Low-Resolution Chinese Character Recognition of Vehicle License Plate Based on ALBP and Gabor Filters

Low-resolution Chinese character recognition of vehicle license plate is always a difficult problem. On the basic of existing local binary patterns(LBP) operator, we propose a powerful and low-computation advanced LBP(ALBP)operator as feature extraction, and apply into Chinese character recognition for the first time. As local feature extraction operater, it produces a feature excursion for characters of barycenter departure. Therefore we use the advantage of global analysis of Gabor filters, construct Gabor filters to recognize characters of barycenter departure. The experimental results show the method is robust against low quality Chinese characters and more adaptive than conventional approach both on preciseness and recognition speed.