30-07-2012, 03:51 PM
A license plate recognition algorithm for Intelligent Transportation System applications
A license plate recognition.pdf (Size: 1.21 MB / Downloads: 108)
I. INTRODUCTION
dURING the recent years, Intelligent Transportation Systems (ITS) are having a wide impact in people’s life as their scope is to improve transportation safety and mobility and to enhance productivity through the use of advanced technologies. ITS are made up of 16 types of technology based systems. These systems are divided into intelligent infrastructure systems and intelligent vehicle systems [1].
Character segmentation
The license plate candidates determined in the previous stage are examined in the license number identification phase. There are two major tasks involved in the identification phase, character segmentation and character recognition. A number of techniques to segment each character after localizing the plate in the image have also been developed, such as feature vector extraction and mathematical morphology [32] and Markov Random Fields [22].
SCW SEGMENTATION METHOD
Hypothetically, license plates can be viewed as irregularities in the texture of the image and therefore abrupt changes in the local characteristics of the image, manifest probably the presence of a license plate. Based on the above, this paper proposes a novel adaptive segmentation technique named Sliding Concentric Windows (SCW).
SAMPLE SET – EXPERIMENTAL RESULTS
The complete testing image database consists of 1334 digital images from different 5 sample sets. The majority of the images represents Greek license plates from natural scenes obtained in various illumination conditions. Sample sets 1 and 2 (Fig. 8) contain actual images acquired from a testbed set in the National Technical University of Athens campus, which consisted of a digital camera, a vehicle proximity sensor, the PC and the communication cables. The images were not processed in real-time but stored for later processing.
From 1983 the license plates in Greece have a standard format of three alphabets and four numerals. The first one or two of the alphabets are indicative of the prefecture where the vehicle is registered. For instance, in the wide region of Athens (Attica) the first letter of the plate was originally set to “Y”.
SUMMARY-FUTURE EXTENSIONS
The operation of an automated vehicle license plates recognition system was analyzed in the present paper in terms of software and hardware aspects. Its operation is divided in two image processing phases: the phase of license plate segmentation and the phase of license plate processing and character recognition.