Detection and Recognition of Malaysian Special License Plate Based On SIFT Features
This addresses a domain-specific problem for automated surveillance and law enforcement in Malaysia, but it is incremental as it applies an existing method (SIFT) to a new type of data (special plates).
The paper tackled the problem of recognizing Malaysian special license plates, which have non-standard formats like italic and cursive letters, by proposing a SIFT feature points clustering and matching algorithm. The result was a relatively robust algorithm tested on 150 images under different environments.
Automated car license plate recognition systems are developed and applied for purpose of facilitating the surveillance, law enforcement, access control and intelligent transportation monitoring with least human intervention. In this paper, an algorithm based on SIFT feature points clustering and matching is proposed to address the issue of recognizing Malaysian special plates. These special plates do not follow the format of standard car plates as they may contain italic, cursive, connected and small letters. The algorithm is tested with 150 Malaysian special plate images under different environment and the promising experimental results demonstrate that the proposed algorithm is relatively robust.