Application of Gaussian-Hermite Moments in License

In recent years, many researches on intelligent transportation systems (ITS) have been reported. ITSs are made up of 16 types of technology-based systems divided into intelligent infrastructure systems and intelligent vehicle systems. As one form of ITS technology, vehicle license plate recognition (VLPR) is one of important techniques that can be used for the identification of vehicles all over the world. There are many applications such as entrance admission, security, parking control, airport or harbor cargo control, road traffic control, speed control, toll gate automation and so on. LPR, as a means of vehicle identification, may be further exploited in various ways such as vehicle model identification, under-vehicle surveillance, speed estimation, and intelligent traffic management. Character recognition is an essential and important step in an ALPR system, which influences the overall accuracy and processing speed of the whole system significantly (Jia, 2007 & Christos-Nikolaos et al., 2008). However, few researches have been done for recognition of car plate character. Neural network method has been employed to recognize car plate characters. The method can achieve promising performance if the quality of the given car plate image is well. However, the quality of image taken for car plates is not always well. This is due to the operating conditions (e.g. dust on the car plates) and distortion or degraded because of poor photographical environment. Experiments have shown that it is difficult to achieve high car plate recognition rates only by extracting features from character are fed into neural network method (Rosenfeld, 1969, Huang et al., 2008). Moments, such as geometric moments and orthogonal moments, are widely used in pattern recognition, image processing, computer vision and multiresolution analysis (Shen, 1997, 2000; Wu & Shen, 2004; Wang et al., 2004, 2007; ). We present in this paper a study on Gaussian-Hermite moments (GHMs), their calculation, properties, application and so forth. In this paper, we at first the plate image by preprocessing algorithms (skew corrected, character segmentation, binary image and normalized) before recognition. Then, we propose the GHMs features as the input vector of BP neural network. Our analysis shows orthogonal moment’s base functions of different orders having different number of zero crossings and very different shapes, therefore they can better reflect image features based on different modes, which is very interesting for pattern analysis, shape classification, and detection of the moving objects. Moreover, the base functions of GHMs are much more smoothed; are thus less sensitive to noise and avoid the artifacts introduced by window