International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 181 - Number 29 |
Year of Publication: 2018 |
Authors: Mohammad Jaber Hossain, Md. Hasan Uzzaman, A. F. M. Saifuddin Saif |
10.5120/ijca2018918140 |
Mohammad Jaber Hossain, Md. Hasan Uzzaman, A. F. M. Saifuddin Saif . Bangla Digital Number Plate Recognition using Template Matching for Higher Accuracy and Less Time Complexity. International Journal of Computer Applications. 181, 29 ( Nov 2018), 15-21. DOI=10.5120/ijca2018918140
The importance of vehicle number plate detection is increasing day by day notably in Bangladesh for digitalized transportation system. Particularly in situation to find out the lost vehicle, improvement of security, access of vehicles in restricted areas, to save time in toll gates and detecting the guilty vehicles which are involved in road accidents or other related crime. This paper represents a method of Bangla number plate recognition. The propose method have four main steps-preprocessing, number plate extraction, segmentation of characters and character recognition. In preprocessing step need to convert the test image in gray level first and then binarized using Otsu method. Sobel edge operator, morphological dilation and erosion are used to find the plate location. Boundary box feature in used for segmentation of characters. Then template matching technique was applied for recognition of the characters. The proposed method is more effective to extract the license plate region. The recognition rate and time required to extract is also improved then some other studies done earlier.