Robust Car License Plate Localization using a Novel Texture Descriptor

Chu Duc Nguyen 1 Mohsen Ardabilian 1 Liming Chen 1
1 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : 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 arm 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 are 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.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01437683
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Tuesday, January 17, 2017 - 1:55:29 PM
Last modification on : Thursday, November 21, 2019 - 2:27:32 AM

Identifiers

Citation

Chu Duc Nguyen, Mohsen Ardabilian, Liming Chen. Robust Car License Plate Localization using a Novel Texture Descriptor. 6th IEEE International Conference On Advanced Video and Signal Based Surveillance (AVSS), Sep 2009, Genoa, Italy. pp.523-528, ⟨10.1109/AVSS.2009.22⟩. ⟨hal-01437683⟩

Share

Metrics

Record views

227