For low probability of intercept (LPI) radar waveform identication accuracy (ACC) problem at low Signal-to-Noise Ratios (SNRs), an approach based on time-frequency analysis (TFA) and Asymmetric Dilated Convolution Coordinate Attention Residual networks (ACDCA-ResNeXt) is proposed to recognize twelve kinds of LPI radar signals automatically. First, we apply Choi-Williams distribution (CWD), which shows superior performance at low SNRs, to transforming radar signals into time-frequency images (TFI). Then, in order to obtain the high-quality TFIs, a series of image processing techniques, including 2D Wiener ltering, image cutting, and image resize, are used to remove the background noise and redundant frequency bands of the TFI and obtain a xed-size gray scale image containing main morphological features of the TFI. Finally, the TFIs are input into ACDCA-ResNeXt network that can extract and learn deep features to recognize radar waveforms. Furthermore, a fusion loss function, which is composed of a soft-label smoothed cross entropy loss function and a center loss function, improves the generalization capability performance of network and achieves a better clustering eect. Experimental results demonstrate that, for twelve kinds of LPI radar waveforms, the overall recognition ACC of the proposed approach achieves 97.94% when SNR is -8 dB. INDEX TERMS Radar waveform recognition, time-frequency analysis (TFA), asymmetric convolution (AC), dilated convolution, coordinate attention (CA) mechanism.