Abdelhakim Zeroual
Abdelhakim Zeroual has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Abdallah Meraoumia
University of Larbi Tebessi, Laboratory of Mathematics, Informatics and Systems (LAMIS), Tebessa
2 shared publications - Atef Bentahar
Larbi Tebessi University,LAboratory of Mathematics, Informatics and Systems (LAMIS),Tebessa,Algeria,12002
2 shared publications - Hakim Bendjenna
Echahid Cheikh Larbi Tebessi University
2 shared publications - Salim Chitroub
LISIC Laboratory, Science Faculty, USTHB, Algiers, Algeria
1 shared publication - Tarek Bentahar
Larbi Tebessi University,LABGE T-laboratery,Tebessa,ALGERIA,12002
1 shared publication
Latest Publications
- 12 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Combination of Closed-Set and Open-Set Biometric Identification
The decision phase may be the most important phase of a biometric system. The human can be accepted or rejected based on the decision taken, that is built on a predefined threshold in the open-set systems, whereas in closed-set systems, the decision is built on the minimum score. Both systems have many drawbacks if they are performed separately. This paper presents a new identification system that combines the two systems. This combination offers all the advantages of both systems and overcomes their disadvantages. Consequently, this combination results new identification evaluation criteria. These new criteria are also described in this paper.
- 12 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Combination of Closed-Set and Open-Set Biometric Identification
The decision phase may be the most important phase of a biometric system. The human can be accepted or rejected based on the decision taken, that is built on a predefined threshold in the open-set systems, whereas in closed-set systems, the decision is built on the minimum score. Both systems have many drawbacks if they are performed separately. This paper presents a new identification system that combines the two systems. This combination offers all the advantages of both systems and overcomes their disadvantages. Consequently, this combination results new identification evaluation criteria. These new criteria are also described in this paper.
- 1 October 2021
- Published by Bentham Science Publishers Ltd. in Recent Advances in Computer Science and Communications
- Vol. 14 (7) , 2087-2102
Biometric Cryptosystems: Towards a Light and Precise Remote Authentication
Background: Remote authentication in current networks such as IoT that connects many end-devices of low capacity must be light, accurate and scalable without threaten security. In general, biometrics is the most reliable way to authenticate users because of its efficient results in many applications. Objective: The biometric data is expressed by a feature vector that should be extracted and secured by reliable techniques. This paper proposes a suitable extraction and encryption scheme in the aim to make the authentication light, accurate, scalable and secure. Method: As extraction technique, principle component analysis with a nonlinear block average quantization is used to reduce the feature vector length in the aim to increase the rapidity and the scalability. As encryption technique, the fuzzy commitment and the fuzzy vault with Hamming and Reed-Solomon codes are used in to increase security. These cryptosystems are tested with multi-biometric modalities to make the validation more credible. Results: Experimental results are analyzed, validated and compared to other works according to several conventional and new recognition rates. Analysis is also done in terms of computation time to validate the lightness of our findings. It is shown that the proposed scheme finds a compromise between the coveted features. Conclusion: Our biometric cryptosystems ensure a secure, light, precise and scalable remote authentication. These properties can be achieved by using PCA technique with nonlinear coefficient quantization and fuzzy schemes with the appropriate correcting-code.
- 1 October 2021
- Published by Bentham Science Publishers Ltd. in Recent Advances in Computer Science and Communications
- Vol. 14 (7) , 2087-2102
Biometric Cryptosystems: Towards a Light and Precise Remote Authentication
Background: Remote authentication in current networks such as IoT that connects many end-devices of low capacity must be light, accurate and scalable without threaten security. In general, biometrics is the most reliable way to authenticate users because of its efficient results in many applications. Objective: The biometric data is expressed by a feature vector that should be extracted and secured by reliable techniques. This paper proposes a suitable extraction and encryption scheme in the aim to make the authentication light, accurate, scalable and secure. Method: As extraction technique, principle component analysis with a nonlinear block average quantization is used to reduce the feature vector length in the aim to increase the rapidity and the scalability. As encryption technique, the fuzzy commitment and the fuzzy vault with Hamming and Reed-Solomon codes are used in to increase security. These cryptosystems are tested with multi-biometric modalities to make the validation more credible. Results: Experimental results are analyzed, validated and compared to other works according to several conventional and new recognition rates. Analysis is also done in terms of computation time to validate the lightness of our findings. It is shown that the proposed scheme finds a compromise between the coveted features. Conclusion: Our biometric cryptosystems ensure a secure, light, precise and scalable remote authentication. These properties can be achieved by using PCA technique with nonlinear coefficient quantization and fuzzy schemes with the appropriate correcting-code.