Backpropagation neural networks (BPNNs) were used to distinguish among 10 olive (Olea europaea L.) cultivars, originating throughout the Mediterranean basin. Identification was performed on the basis of 17 phyllometric parameters resulting from image analysis. Different BPNN architectures were attempted and best performance was achieved using a 17 × 20 × 10 BPNN. Networks were tested with sets of phyllometric parameters not involved in the training phase. Results enabled identification with certainty all cultivars tested.