Deep Inference Localization Approach of License Plate Recognition: A 2014 Series Philippine Vehicle License Plate

Abstract

License plates are the most reliable and cost-effective approach used for automobile verification purposes. With the advancement of technology, a different application that is related to the vehicle license plate such as license plate recognition has emerged and became a major area of research due to its diverse applications in many areas such as toll collection, road and traffic management, and for law enforcement. In the Philippines, due to the multiple versions of license plates, introducing such a system has made it difficult. To be able to adapt to this kind of system, this study proposed a system that uses a deep learning approach for detection or recognition of license plates focusing on the 2014 license plate format that can be used for different applications and purposes. The study utilized a simple but effective algorithm that is capable of detecting license plates accurately by generating a 100% accuracy as it can detect all the license plates in the video frames with 40%-60% precision.