The Recognition of Handwritten Digital Based on BP Neural Network

Abstract:

The article put forward to new recognition method of handwritten digital based on BP neural network. Its recognition process mainly includes ten aspect: incline correction of handwritten number, edge detection and separation of a set number, binarization, denoising, extraction of numerals, window scaling, location standardization, thinning, extraction of numeral feature and fuzzy recognition based on BP neural network. The test results show that the recognition rate of this method can be over 92 percent. The recognition time of characters for character is less than 1.1 second, which means that the method is more effective recognition ability and can better satisfy the real system requirements.It should be widely applied practical significance for Book Number Recognition, zip code recognition sorting.

• Periodical: Applied Mechanics and Materials (Volumes 416-417)
• Pages: 1239-1243
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.416-417.1239
• Online since: September 2013
• Authors: Shan Gao
• Keywords: BP Neural Network (BPNN), Fuzzy Recognition, Handwritten Digital

References

[1] Zhao Xuechun, Qi Feihu (2000) Automatic Recognition of Vehicle License Based on Color Segmentation (Journal Of Shanghai Jiaotong U Niversity) 98(5): 31-37.

[2] WEI Wu, ZHANG Qi-sen, HUANG Xin-han (1998) Research of Number-Plate Recognition Using Distributed Processing (Journal Of Changsha Communications University 11(02): 77-81.

[3] WANG Ming-chang, XING Lixin1b, YANG Yiheng, LIU Zhihui (2006) Directional Weighted Two Dimensional Multistep Median Filtering in Image Processing Journal of Jilin University) 113(5): 644-648.

[4] WANG Jian Ping, QIN Feng (2004) On the adaptive binarization filtering algorithm for gray character images and its application (Jou Rnal O F Hefe Iun Iv Ers Ity O F Technolo Gy 4(8): 67-73.