The Correction Algorithm Research of Inclination Paper Currency Image

Abstract:

There exist low recognition speed and non-ideal recognition effect in some recognition algorithms of paper currency value. One of very important reasons is that the shooting angle makes the image inclined. This paper firstly analyses the binarization processing of RMB 100-Yuan image and then the method of acquiring straight lines in image is discussed. Thus, the inclination angle of image is calculated by using the obtained straight lines. Finally, through rotation transformation, the inclination image is corrected. The experimental results show that this algorithm has a good corrected effect to the inclination image of paper currency and improves the image recognition effect.

• Periodical: Advanced Materials Research (Volumes 756-759)
• Pages: 1464-1468
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.756-759.1464
• Online since: September 2013
• Authors: Hong Hai Liu, Xiang Hua Hou
• Keywords: Image Inclination, Image Rotation, Method of Maximum Classes Square Error, Two-Peak Method

References

[1] Duan T D, Duc D A, and Du T L H：Combining Hough Transform and Contour Algorithm for Detecting Vehicles License Plate， Proceedings of 2004 International Symposium on Itelligent Multimedia, Video and Speech Processing (2004).

DOI: 10.1109/isimp.2004.1434172

[2] Nomura S, Yamanaka K, Katai : A Novel Adaptive Morphological Approach for Degraded Character Image Segmentation , in Pattern Recognition( 2005).

DOI: 10.1016/j.patcog.2005.01.026

[3] Rafael. C. Gonzalez, and Richard E. Woods: Digital Image Processing, Pearson Prentice Hall (2004).

[4] Kim K I, Jung K, Park S H: Support Vector Machines for Texture Classification, IEEE Transactions on Pattern Analysis and Machine Intelligence (2002).

DOI: 10.1109/tpami.2002.1046177

[5] Stuart C. Hinds, et al: A Document Skew Detection Method Using Run-Length Encoding And The Hough Transform, IEEE(1990).

DOI: 10.1109/icpr.1990.118147

[6] C. Sun and D. Si: Skew and Slant Correction for Document Image Using Gradient Direction, in Proceedings of the Fourth International Conference on Document Analysis and Recognition, Ulm, Germany (1997).

DOI: 10.1109/icdar.1997.619830