- 期刊
An Improved Binarization Method for Passenger Car Limited-load Character Area
摘要
There is important information in the body text. In order to effectively extract the text area of the passenger car body, a modified binarization algorithm based on the bernsen algorithm is proposed for the body text characteristics. The algorithm is carried out on the sample of the passenger car. Experiments, and compared with the classical local threshold binarization methods bernsen, Niblack, Sauvola, etc., subjective visual assessment and objective image quality assessment (IQA) results show that the proposed method performs better in terms of preservation and differentiation of character regions.
參考文獻
Dalida J P D, Galiza A J N, Godoy A G O, et al. Development of intelligent transportation system for Philippine license plate recognition[C]// 2016 Institute of Electrical and Electronics Engineers Region 10 Conference (TENCON). Institute of Electrical and Electronics Engineers, Singapore, 2017: 3762-3766
Nobuyuki Otsu. A Threshold Selection Method from Gray- Level Histograms[ J] . IEEE Transactions on Systems Man & amp; Cybernetics, 1979 , 9 ( 1 ) : 62 - 66
Pun T. A new method for grey-level picture thresholding using the entropy of the histogram[J]. Signal Processing, 1980, 2(3): 223-237
J. Sauvola, M. Pietikainen. Adaptive document image binarization Pattern Recognition[J]. Pattern Recognition, 2000, 33(2): 225-236
Zheng X, Tan W, Du J. A Fast Adaptive Binarization Method Based on Sub Block OSTU and Improved Sauvola[C]// 2011 7th International Conference on Wireless Communications, Networking and Mobile Computing, Wuhan, 2011: 1-5