FIRE is a Fast Iris REcognition algorithm especially designed for iris recognition on mobile phones under visible-light. It is based on the combination of three classifiers exploiting the iris colour and texture information. Its limited computational time makes FIRE particularly suitable for fast user verification on mobile devices. The high parallelism of the code allows its use also on large databases. FIRE, in its first version, was submitted to the Mobile Iris CHallenge Evaluation part II held in 2016. In this paper, FIRE is further improved: a number of different techniques has been analyzed and the best performing ones have been selected for fusion at score level. Performance are assessed in terms of Recognition Rate (RR), Area Under Receiver Operating Characteristic Curve (AUC), and Equal Error Rate (EER).