Abstract: The use of the Choquet integral with respect to a 2-additive fuzzy measure in the pattern recognition is the subject of this study. As an aggregation tool the Choquet integral brings more sensitive results. Our main aims are to increase the sensitivity of the solution thanks to the fuzzy measure theory that considers the interaction among criteria and to reduce the computational effort in the solution of a pattern recognition problem that has numerous criteria thanks to 2-additivity. For this purpose, we introduce a new cosine similarity measure which is modified from some existing cosine similarity measures for interval-valued intuitionistic fuzzy sets via the Choquet integral with respect to a 2-additive fuzzy measure. Then, we apply it to a real pattern recognition problem from the literature. Finally, we compare the results with the some existing ones.