IJCSNS International Journal of Computer Science and Network Security, VOL.9 No.1, January 2009
Manuscript received January 5, 2009
Manuscript revised January 20, 2009
A CAM-Based Pattern Accumulated Vector Method
for Real-Time Character Recognition of License Plates
Yon-Ping Chen, Tien-Der Yeh, Feng-Chou Ni and Chung-Hsien Chang
Electrical and Control Engineering, National Chiao Tung University,, 1001 Ta Hsueh Rd., Hsinchu / Taiwan, ROC
A novel Pattern Accumulated Vector(PAV) method implemented
by CAM-based architecture has been proposed for character
recognition in license plate recognition(LPR). Instead of
comparing all the pattern blocks, the PAV method adopts the
principal pattern blocks as feature vectors so that the computation
complexity is highly reduced. Furthermore, the PAV method
adopts the extended templates for the character recognition and is
proved to have higher recognition rate when dealing with license
inclined characters. Finally,
architecture is used to further reduce the processing time and
makes the PAV method more efficient for real-time LPR systems.
Content Addressable Memory(CAM), Pattern Accumulated
Vector(PAV), License Plate Recognition(LPR), Character
Recognition, principal pattern blocks.
The license plate recognition, or LPR in short, has been
a popular research topic for several decades   .
Up to now, an LPR system still faces some problems
concerning various light condition, image deformation,
and processing time consumption  . In general,
there are three fundamental steps required for the process
of an LPR system, including the license plate extraction,
the character segmentation, and the character recognition.
Since many methodologies have been well developed for
the first two steps, the license plate extraction and the
character segmentation , this paper will only focus
on the third step, the character recognition, especially for