We present an application of self-adaptive supervised learning classifiers derived from the machine learning paradigm to the identification of candidate globular clusters in deep, wide-field, single-band Hubble Space Telescope (HST) images. Several methods provided by the DAta Mining and Exploration (DAME) web application were tested and compared on the NGC 1399 HST data described by Paolillo and collaborators in a companion paper. The best results were obtained using a multilayer perceptron with quasi-Newton learning rule which achieved a classification accuracy of 98.3 per cent, with a completeness of 97.8 per cent and contamination of 1.6 per cent. An extensive set of experiments revealed that the use of accurate structural parameters (effective radius, central surface brightness) does improve the final result, but only by ∼5 per cent. It is also shown that the method is capable to retrieve also extreme sources (for instance, very extended objects) which are missed by more traditional approaches.