Project

Car license plate recognition using template matching algorithm

Project (M.S., Electrical and Electronic Engineering) -- California State University, Sacramento, 2010.

License Plate Recognition or LPR is an image-processing technology used to identify vehicles by their license plates. This technology is used in various applications involving security, traffic, law enforcement, public safety and transportation sectors. It mainly uses software code that enables computer systems to read automatically the registration number (license number) of vehicles from digital pictures.
 The project explains various algorithms that are exercised to recognize the characters present on the California Car License Plate. One of them is Template Matching algorithm that has an ability to store the information of a particular size template in the form of four 16-bit vectors and apply it for recognizing the characters. This feature of the algorithm mentioned above helped in achieving faster character recognition of the license plate. This process of character recognition consists of steps like Image processing, Defragmentation, Resizing and Character localization that are required to be performed on the image in order for Template Matching to be done.
 The final goal of the project was to simulate these algorithms initially on Microsoft Visual Studio using Open CV libraries. Once this was established, the design was transferred on the TI’s video development platform DM6437 DVDP for testing and performance analysis. The earlier mentioned algorithmic steps were written in C programming language and demonstration of the project was successfully presented on the TI’s DSP board EVM320DM6437.

License Plate Recognition or LPR is an image-processing technology used to identify vehicles by their license plates. This technology is used in various applications involving security, traffic, law enforcement, public safety and transportation sectors. It mainly uses software code that enables computer systems to read automatically the registration number (license number) of vehicles from digital pictures. The project explains various algorithms that are exercised to recognize the characters present on the California Car License Plate. One of them is Template Matching algorithm that has an ability to store the information of a particular size template in the form of four 16-bit vectors and apply it for recognizing the characters. This feature of the algorithm mentioned above helped in achieving faster character recognition of the license plate. This process of character recognition consists of steps like Image processing, Defragmentation, Resizing and Character localization that are required to be performed on the image in order for Template Matching to be done. The final goal of the project was to simulate these algorithms initially on Microsoft Visual Studio using Open CV libraries. Once this was established, the design was transferred on the TI’s video development platform DM6437 DVDP for testing and performance analysis. The earlier mentioned algorithmic steps were written in C programming language and demonstration of the project was successfully presented on the TI’s DSP board EVM320DM6437.

Relationships

Items