A method of vehicle license plate recognition utilizing Karhunen-Loeve(K-L) transform is provided. The transform is used to extract features from a mass of image templates, to describe high-dimensional images with low...A method of vehicle license plate recognition utilizing Karhunen-Loeve(K-L) transform is provided. The transform is used to extract features from a mass of image templates, to describe high-dimensional images with low-dimensional ones, and moreover, to implement data compression and play down complexity of the neural network. With the character to reduce eigenspace dimensionality of K-L transform and the ability to map data of BP network, the method does effectively in recognizing license plates.展开更多
Ambiguity function （AF） is proposed to represent ultrasonic signal to resolve the preprocessing problem of different center frequencies and different arriving times among ultrasonic signals for feature extraction, a...Ambiguity function （AF） is proposed to represent ultrasonic signal to resolve the preprocessing problem of different center frequencies and different arriving times among ultrasonic signals for feature extraction, as well as offer time-frequency features for signal classification. Moreover, Karhunen-Loeve （K-L） transform is considered to extract signal features from ambiguity plane, and then the features are presented to probabilistic neural network （PNN） for signal classification. Experimental results show that ambiguity function eliminates the difference of center frequency and arriving time existing in ultrasonic signals, and ambiguity plane features extracted by K-L transform describe the signal of different classes effectively in a reduced dimensional space. Classification result suggests that the ambiguity plane features obtain better performance than the features extracted by wavelet transform （WT）.展开更多
In the course of vehicle license plate （VLP） automatic recognition, tilt correction is a very crucial process. According to Karhunen-Loeve （K-L） transformation, the coordinates of characters in the image are arran...In the course of vehicle license plate （VLP） automatic recognition, tilt correction is a very crucial process. According to Karhunen-Loeve （K-L） transformation, the coordinates of characters in the image are arranged into a two-dimensional covariance matrix, on the basis of which the centered process is carried out. Then, the eigenvector and the rotation angle α are computed in turn. The whole image is rotated by -α. Thus, image horizontal tilt correction is performed. In the vertical tilt correction process, three correction methods, which are K-L transformation method, the line fitting method based on K -means clustering （LFMBKC）, and the line fitting based on least squares （LFMBLS）, are put forward to compute the vertical tilt angle θ. After shear transformation （ST） is imposed on the rotated image, the final correction image is obtained. The experimental results verify that this proposed method can be easily implemented, and can quickly and accurately get the tilt angle. It provides a new effective way for the VLP image tilt correction as well.展开更多
This paper proposed an improved method for license plate recognition based on hierarchical classification. First, the method of feature extraction and dimension reduction is presented by finding the optimal wavelet pa...This paper proposed an improved method for license plate recognition based on hierarchical classification. First, the method of feature extraction and dimension reduction is presented by finding the optimal wavelet packet basis in the process of wavelet packet decomposition and K-L transform. Then the recognition algorithm is introduced based on feature extraction and hierarchical classification. Finally, the principles and procedures of using support vector machines, Harris corner detection algorithm and digital character classification are explained in detail. Simulation results indicate that the presented recognition algorithm performs well with higher speed and efficiency in recognition.展开更多
Aimed at the problems of infrared image recognition under varying illumination,face disguise,etc.,we bring out an infrared human face recognition algorithm based on 2DPCA.The proposed algorithm can work out the covari...Aimed at the problems of infrared image recognition under varying illumination,face disguise,etc.,we bring out an infrared human face recognition algorithm based on 2DPCA.The proposed algorithm can work out the covariance matrix of the training sample easily and directly;at the same time,it costs less time to work out the eigenvector.Relevant experiments are carried out,and the result indicates that compared with the traditional recognition algorithm,the proposed recognition method is swift and has a good adaptability to the changes of human face posture.展开更多
The ambiguity function (AF) is proposed to represent the ultrasonic signal for its modulus’ independence of time shift and frequency shift, which avoids the effect of center frequency and arriving time of the ultraso...The ambiguity function (AF) is proposed to represent the ultrasonic signal for its modulus’ independence of time shift and frequency shift, which avoids the effect of center frequency and arriving time of the ultrasonic signal on feature extraction. Moreover, the K-L transform is considered to extract features from the ambiguity plane, and the effect of signals to noises on validity of ambiguity features is analyzed. Furthermore, we discuss the performance of recognizing ultrasonic signals at different center frequencies and different arriving time based on ambiguity features. Experimental results show that the features extracted by the K-L transform (KLT) are immune to noises, and can recognize ultrasonic signals effectively in a lower dimensional space.展开更多
文摘A method of vehicle license plate recognition utilizing Karhunen-Loeve(K-L) transform is provided. The transform is used to extract features from a mass of image templates, to describe high-dimensional images with low-dimensional ones, and moreover, to implement data compression and play down complexity of the neural network. With the character to reduce eigenspace dimensionality of K-L transform and the ability to map data of BP network, the method does effectively in recognizing license plates.
文摘Ambiguity function （AF） is proposed to represent ultrasonic signal to resolve the preprocessing problem of different center frequencies and different arriving times among ultrasonic signals for feature extraction, as well as offer time-frequency features for signal classification. Moreover, Karhunen-Loeve （K-L） transform is considered to extract signal features from ambiguity plane, and then the features are presented to probabilistic neural network （PNN） for signal classification. Experimental results show that ambiguity function eliminates the difference of center frequency and arriving time existing in ultrasonic signals, and ambiguity plane features extracted by K-L transform describe the signal of different classes effectively in a reduced dimensional space. Classification result suggests that the ambiguity plane features obtain better performance than the features extracted by wavelet transform （WT）.
基金supported by Scientific Research Fund of Hunan Province, PRC (No. 07JJ6141)Scientific Research Fund of Hunan Provincial Education Department, PRC (No. 06C582)
文摘In the course of vehicle license plate （VLP） automatic recognition, tilt correction is a very crucial process. According to Karhunen-Loeve （K-L） transformation, the coordinates of characters in the image are arranged into a two-dimensional covariance matrix, on the basis of which the centered process is carried out. Then, the eigenvector and the rotation angle α are computed in turn. The whole image is rotated by -α. Thus, image horizontal tilt correction is performed. In the vertical tilt correction process, three correction methods, which are K-L transformation method, the line fitting method based on K -means clustering （LFMBKC）, and the line fitting based on least squares （LFMBLS）, are put forward to compute the vertical tilt angle θ. After shear transformation （ST） is imposed on the rotated image, the final correction image is obtained. The experimental results verify that this proposed method can be easily implemented, and can quickly and accurately get the tilt angle. It provides a new effective way for the VLP image tilt correction as well.
文摘This paper proposed an improved method for license plate recognition based on hierarchical classification. First, the method of feature extraction and dimension reduction is presented by finding the optimal wavelet packet basis in the process of wavelet packet decomposition and K-L transform. Then the recognition algorithm is introduced based on feature extraction and hierarchical classification. Finally, the principles and procedures of using support vector machines, Harris corner detection algorithm and digital character classification are explained in detail. Simulation results indicate that the presented recognition algorithm performs well with higher speed and efficiency in recognition.
基金Sponsored by the Natural Science Fund of Heilongjiang province(Grant No. F2007-13)Science and Technology Research Projects in Office of Education of Heilongjiang province(Grant No.11531034)the Heilongjiang Postdoctoral Science Foundation(Grant No.LBH-Z06054)
文摘Aimed at the problems of infrared image recognition under varying illumination,face disguise,etc.,we bring out an infrared human face recognition algorithm based on 2DPCA.The proposed algorithm can work out the covariance matrix of the training sample easily and directly;at the same time,it costs less time to work out the eigenvector.Relevant experiments are carried out,and the result indicates that compared with the traditional recognition algorithm,the proposed recognition method is swift and has a good adaptability to the changes of human face posture.
文摘The ambiguity function (AF) is proposed to represent the ultrasonic signal for its modulus’ independence of time shift and frequency shift, which avoids the effect of center frequency and arriving time of the ultrasonic signal on feature extraction. Moreover, the K-L transform is considered to extract features from the ambiguity plane, and the effect of signals to noises on validity of ambiguity features is analyzed. Furthermore, we discuss the performance of recognizing ultrasonic signals at different center frequencies and different arriving time based on ambiguity features. Experimental results show that the features extracted by the K-L transform (KLT) are immune to noises, and can recognize ultrasonic signals effectively in a lower dimensional space.
