Using a Circular grid for Offline Handwritten Character Recognition
Offline handwritten recognition is more challenging as indicated by the recognition technologies. This study demon-strates significantly higher rates recognition when compared with other comparable studies. In this paper, we present a circular grid zoning method applied on Polar transformation recognition system. It compares the circular grid zoning (CGZ) and standard zoning (SZ) feature extraction method on Polar and Cartesian coordinate system. We report recognition rates of 923％, which are considerably higher than previous studies of zoning based Polar transformation system (86.6％) and zoning based Cartesian recognition system (80.6％). Based on the finding, we propose that our circular grid zoning based Polar transformation system may provide improved classification rates for complex offline handwritten recognition.
Feature extraction Polar transformation Hand-written character recognition Image processing
Xianjing Wang Atul Sajjanhar
School of Information Technology Deakin University, Australia
国际会议
2011 4th International Congress on Image and Signal Processing(第四届图像与信号处理国际学术会议 CISP 2011)
上海
英文
959-963
2011-10-15（万方平台首次上网日期，不代表论文的发表时间）