In this study, a Mexican Hat Wavelet scalogram neural genetic network approach is proposed for signal classification. The Wavelet Scalogram network uses a Levenberg-Marquardt multilayer feed- forward neural network-genetic algorithm hybrid structure, and its input layer constitutes the feature extraction part, whereas the hidden layer and output layer constitute the signal classification part. From the physics point of view, it is shown that the time-shifted, frequency-modulated, and scaled Mexican Hat Wavelet scalogram is available for a basic model for the 1-D target Doppler signal of high-resolution radar. Logarithmic Normalization Method (LNM) was proposed for increasing efficiently of feature extraction phase of Wavelet Nero Genetic Network and classification. Two experiment examples show that the Wavelet Nero Genetic Network (WNGN) approach has a higher recognition rate in radar target recognition from Doppler signals as compared with several existing methods.