Speed-up ellipse enclosing character detection approach for large-size document images by parallel scanning and Hough transform

This paper presents a speed-up ellipse enclosing character detection algorithm that uses parallel image scanning and the Hough transform (HT) for large-size document images. Objects in images are generally detected based on geometrical information obtained via raster scanning. In raster scanning, all pixels of an image are scanned starting from the upper-left point and ending with the lower-right point. In the case of large-size images, considerable time is needed for processing an image by scanning all pixels. In this paper, an object detection approach for large-size images is proposed which does not require scanning all pixels in the images. In this speed-up ellipse enclosing character detection approach for large-size document images, pixels are scanned on constantly spaced vertical parallel lines. If an object larger than a certain size is identified while scanning, the presence of an ellipse enclosing character is assumed and ellipse detection is conducted by applying HT only in a defined local image area over the found object. With this approach, processing time can be dramatically reduced by disregarding some objects and reducing the total image area used for ellipse detection.

[1]  Ebroul Izquierdo,et al.  Document Image Processing for Paper Side Communications , 2008, IEEE Transactions on Multimedia.

[2]  Toshiaki Fujii,et al.  Traffic Sign Recognition Using Hybrid Camera System , 2011 .

[3]  A Gonzaga,et al.  Wavelet-based estimation of generalized fractional process. , 2007, Methods of information in medicine.

[4]  Saburo Tsuji,et al.  Detection of Ellipses by a Modified Hough Transformation , 1978, IEEE Transactions on Computers.

[5]  H Kawanaka,et al.  Document recognition and XML generation of tabular form discharge summaries for analogous case search system. , 2007, Methods of information in medicine.

[6]  Atsuhiro Takasu,et al.  A rule learning method for academic document image processing , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[7]  Hong Wang,et al.  A Fast and Robust Ellipse Detection Algorithm Based on Pseudo-random Sample Consensus , 2007, CAIP.

[8]  Edward Roy Davies.  Finding ellipses using the generalised Hough transform , 1989, Pattern Recognit. Lett..

[9]  Qing Wang,et al.  Hierarchical content classification and script determination for automatic document image processing , 2002, Object recognition supported by user interaction for service robots.

[10]  Ying Li,et al.  A knowledge-based image understanding environment for document processing , 1997, Proceedings of the Fourth International Conference on Document Analysis and Recognition.

[11]  Qiang Ji,et al.  A new efficient ellipse detection method , 2002, Object recognition supported by user interaction for service robots.

[12]  Qiang Ji,et al.  A statistically efficient method for ellipse detection , 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

[13]  Chinthaka Premachandra.  Parallel Scanning Based Speed-up Method for Detection of Elliptical Obstacles in High-resolution Image , 2013 .

[14]  P.E. Baier.  Image processing of forensic documents , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[15]  Hong Yan,et al.  A robust document processing system combining image segmentation with content-based document compression , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[16]  Ling-Hwei Chen,et al.  A fast ellipse/circle detector using geometric symmetry , 1995, Pattern Recognit..

[17]  Koji Nakano,et al.  Fast Ellipse Detection Algorithm Using Hough Transform on the GPU , 2011, 2011 Second International Conference on Networking and Computing.

[18]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[19]  V. Manikandan,et al.  An enhanced algorithm for Character Segmentation in document image processing , 2010, 2010 IEEE International Conference on Computational Intelligence and Computing Research.

[20]  Chinthaka Premachandra.  Interactive Learning Support User Interface for Lecture Scenes Indexed with Extracted Keyword from Black board , 2014 .

[21]  S. K. Yip,et al.  Page segmentation and content classification for automatic document image processing , 2001, Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing. ISIMP 2001 (IEEE Cat. No.01EX489).

[22]  Harry Wechsler,et al.  Document image analysis using integrated image and neural processing , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[23]  Venu Govindaraju,et al.  A Model Based Framework for Table Processing in Degraded Document Images , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[24]  Peter Kwong-Shun Tam,et al.  Modification of hough transform for circles and ellipses detection using a 2-dimensional array , 1992, Pattern Recognit..

[25]  Chew Lim Tan,et al.  A wavelet approach to double-sided document image pair processing , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[26]  Qing Wang,et al.  Hierarchical content classification and script determination for automatic document image processing , 2003, Pattern Recognit..

[27]  P. S. Nair,et al.  Hough transform based ellipse detection algorithm , 1996, Pattern Recognit. Lett..

[28]  Shang Jin,et al.  A Scanned Document Image Processing Model for Information System , 2010, 2010 Asia-Pacific Conference on Wearable Computing Systems.

[29]  Pietro Parodi,et al.  An efficient pre-processing of mixed-content document images for OCR systems , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[30]  Nicolae Tapus,et al.  Text line processing for high-confidence skew detection in image documents , 2010, Proceedings of the 2010 IEEE 6th International Conference on Intelligent Computer Communication and Processing.

[31]  Chengan Guo,et al.  An image segmentation method based on the fusion of vector quantization and edge detection with applications to medical image processing , 2013, International Journal of Machine Learning and Cybernetics.

[32]  Mark S. Nixon,et al.  On using directional information for parameter space decomposition in ellipse detection , 1996, Pattern Recognit..