Threat Recognition is a primary task in Homeland Protection systems. When performing this task, Human in the Loop is the main part of a multidisciplinary reasoning process, that allows to achieve a high probability of correct classification. This reasoning process relies on two important factors, namely the past recognition history and the threat scenario. The Human in the Loop agent contributes both in controlling the automated process and in acting as a decision support system in different situations, such as dynamic changes in the scenario and occurrence of anomalous conditions. In this paper, we evaluate the performance of a multidisciplinary system, which uses a combination of a multisensory classification algorithm and a multidisciplinary fusion rule. This fusion rule combines the decisions coming from different channels with the reasoning process of a Human in the Loop agent. The performance evaluation of the multidisciplinary threat recognition system is carried out by considering different case studies. The evaluation demonstrates that a multidisciplinary system with a Human in the Loop agent can classify different threats, by using a set of methods and algorithms, with a high probability of correct classification, when compared to a completely automated recognition criterium.