang and S. Belongie, "Word spotting in the wild," in Proc. ECCV, 2010, pp. 591-604.
    • (2010) Proc. ECCV , pp. 591-604
    • Wang, K.1    Belongie, S.2
  • 27
    • 84856682512 scopus 로고    scopus 로고
    • A method for text localization and recognition in real-world images
    • L. Neumann and J. Matas, "A method for text localization and recognition in real-world images," in Proc. ACCV, 2010, pp. 770-783.
    • (2010) Proc. ACCV , pp. 770-783
    • Neumann, L.1    Matas, J.2
  • 28
    • 84866697058 scopus 로고    scopus 로고
    • Top-down and bottom-up cues for scene text recognition
    • A. Mishra, K. Alahari, and C. V. Jawahar, "Top-down and bottom-up cues for scene text recognition," in Proc. CVPR, 2012, pp. 2687-2694.
    • (2012) Proc. CVPR , pp. 2687-2694
    • Mishra, A.1    Alahari, K.2    Jawahar, C.V.3
  • 29
    • 84878240310 scopus 로고    scopus 로고
    • Text recognition in natural images using multiclass Hough forests
    • G. Yildirim, R. Achanta, and S. Süsstrunk, "Text recognition in natural images using multiclass Hough forests," in Proc. VISAPP, 2013, pp. 737-741.
    • (2013) Proc. VISAPP , pp. 737-741
    • Yildirim, G.1    Achanta, R.2    Süsstrunk, S.3
  • 30
    • 84889587871 scopus 로고    scopus 로고
    • Whole is greater than sum of parts: Recognizing scene text words
    • V. Goel, A. Mishra, K. Alahari, and C. V. Jawahar, "Whole is greater than sum of parts: Recognizing scene text words," in Proc. ICDAR, 2013, pp. 398-402.
    • (2013) Proc. ICDAR , pp. 398-402
    • Goel, V.1    Mishra, A.2    Alahari, K.3    Jawahar, C.V.4
  • 32
    • 84924085720 scopus 로고    scopus 로고
    • Text detection approach based on confidence map and context information
    • Jun.
    • R. Wang, N. Sang, and C. Gao, "Text detection approach based on confidence map and context information," Neurocomputing, vol. 157, pp. 153-165, Jun. 2015.
    • (2015) Neurocomputing , vol.157 , pp. 153-165
    • Wang, R.1    Sang, N.2    Gao, C.3
  • 33
    • 84952628804 scopus 로고    scopus 로고
    • Scene text detection and recognition: Recent advances and future trends
    • Y. Zhu, C. Yao, and X. Bai, "Scene text detection and recognition: Recent advances and future trends," Frontier Comput. Sci., vol. 10, no. 1, pp. 19-36, 2016.
    • (2016) Frontier Comput. Sci. , vol.10 , Issue.1 , pp. 19-36
    • Zhu, Y.1    Yao, C.2    Bai, X.3
  • 34
    • 84863052045 scopus 로고    scopus 로고
    • Robust text detection in natural images with edge-enhanced maximally stable extremal regions
    • H. Chen, S. S. Tsai, G. Schroth, D. M. Chen, R. Grzeszczuk, and B. Girod, "Robust text detection in natural images with edge-enhanced maximally stable extremal regions," in Proc. ICIP, 2011, pp. 2609-2612.
    • (2011) Proc. ICIP , pp. 2609-2612
    • Chen, H.1    Tsai, S.S.2    Schroth, G.3    Chen, D.M.4    Grzeszczuk, R.5    Girod, B.6
  • 35
    • 84876208085 scopus 로고    scopus 로고
    • Scene text detection via connected component clustering and nontext filtering
    • Jun.
    • H. IlKoo and D. HoonKim, "Scene text detection via connected component clustering and nontext filtering," IEEE Trans. Image Process., vol. 22, no. 6, pp. 2296-2305, Jun. 2013.
    • (2013) IEEE Trans. Image Process. , vol.22 , Issue.6 , pp. 2296-2305
    • IlKoo, H.1    HoonKim, D.2
  • 36
    • 84883074303 scopus 로고    scopus 로고
    • Accurate and robust text detection: A step-in for text retrieval in natural scene images
    • X.-C. Yin, X. Yin, K. Huang, and H.-E. Hao, "Accurate and robust text detection: A step-in for text retrieval in natural scene images," in Proc. SIGIR, 2013, pp. 1091-1092.
    • (2013) Proc. SIGIR , pp. 1091-1092
    • Yin, X.-C.1    Yin, X.2    Huang, K.3    Hao, H.-E.4
  • 38
    • 33645146449 scopus 로고    scopus 로고
    • Histograms of oriented gradients for human detection
    • N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection," in Proc. CVPR, 2005, pp. 886-893.
    • (2005) Proc. CVPR , pp. 886-893
    • Dalal, N.1    Triggs, B.2
  • 39
    • 84898792558 scopus 로고    scopus 로고
    • Scene text localization and recognition with oriented stroke detection
    • L. Neumann and J. Matas, "Scene text localization and recognition with oriented stroke detection," in Proc. ICCV, 2013, pp. 97-104.
    • (2013) Proc. ICCV , pp. 97-104
    • Neumann, L.1    Matas, J.2
  • 41
    • 0142192295 scopus 로고    scopus 로고
    • Conditional random fields: Probabilistic models for segmenting and labeling sequence data
    • J. D. Lafferty, A. McCallum, and F. C. N. Pereira, "Conditional random fields: Probabilistic models for segmenting and labeling sequence data," in Proc. ICML, 2005, pp. 282-289.
    • (2005) Proc. ICML , pp. 282-289
    • Lafferty, J.D.1    McCallum, A.2    Pereira, F.C.N.3
  • 42
    • 84867880615 scopus 로고    scopus 로고
    • Unsupervised discovery of midlevel discriminative patches
    • S. Singh, A. Gupta, and A. A. Efros, "Unsupervised discovery of midlevel discriminative patches," in Proc. ECCV, 2012, pp. 73-86.
    • (2012) Proc. ECCV , pp. 73-86
    • Singh, S.1    Gupta, A.2    Efros, A.A.3
  • 43
    • 84887354170 scopus 로고    scopus 로고
    • Sketch tokens: A learned midlevel representation for contour and object detection
    • J. J. Lim, C. L. Zitnick, and P. Dollár, "Sketch tokens: A learned midlevel representation for contour and object detection," in Proc. CVPR, 2013, pp. 3158-3165.
    • (2013) Proc. CVPR , pp. 3158-3165
    • Lim, J.J.1    Zitnick, C.L.2    Dollár, P.3
  • 44
    • 84911382242 scopus 로고    scopus 로고
    • Max-margin multipleinstance dictionary learning
    • X. Wang, B. Wang, X. Bai, W. Liu, and Z. Tu, "Max-margin multipleinstance dictionary learning," in Proc. ICML, 2013, pp. 846-854.
    • (2013) Proc. ICML , pp. 846-854
    • Wang, X.1    Wang, B.2    Bai, X.3    Liu, W.4    Tu, Z.5
  • 45
    • 0000494467 scopus 로고
    • Handwritten digit recognition with a back-propagation network
    • Y. Le Cun et al., "Handwritten digit recognition with a back-propagation network," in Proc. NIPS, 1990, pp. 396-404.
    • (1990) Proc. NIPS , pp. 396-404
    • Le Cun, Y.1
  • 46
    • 84876231242 scopus 로고    scopus 로고
    • Imagenet classification with deep convolutional neural networks
    • A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," in Proc. NIPS, 2012, pp. 1097-1105.
    • (2012) Proc. NIPS , pp. 1097-1105
    • Krizhevsky, A.1    Sutskever, I.2    Hinton, G.E.3
  • 48
    • 84911198048 scopus 로고    scopus 로고
    • DeepFace: Closing the gap to human-level performance in face verification
    • Y. Taigman, M. Yang, M. Ranzato, and L. Wolf, "DeepFace: Closing the gap to human-level performance in face verification," in Proc. CVPR, 2014, pp. 1701-1708.
    • (2014) Proc. CVPR , pp. 1701-1708
    • Taigman, Y.1    Yang, M.2    Ranzato, M.3    Wolf, L.4
  • 49
    • 84911400494 scopus 로고    scopus 로고
    • Rich feature hierarchies for accurate object detection and semantic segmentation
    • R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation," in Proc. CVPR, 2014, pp. 580-587.
    • (2014) Proc. CVPR , pp. 580-587
    • Girshick, R.1    Donahue, J.2    Darrell, T.3    Malik, J.4
  • 50
    • 82355160847 scopus 로고    scopus 로고
    • Text detection and character recognition in scene images with unsupervised feature learning
    • A. Coates et al., "Text detection and character recognition in scene images with unsupervised feature learning," in Proc. ICDAR, 2011, pp. 440-445.
    • (2011) Proc. ICDAR , pp. 440-445
    • Coates, A.1
  • 51
    • 84874562673 scopus 로고    scopus 로고
    • End-to-end text recognition with convolutional neural networks
    • T. Wang, D. J. Wu, A. Coates, and A. Y. Ng, "End-to-end text recognition with convolutional neural networks," in Proc. ICPR, 2012, pp. 3304-3308.
    • (2012) Proc. ICPR , pp. 3304-3308
    • Wang, T.1    Wu, D.J.2    Coates, A.3    Ng, A.Y.4
  • 52
    • 84898778744 scopus 로고    scopus 로고
    • PhotoOCR: Reading text in uncontrolled conditions
    • A. Bissacco, M. Cummins, Y. Netzer, and H. Neven, "PhotoOCR: Reading text in uncontrolled conditions," in Proc. ICCV, 2013, pp. 785-792.
    • (2013) Proc. ICCV , pp. 785-792
    • Bissacco, A.1    Cummins, M.2    Netzer, Y.3    Neven, H.4
  • 54
    • 0036460907 scopus 로고    scopus 로고
    • Weighted finite-state transducers in speech recognition
    • M. Mohri, F. Pereira, and M. Riley, "Weighted finite-state transducers in speech recognition," Comput. Speech Lang., vol. 16, no. 1, pp. 69-88, 2013.
    • (2013) Comput. Speech Lang. , vol.16 , Issue.1 , pp. 69-88
    • Mohri, M.1    Pereira, F.2    Riley, M.3
  • 55
    • 84899104715 scopus 로고    scopus 로고
    • Spatially local coding for object recognition
    • S. McCann and D. G. Lowe, "Spatially local coding for object recognition," in Proc. ACCV, 2012, pp. 204-217.
    • (2012) Proc. ACCV , pp. 204-217
    • McCann, S.1    Lowe, D.G.2
  • 56
    • 0035478854 scopus 로고    scopus 로고
    • Random forests
    • L. Breiman, "Random forests," Mach. Learn., vol. 45, no. 1, pp. 5-32, 2001.
    • (2001) Mach. Learn. , vol.45 , Issue.1 , pp. 5-32
    • Breiman, L.1
  • 57
    • 85112851150 scopus 로고    scopus 로고
    • Poselets: Body part detectors trained using 3D human pose annotations
    • L. Bourdev and J. Malik, "Poselets: Body part detectors trained using 3D human pose annotations," in Proc. ICCV, 2009, pp. 1365-1372.
    • (2009) Proc. ICCV , pp. 1365-1372
    • Bourdev, L.1    Malik, J.2
  • 58
    • 78149356001 scopus 로고    scopus 로고
    • Detecting people using mutually consistent poselet activations
    • L. Bourdev, S. Maji, T. Brox, and J. Malik, "Detecting people using mutually consistent poselet activations," in Proc. ECCV, 2010, pp. 168-181.
    • (2010) Proc. ECCV , pp. 168-181
    • Bourdev, L.1    Maji, S.2    Brox, T.3    Malik, J.4
  • 59
    • 39749124915 scopus 로고    scopus 로고
    • Robust object detection with interleaved categorization and segmentation
    • B. Leibe, A. Leonardis, and B. Schiele, "Robust object detection with interleaved categorization and segmentation," Int. J. Comput. Vis., vol. 77, nos. 1-3, pp. 259-289, 2008.
    • (2008) Int. J. Comput. Vis. , vol.77 , Issue.1-3 , pp. 259-289
    • Leibe, B.1    Leonardis, A.2    Schiele, B.3
  • 60
    • 0029357425 scopus 로고
    • Mean shift, mode seeking, and clustering
    • Aug.
    • Y. Cheng, "Mean shift, mode seeking, and clustering," IEEE Trans. Pattern Anal. Mach. Intell., vol. 17, no. 8, pp. 790-799, Aug. 1995.
    • (1995) IEEE Trans. Pattern Anal. Mach. Intell. , vol.17 , Issue.8 , pp. 790-799
    • Cheng, Y.1
  • 61
    • 84906498729 scopus 로고    scopus 로고
    • Human detection using learned part alphabet and pose dictionary
    • C. Yao, X. Bai, W. Liu, and L. J. Latecki, "Human detection using learned part alphabet and pose dictionary," in Proc. ECCV, 2014, pp. 251-266.
    • (2014) Proc. ECCV , pp. 251-266
    • Yao, C.1    Bai, X.2    Liu, W.3    Latecki, L.J.4
  • 62
    • 33845572523 scopus 로고    scopus 로고
    • Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories
    • S. Lazebnik, C. Schmid, and J. Ponce, "Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories," in Proc. CVPR, 2006, pp. 2169-2178.
    • (2006) Proc. CVPR , pp. 2169-2178
    • Lazebnik, S.1    Schmid, C.2    Ponce, J.3
  • 63
    • 70450209196 scopus 로고    scopus 로고
    • Linear spatial pyramid matching using sparse coding for image classification
    • J. Yang, K. Yu, Y. Gong, and T. Huang, "Linear spatial pyramid matching using sparse coding for image classification," in Proc. CVPR, 2009, pp. 1794-1801.
    • (2009) Proc. CVPR , pp. 1794-1801
    • Yang, J.1    Yu, K.2    Gong, Y.3    Huang, T.4
  • 64
    • 84906332834 scopus 로고    scopus 로고
    • DeCAF: A deep convolutional activation feature for generic visual recognition
    • J. Donahue et al., "DeCAF: A deep convolutional activation feature for generic visual recognition," in Proc. ICML, 2014, pp. 647-655.
    • (2014) Proc. ICML , pp. 647-655
    • Donahue, J.1
  • 65
  • 67
    • 84907546391 scopus 로고    scopus 로고
    • A unified framework for multioriented text detection and recognition
    • Nov.
    • C. Yao, X. Bai, and W. Liu, "A unified framework for multioriented text detection and recognition," IEEE Trans. Image Process., vol. 23, no. 11, pp. 4737-4749, Nov. 2014.
    • (2014) IEEE Trans. Image Process. , vol.23 , Issue.11 , pp. 4737-4749
    • Yao, C.1    Bai, X.2    Liu, W.3
  • 68
    • 84870246844 scopus 로고    scopus 로고
    • T-HOG: An effective gradient-based descriptor for single line text regions
    • R. Minetto, N. Thome, M. Cord, N. J. Leite, and J. Stolfi, "T-HOG: An effective gradient-based descriptor for single line text regions," Pattern Recognit., vol. 46, no. 3, pp. 1078-1090, 2013.
    • (2013) Pattern Recognit. , vol.46 , Issue.3 , pp. 1078-1090
    • Minetto, R.1    Thome, N.2    Cord, M.3    Leite, N.J.4    Stolfi, J.5
  • 69
    • 82355175563 scopus 로고    scopus 로고
    • ICDAR 2011 robust reading competition challenge 2: Reading text in scene images
    • A. Shahab, F. Shafait, and A. Dengel, "ICDAR 2011 robust reading competition challenge 2: Reading text in scene images," in Proc. ICDAR, 2011, pp. 1491-1496.
    • (2011) Proc. ICDAR , pp. 1491-1496
    • Shahab, A.1    Shafait, F.2    Dengel, A.3
  • 70
    • 33947430146 scopus 로고    scopus 로고
    • ICDAR 2005 text locating competition results
    • S. M. Lucas, "ICDAR 2005 text locating competition results," in Proc. ICDAR, 2005, pp. 80-84.
    • (2005) Proc. ICDAR , pp. 80-84
    • Lucas, S.M.1
  • 71
    • 33747390127 scopus 로고    scopus 로고
    • Object count/area graphs for the evaluation of object detection and segmentation algorithms
    • C. Wolf and J.-M. Jolion, "Object count/area graphs for the evaluation of object detection and segmentation algorithms," Int. J. Document Anal. Recognit., vol. 8, no. 4, pp. 280-296, 2006.
    • (2006) Int. J. Document Anal. Recognit. , vol.8 , Issue.4 , pp. 280-296
    • Wolf, C.1    Jolion, J.-M.2
  • 73
    • 85083954541 scopus 로고    scopus 로고
    • Deep structured output learning for unconstrained text recognition
    • M. Jaderberg, K. Simonyan, A. Vedaldi, and A. Zisserman, "Deep structured output learning for unconstrained text recognition," in Proc. ICLR, 2015, pp. 1-10.
    • (2015) Proc. ICLR , pp. 1-10
    • Jaderberg, M.1    Simonyan, K.2    Vedaldi, A.3    Zisserman, A.4
  • 74
    • 84898455310 scopus 로고    scopus 로고
    • acessed on Apr. 15, 2016. [Online]
    • ABBYY FineReader 9.0, acessed on Apr. 15, 2016. [Online]. Available: http://www.abbyy.com/
    • ABBYY FineReader 9.0
  • 77
    • 70349280061 scopus 로고    scopus 로고
    • Character recognition in natural images
    • T. E. de Campos, B. R. Babu, and M. Varma, "Character recognition in natural images," in Proc. VISAPP, 2009, pp. 273-280.
    • (2009) Proc. VISAPP , pp. 273-280
    • De Campos, T.E.1    Babu, B.R.2    Varma, M.3
  • 78
    • 84906502933 scopus 로고    scopus 로고
    • Robust scene text detection with convolution neural network induced MSER trees
    • W. Huang, Y. Qu, and X. Tang, "Robust scene text detection with convolution neural network induced MSER trees," in Proc. ECCV, 2014, pp. 497-511.
    • (2014) Proc. ECCV , pp. 497-511
    • Huang, W.1    Qu, Y.2    Tang, X.3
  • 79
    • 84889593064 scopus 로고    scopus 로고
    • On combining multiple segmentations in scene text recognition
    • L. Neumann and J. Matas, "On combining multiple segmentations in scene text recognition," in Proc. ICDAR, 2013, pp. 523-527.
    • (2013) Proc. ICDAR , pp. 523-527
    • Neumann, L.1    Matas, J.2
  • 80
    • 82355187602 scopus 로고    scopus 로고
    • Text detection in natural scene images by stroke Gabor words
    • C. Yi and Y. Tian, "Text detection in natural scene images by stroke Gabor words," in Proc. ICDAR, 2011, pp. 171-177.
    • (2011) Proc. ICDAR , pp. 171-177
    • Yi, C.1    Tian, Y.2
  • 81
    • 79951841939 scopus 로고    scopus 로고
    • A hybrid approach to detect and localize texts in natural scene images
    • Mar.
    • Y.-F. Pan, X. Hou, and C.-L. Liu, "A hybrid approach to detect and localize texts in natural scene images," IEEE Trans. Image Process., vol. 20, no. 3, pp. 800-813, Mar. 2011.
    • (2011) IEEE Trans. Image Process. , vol.20 , Issue.3 , pp. 800-813
    • Pan, Y.-F.1    Hou, X.2    Liu, C.-L.3
  • 82
    • 78149484901 scopus 로고    scopus 로고
    • Scene text extraction with edge constraint and text collinearity
    • S. Lee, M. S. Cho, K. Jung, and J. H. Kim, "Scene text extraction with edge constraint and text collinearity," in Proc. ICPR, 2010, pp. 3983-3986.
    • (2010) Proc. ICPR , pp. 3983-3986
    • Lee, S.1    Cho, M.S.2    Jung, K.3    Kim, J.H.4
  • 83
    • 84949254659 scopus 로고    scopus 로고
    • Script identification in the wild via discriminative convolutional neural network
    • Apr.
    • B. Shi, X. Bai, and C. Yao, "Script identification in the wild via discriminative convolutional neural network," Pattern Recognit., vol. 52, pp. 448-458, Apr. 2016.
    • (2016) Pattern Recognit. , vol.52 , pp. 448-458
    • Shi, B.1    Bai, X.2    Yao, C.3
  • 84
    • 84893656343 scopus 로고    scopus 로고
    • Accurate junction detection and characterization in natural images
    • Jan.
    • G.-S. Xia, J. Delon, and Y. Gousseau, "Accurate junction detection and characterization in natural images," Int. J. Comput. Vis., vol. 106, no. 1, pp. 31-56, Jan. 2014.
    • (2014) Int. J. Comput. Vis. , vol.106 , Issue.1 , pp. 31-56
    • Xia, G.-S.1    Delon, J.2    Gousseau, Y.3
  • 85
    • 85027932133 scopus 로고    scopus 로고
    • Robust feature matching for remote sensing image registration via locally linear transforming
    • Dec.
    • J. Ma, H. Zhou, J. Zhao, Y. Gao, J. Jiang, and J. Tian, "Robust feature matching for remote sensing image registration via locally linear transforming," IEEE Trans. Geosci. Remote Sens., vol. 53, no. 12, pp. 6469-6481, Dec. 2015.
    • (2015) IEEE Trans. Geosci. Remote Sens. , vol.53 , Issue.12 , pp. 6469-6481
    • Ma, J.1    Zhou, H.2    Zhao, J.3    Gao, Y.4    Jiang, J.5    Tian, J.6


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.