Use of multiple features in license plate detection

Recognition of license plates in images is analyzed in two steps as the detection of the license plate and the recognition of the text included within. Although this problem is widely regarded as solved, there is still room for research and development in cases of low quality images and existence of other structures in images hindering correct detection. In this paper, the techniques used in the detection process are evaluated and it is shown that employment of multiple features improves success rate compared to the implementations where only a single feature is used.