A scheme for automatic text rectification in real scene images

Digital camera is gradually replacing traditional flat-bed scanner as the main access to obtain text information for its usability, cheapness and high-resolution, there has been a large amount of research done on camera-based text understanding. Unfortunately, arbitrary position of camera lens related to text area can frequently cause perspective distortion which most OCR systems at present cannot manage, thus creating demand for automatic text rectification. Current rectification-related research mainly focused on document images, distortion of natural scene text is seldom considered. In this paper, a scheme for automatic text rectification in natural scene images is proposed. It relies on geometric information extracted from characters themselves as well as their surroundings. For the first step, linear segments are extracted from interested region, and a J-Linkage based clustering is performed followed by some customized refinement to estimate primary vanishing point(VP)s. To achieve a more comprehensive VP estimation, second stage would be performed by inspecting the internal structure of characters which involves analysis on pixels and connected components of text lines. Finally VPs are verified and used to implement perspective rectification. Experiments demonstrate increase of recognition rate and improvement compared with some related algorithms.

[1]  Ana Cristina Murillo,et al.  Towards robust and efficient text sign reading from a mobile phone , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[2]  Kongqiao Wang,et al.  An Improved Scene Text Extraction Method Using Conditional Random Field and Optical Character Recognition , 2011, 2011 International Conference on Document Analysis and Recognition.

[3]  Majid Mirmehdi,et al.  Location and recovery of text on oriented surfaces , 1999, Electronic Imaging.

[4]  Jun Sun,et al.  Perspective rectification for mobile phone camera-based documents using a hybrid approach to vanishing point detection , .

[5]  Robert C. Bolles,et al.  Rectification and recognition of text in 3-D scenes , 2004, International Journal of Document Analysis and Recognition (IJDAR).

[6]  Majid Mirmehdi,et al.  Rectifying perspective views of text in 3D scenes using vanishing points , 2003, Pattern Recognit..

[7]  Shijian Lu,et al.  The Restoration of Camera Documents Through Image Segmentation , 2006, Document Analysis Systems.

[8]  Yi Ma,et al.  TILT: Transform Invariant Low-Rank Textures , 2010, ACCV.

[9]  Xin Zhang,et al.  Rectification of Optical Characters as Transform Invariant Low-Rank Textures , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[10]  Maurizio Pilu,et al.  Extraction of illusory linear clues in perspectively skewed documents , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[11]  Zhuowen Tu,et al.  Detecting Texts of Arbitrary Orientations in 1 Natural Images , 2012 .

[12]  Xin Zhang,et al.  Multiple Geometry Transform Estimation from Single Camera-Captured Text Image , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[13]  Majid Mirmehdi,et al.  Fast perspective recovery of text in natural scenes , 2013, Image Vis. Comput..

[14]  Xiaoqing Ding,et al.  Linear Sequence Discriminant Analysis: A Model-Based Dimensionality Reduction Method for Vector Sequences , 2013, 2013 IEEE International Conference on Computer Vision.

[15]  Ming Chen,et al.  A robust skew detection algorithm for grayscale document image , 1999, Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318).

[16]  Shijian Lu,et al.  Document image rectification using fuzzy sets and morphological operators , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..