Radar sensors in automotive cars are crucial for detecting and avoiding obstacles, improving safety, and enabling advanced driver-assistance systems. The signal-to-noise ratio (SNR) is a significant metric in radar systems for detecting the target at the output of the radar receiver and classifying the images in the algorithm classification. The purpose of this study is to determine the minimum SNR of images and signals to achieve high classification accuracy. A public dataset based on impulse radar and the LeNet-5 CNN architecture were used. The simulations demonstrated that images with an 10 dB of SNR can be classified with a high accuracy of 98%, and a 0 dB SNR at the output of the radar receiver was reported to be the minimum SNR required at the front-end output.