目前在車牌辨識系統的應用上,大多在高速公路、收費停車場以及社區大樓停車場的應用等,當環境控制得當時,其辨識率達到九成以上,但大多仍受限於環境及天候因素,至今仍無法達到百分之百的辨識率。 本研究所希望能夠希望能夠協助警調單位於贓車查緝或道路可疑車輛的過濾,與一般車牌辨識系統的不同處為所擷取的影像背景複雜度較高,且可能同時擷取到一部以上的車輛,因此需要在處理時,過濾更多的無用影像物件,保留有用的車牌影像供後續牌照辨識之用。 針對多目標判定、反向判定及車輀屬性各階段皆有九成以上的辨識率,在車號辨識率方面,在單目標與多目標影像亦有91.77%與88.58%的辨識率。
License plate recognition systems may be deployed in a variety of applications such as, highway toll systems, traffic control systems, or parking lot management systems. Due to the volatile work environments, it is not practical for a system to claim 100% recognition rate. However, under the circumstances where the environment is controlled to a certain degree, it is not uncommon for the vehicle license plate recognition rate to reach the level of 90s. Most commonly available license plate recognition systems recognize only static pictures. In this study, a motion-based multiple targets vehicle license plate recognition prototype is proposed. Multiple-frames of pictures are used for recognition. As a result, the time for preprocessing stages is critical and developing time-efficient algorithms become more important. This prototype is designed mainly for specific car-search that should be helpful for many organizations such as police departments or highway patrol departments. In this study, a real time hybrid approach is proposed for motion-based multiple targets vehicle license plate recognition. A system prototype will be built which can be used independently or cooperating with current vehicle identification system in identifying a vehicle. The prototype consists of four major modules, including the module for image processing, the module for license plate region identification, the module for character extraction, and the module for pattern recognition called SimNet.