![]() | Only 14 pages are availabe for public view |
Abstract This thesis offers an integrated system for automatic number plate recognition of Egyptian vehicles following the extraction of number plate from the general framework of the image. These systems are the most advanced branches of science developed in the past years. It is worth mentioning that there is a scarcity in researches that introduce an automatic number plate recognition which depends on Arabic language. The importance of these systems returns to the multiplicity of applications in many of the areas of combating crimes, traffic control, roads management and detection of stolen vehicles. Reading the number plate of vehicles automatically is achieved by passing the following stages:- First stage: Extraction the number plate of vehicles from the general framework of the image through the use of Edge detection and image analysis techniques to extract parts of the image in order to identify some of their components. Second stage: Recognition of the number plate from the system database through the use of new innovation of the proposed algorithm that does not need a process for segmentation of input image of number plate (character segmentation) but finds features in the whole number plate image. LDA and DCT feature extraction methods are used to classify the given number plate. The experimental results show that our new method has higher recognition accuracy than using traditional methods in case of ignoring the country logo. |