Biometrics lack revocability and privacy while cryptography cannot detect the user's identity. By obtaining cryptographic keys using biometrics, one can achieve the properties such as revocability, assurance about user's identity, and privacy. In this paper, we propose a multi-biometric based cryptographic key regeneration scheme. Since left and right irises of a person are uncorrelated, we treat them as two independent biometrics and combine in our system. We propose a novel idea for feature level fusion through weighted error correction to obtain a multi-biometric feature vector which is used to get a secure template. A shuffling key which is protected by a password is used to shuffle the error correcting codes data. The password helps improve revocability, privacy, and security of the system. We succeed to generate 147-bit long keys with as much entropy at 0% FAR and 0.18% FRR on the NIST-ICE database