http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A License Plate Recognition System Based On SURF Algorithm
Nguyen Quoc Hung,A.A. Lensky,Jong Soo Lee 제어로봇시스템학회 2009 제어로봇시스템학회 국제학술대회 논문집 Vol.2009 No.8
The popularity and importance of intelligent transportation systems (ITS) are widely increasing. One of the big issue of the ITS system is an accurate late recognition feature. In this paper, we propose a novel license plate detection method based on the features [1] extracted from the speeded up robust features (SURF) algorithm. A “eatures dictionary”is constructed from the most frequent features and compared to a new input feature to find the appropriate license plate. A new detected feature is compared to the entire features in the dictionary to yield the distances between the feature and the features in the dictionary. The distances are used to estimate the probability density function. Moreover, the pattern matching framework utilizing the feature vectors and the dictionary are proposed. The final results of the experiment show that the average success rate is about 93 percent.