Robust Blur Kernel Estimation for License Plate Images From Fast Moving Vehicles

Vehicle license plates serve as the unique identification for a vehicle and often play a critical role in the identification of vehicles involved in hit-and-run accidents. One challenge to capturing license plates via traffic surveillance camera is that the fast motion of the vehicle can cause the plate to be blurred. In recent years, blind image deblurring/deconvolution (BID) has gained lots of attention from the image processing community. For license plate image blurring caused by fast motion, the blur kernel can be viewed as linear uniform convolution and parametrically modeled with angle and length. In this article, the authors propose a novel kernel parameter estimation algorithm for license plate identification from fast-moving vehicles. Their proposed scheme is able to handle large motion blur even when the the image cannot be recognized by the human eye, and the authors suggest that it is a great improvement in the area of license plate recognition.

• Record URL:
  • https://doi.org/10.1109/TIP.2016.2535375
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/10577149
• Authors:
  • Lu, Qingbo
  • Zhou, Wengang
  • Fang, Lu
  • Li, Houqiang
• Publication Date: 2016

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; Photos; References; Tables;
• Pagination: pp 2311-2323
• Serial:
  • IEEE Transactions on Image Processing
  • Volume: 25
  • Issue Number: 5
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
  • ISSN: 1057-7149

Subject/Index Terms

• TRT Terms: Automatic vehicle identification; High speed vehicles; Image processing; License plates
• Uncontrolled Terms: Kernel estimation
• Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management;

Filing Info

• Accession Number: 01602658
• Record Type: Publication
• Files: TRIS
• Created Date: Jun 27 2016 3:03PM