From Friday, April 19th (11:00 PM CDT) through Saturday, April 20th (2:00 PM CDT), 2024, ni.com will undergo system upgrades that may result in temporary service interruption.
We appreciate your patience as we improve our online experience.
Student Projects
Contact Information
University and Department: UPC.EPSEVG, Electronic Engineering Dpt.
Team Members: David Sarriá
Faculty Advisors: Joaquín del Río
Primary Email Address: d_sarria@hotmail.com
Project Information
Project Title: Vision System for Plate Numbers Recognition
List all parts (hardware, software, etc.) you used to design and complete your project: LabVIEW, Vision Development Module, Visual C++, PCI-1408, JAI CV-M50 camera and webcam
Describe the challenge your project is trying to solve.
The project aims to learn the techniques, tools and elements of a vision system and the development of an application for recognition of plates numbers through LabVIEW programming enviroment.
Describe how you addressed the challenge through your project.
Image acquisition is done through a web camera. Different techniques of image processing and analysis are applied to the image. Then, the plate number is located by extraction methods. Finally, the alphanumeric code of the plate number is obtained by applying an optical character recognition.
The study began with an industrial camera and a frame grabber from National Instruments. Then, it was possible to work with a webcam. This way we would have a low cost and portable vision system.
Existing methods for locating the plate number are: Edge detection and Mathematical morphology
Edge Detection Step (sobel operator has been applied): the image is captured in grayscale, a edge detection is performed, then a calculation of changes in contrast for each line of the image is done and finally, the area with the largest number of variations is located.
Mathematical morphology: allows to obtain the left and right edge of the plate number.
Conclusions: it has been developed a low cost and portable vision system that meets the goals and extract the plate number from the image regardless of its position in the image and/or its format or aspect ratio. By mean of the algorithms developed it has been possible to take advantage of the two extraction methods known for plates numbers (edge detection and mathematical morphology) and have obtained good results with complex images.
The system has many practical applications such as traffic control, detection of stolen vehicles, billing systems for parking ...
