Vessel Registration Number Detection and Recognition System
Accurate identification of ships is vital for global trade and maritime security. More specifically, reliable recognition of the vessel registration number helps in orderly navigation and port use for maritime transportation activities. The purpose of this research was to develop and analyze different methods for detecting vessel registration numbers with a monocular camera. We used existing OCR tools available online and modified them to improve their out-of-the-box performance. Three neural network-based text detection methods were developed and tested. All three methods use different text region detection modules for real scenes, while available OCR software is used in all of them for specific character recognition. The methods are compared using standard optical character recognition metrics. The best method that was developed uses a deep neural network model to detect a vessel, then another fine-tuned neural network model to detect a text region, coupled with deterministic image processing methods to improve picture quality. In conclusion, with an accuracy of 72.69% recognized characters of vessel registrations using a limited image dataset, we achieve satisfactory results. Further effort focusing on collecting and annotating diverse maritime environment datasets featuring footage of vessels with visible registration numbers is needed to have a more reliable and robust system.