Robust Car License Plate Localization Using a Novel Texture Descriptor

This paper presents a novel texture descriptor based on line-segment features for text detection in images and video sequences, which is applied to build a robust car license plate localization system. Unlike most of existing approaches which use low level features (color, edge) for text/non-text discrimination, our aim is to exploit more accurate perceptual information. A - scale and rotation invariant - texture descriptor which describes the directionality, regularity, similarity, alignment and connectivity of group of segments is proposed. A improved algorithm for feature extraction based on local connective Hough transform has been also investigated. The robustness of our approach is proved throughout a real-time detection/verification scheme of car license plate. First, all possible candidates are detected using a rule based method, which is very robust to illumination change and in varying poses. Then, true license plates are identified by the mean of a SVM classifier trained with proposed descriptor. Comparison and evaluation are conducted with two complex datasets.