This paper presents a multimodal biometric fusion algorithm that supports biometric image quality and case-based context switching approach for selecting appropriate constituent unimodal traits and fusion algorithms. Depending on the quality of input samples, the proposed algorithm intelligently selects appropriate fusion algorithm for optimal performance. Experiments and correlation analysis on a multimodal database of 320 subjects show that the context switching algorithm improves the verification performance both in terms of accuracy and time. © 2009 Springer-Verlag Berlin Heidelberg.