Title :
Algorithm for multinational license plate localization and character segmentation
Author :
Shiying, Mo ; Weixin, Zhou ; Na´na, Lv ; Yaxin, Sun ; Wen, Huang
Author_Institution :
Sch. of Phys. & Telecommun. Eng., South China Normal Univ., Guangzhou, China
Abstract :
As the difference of gray value between the numbers and letters on the license plate and the license plate background is very big. We first use region growing algorithm based on the gray value to separate each number and letter into different area. Secondly, we search for the bounding rectangles of all regions and find some rectangular sequences that meet a special condition. Thirdly, calculate the horizon bias for all rectangles according to the coordination of the up-right point in the rectangle, adjust and get the precise location of each rectangle. Forth, we get the binary image which can separate the numbers and letters on the license plates and the license plate background by the dynamic threshold algorithm. The relation of the maximum width of various license plate numbers and letters and its bounding rectangles helps to count the direction of the vertical bias, then the bias is adjusted. At last we statistic the foreground vertical histogram of the previous results, and get the result of precise vertical position and character segmentation. The experimental results show that this algorithm performs well for location of multi-national license plates.
Keywords :
character recognition; image segmentation; image sequences; traffic engineering computing; binary image; character segmentation; dynamic threshold algorithm; foreground vertical histogram; gray value; multinational license plate localization algorithm; precise vertical position; rectangular sequence; vertical bias; Educational institutions; Heuristic algorithms; Image color analysis; Image edge detection; Instruments; Licenses; Vehicles; character segmentation; license plate correction; license plate location;
Conference_Titel :
Electronic Measurement & Instruments (ICEMI), 2011 10th International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-8158-3
DOI :
10.1109/ICEMI.2011.6037861