License plate location based on singular value feature

Locating the vehicle license plate plays an important role in the vehicle license plate automatic recognition system, At present license plate gray feature and texture feature were considered in the most license plate location methods, however, these methods have weak adaptability in different environment. To solve these problems, license plate location based on singular value feature is proposed on the basis of gray feature of license plate. License plates and non-plate regions can be distinguished by extracting the singular value feature, which is described by Hidden Markov Models (HMM). Experimental results show that accurate positioning of different licenses can be achieved in complex environment and variable illumination conditions with a strong robustness.