In this paper, a fuzzy commitment scheme is applied with a machine vision gait-based biometric system to enhance system security. The proposed biometric cryptosystem has two phases: enrolment and verification. Each of them comprises three main stages: feature extraction, reliable components extraction, and fuzzy commitment scheme. Gait features are extracted from gait images using local ternary pattern (LTP), and then, the average of one complete gait cycle using the gait energy image (GEl) concept is calculated. The average images are joined using a 2D joint histogram, which is reduced using principal component analysis (PCA) to produce the final feature vector. To enhance the robustness of the system, only highly robust and reliable bits from the feature vector are extracted. Finally, the fuzzy commitment scheme is used to secure feature templates. Bose–Chaudhuri–Hocquenghem codes (BCH) are used for key encoding in the enrolment phase and for decoding in the verification phase. The proposed system is tested using the CMU MoBo and CASIA A databases. The experimental results show that the best error rate for the CMU MoBo database is obtained when using a fast walk for enrolment and verification, where we obtain 0% for the false acceptance rate (FAR) and 0% for the false rejection rate (FRR) for a key length equal to 50 bits. The best error rate for CASIA A dataset is obtained when using the 45-degree direction to the image plane view for enrolment and verification, where we obtain 0% for the false acceptance rate (FAR) and 0% for the false rejection rate (FRR) for a key length equal to 45 bits.