@Article{jcs.2021.017071,
AUTHOR = {Yunzuo Zhang, Yi Li, Wei Guo, Lei Huo, Jiayu Zhang, Kaina Guo},
TITLE = {Single-Choice Aided Marking System Research Based on Back Propagation  Neural Network},
JOURNAL = {Journal of Cyber Security},
VOLUME = {3},
YEAR = {2021},
NUMBER = {1},
PAGES = {45--54},
URL = {http://www.techscience.com/JCS/v3n1/42438},
ISSN = {2579-0064},
ABSTRACT = {In the field of educational examination, automatic marking technology 
plays an essential role in improving the efficiency of marking and liberating the 
labor force. At present, the implementation of the policy of expanding erolments
has caused a serious decline in the teacher-student ratio in colleges and 
universities. The traditional marking system based on Optical Mark Reader 
technology can no longer meet the requirements of liberating the labor force of 
teachers in small and medium-sized examinations. With the development of 
image processing and artificial neural network technology, the recognition of 
handwritten character in the field of pattern recognition has attracted the 
attention of many researchers. In this paper, filtering and de-noise processing and 
binary processing are used as preprocessing methods for handwriting recognition. 
Extract the pixel feature of handwritten characters through digital image 
processing of handwritten character pictures, and then, get the feature vector 
from these feature fragments and use it as the description of the character. The 
extracted feature values are used to train the neural network to realize the 
recognition of handwritten English letters and numerical characters. 
Experimental results on Chars74K and MNIST data sets show that the 
recognition accuracy of some handwritten English letters and numerical
characters can reach 90% and 99%, respectively.},
DOI = {10.32604/jcs.2021.017071}
}