This article presents an implementation of Short Time Fourier Transform (STFT) in feature extraction process and Artificial Neural Networks (ANN) in classification for acoustic fingerprints recognition, applied to the identification of marine vessels. Currently the vessel recognition process from an acoustic signal is performed by human operators, which could lead to failures in the identification process. Before entering the ANN classification process, the signal is filtered and its spectral features are extracted using STFT. A comparison of the classification process between three types of neural networks is presented and the neurons in hidden layers are tested too. Experimental results show that the proposed vessel recognition scheme based on acoustic fingerprint is accurate and robust to variations in the signals, such as noise and changes in velocity and position.