Skip to Main Content
An approach of vehicle license plate recognition (VLPR) based on Gabor filter is presented in this paper. The parameters of Gabor filter are different from most traditional ways in the field. The novel way enables us to concisely model the statistical dependencies, and achieve a more reliable and local model using blocks. Firstly, the accurate position of license plate must be extracted from the original image, and each character must be segmented from the segmented license plate. Then, we propose a new simple and fast way, which based on many traditional algorithms of biology recognition, to design these parameters of Gabor filter. Be detected by Gabor filters, the features of each to-test character are represented as a set of the corresponding coefficients. The last step is to classify these to-test characters by the Euclidean distance between the coefficient vectors of the to-test characters and templates. Experiments are conducted on 120 images taken from various illumination situations and experimental results show that the approach is feasible and applicable.