出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：The efficiency of an automatic number plate recognition system depends directly on the propereffective preprocessing of the number plate. The OCRs available for recognition are capable ofreading the number plates which are in proper orientation of 00. In many situations the vehiclenumber plates captured may be in any different orientation like 900, 1800 and 2700. Theseorientations in number plates are due to declamping of number plate at one end or toppling ofvehicle. Such differently oriented number plates cannot be subjected for reading by OCRs andsuch situations require the system to detect the direction of orientation and correct the samebefore subjecting the same for reading. This paper proposes a work to detect the orientation ofsegmented number plates from vehicle image using autocorrelation feature from gray level cooccurrencematrix. A good volume of training samples are generated synthetically to train thesystem and the system is tested using sufficient test samples. The results of system shows anoverall efficiency of 65.61% and performs an essential preprocessing in an automatic numberplate recognition system.
