The biometric data are stored in the template in which various techniques are used to protect it against privacy and security threats. The binary vector derived from biometric samples provide a great portion of template protection technique. For the same template protection system it is observed that there is a large variation on its key length. It determine the analytical relationship between the classification performance of the fuzzy commitment scheme and theoretical maximum key size given as input on Gaussian biometric source. The number of enrolment, verification sample, features component and biometric source capacity. It shows features of estimated maximum key size and classification performance are interdependent in analysis of the work. Both the theoretical analysis, as well as an experimental evaluation showed that feature interdependencies have a large impact on performance and key size estimates