AMAbdallah Meraoumia

Abdallah Meraoumia

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Abdallah Meraoumia has a total of 46 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Efficient Contactless Palmprint Recognition System Based on Deep Rule-Based Classification

    by Yacine Belhocine, Abdallah Meraoumia, Khediri Abderrazak, Mohammed Saigaa

    Peer-reviewed journal on social and business aspects of informatics that covers the theory and application of enterprise information systems, as well as interactions between ICT and people.


  • Open Access

    Innovations in Deep Learning and Intelligent Systems for Healthcare and Engineering Applications

    by Hakim Bendjenna, Lawrence Chung, Abdallah Meraoumia

    Peer-reviewed journal on social and business aspects of informatics that covers the theory and application of enterprise information systems, as well as interactions between ICT and people.

  • Open Access

    An Adaptive Image Watermarking based on Bellman-Ford Algorithm

    by Brahim Ferik, Lakhdar Laimeche, Abdallah Meraoumia, Abdelkader Laouid, Muath Alshaikh, Khaled Chait

    Ensuring the integrity and authenticity of images is a paramount task in the digital multimedia context. The emergence of digital technologies necessitates the development of robust techniques to safeguard medical images against tampering or unauthorized alterations. One such crucial approach is watermarking, which involves embedding imperceptible and secure data within the images to facilitate subsequent verification and authentication. This paper proposes a novel medical image watermarking technique utilizing fingerprint data and a hybrid standard deviation-Bellman Ford algorithm for enhanced security and minimal distortion. The host image is divided into blocks, and the standard deviation quantifies texture variations. The Bellman-Ford algorithm then identifies optimal paths in the image graph corresponding to regions suitable for embedding. Our methodology diverges from existing techniques by enabling adaptive watermark embedding within textured domains while circumventing smooth regions. This study concentrates on the targeted objects within the image to uphold their integrity by inserting the adaptive watermark in the regions of interest. Extensive evaluation of various modalities proves the efficacy of the proposed method with an average Peak Signal Noise Ratio of 60.67dB and Structural Similarity Index of 0.9999, demonstrating marked improvements in imperceptibility over state-of-the-art techniques. The approach is efficient, with embedding and extraction times of 0.0094s and 0.0083s, respectively.


  • Effective persons identification using two- and three- dimensional finger knuckles

    by Bouchareb Faouzi, Djamel Samai, Maarouf Korichi, Abdallah Meraoumia, Abderrazak Lachouri

    Because of their high level of precision, biometric systems continue to attract the attention of several researchers. Different biometric traits have been investigated for use in security systems, such as fingerprints, faces, irises, palmprints, and knuckle prints. In most cases, bi-dimensional information is utilized. To achieve this aim, we have examined the performance of biometric identification systems based on a 3D-FKP database through five pre-trained networks such as AlexNet, VGG19, GoogleNet, ResNet50, and DenseNet201. The obtained experimental results illustrate the effectiveness of the suggested approach, with a high recognition rate and accuracy.


  • Combination of Closed-Set and Open-Set Biometric Identification

    by Atef Bentahar, Abdallah Meraoumia, Hakim Bendjenna, Abdelhakim Zeroual, Tarek Bentahar

    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.


  • The Impact of the Detector on the Performances of a Multi-Person Tracking System

    by Djalal Djarah, Abdallah Meraoumia, Mohamed Lakhdar Louazene

    Background: Pedestrian detection and tracking are an important area of study in realworld applications, such as mobile robots, human-computer interaction, video surveillance, pedestrian protection systems, etc. As a result, it has attracted the interest of the scientific community. Objective: Certainly, tracking people is critical for numerous utility areas which cover unusual situations detection, like vicinity evaluation, and sometimes change direction in human gait and partial occlusions. Researchers' primary focus is to develop a surveillance system that can work in a dynamic environment, but there are major issues and challenges involved in designing such systems. So, it has become a significant issue and challenge to design a tracking system that can be more suitable for such situations. To this end, this paper presents a comparative evaluation of the tracking-by-detection system along with the publicly available pedestrian benchmark databases. Method: Unlike recent works where person detection and tracking are usually treated separately, our work explores the joint use of the popular Simple Online and Real-time Tracking (SORT) method and the relevant visual detectors. Consequently, the choice of the detector is an important factor in the evaluation of the system's performance. Results: Experimental results demonstrate that the performance of the tracking-by-detection system is closely related to the optimal selection of the detector and should be required prior to a rigorous evaluation. Conclusion: The study demonstrates how sensitive the system performance as a whole is to the challenges of the dataset. Furthermore, the efficiency of the detector and the detector-tracker combination is also depending on the dataset.


  • Biometric Cryptosystems: Towards a Light and Precise Remote Authentication

    by Atef Bentahar, Abdallah Meraoumia, Hakim Bendjenna, Salim Chitroub, Abdelhakim Zeroual

    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.

  • Does the Learning Principle Help Us Improve Hand-Crafted Finger-Knuckle-Print Features?

    by Mohamed Yassine Haouam, Abdallah Meraoumia, Issam Bendib, Lakhdar Laimeche

    One of the most critical steps in pattern recognition systems is to extract the most distinctive features of the image. Therefore, the accuracy of these systems is strongly related to the efficiency of this step to represent the image. In general, hand-craft image features are obtained using feature extraction methods that often have no prior knowledge about the image type, which may result in poor features. In this paper, a hand-craft image feature learning method, based on Local Binary Pattern (LBP), for Finger-Knuckle-Print representation and recognition is applied. Thus, in the learning phase, each training finger image is first divided into several non-overlapping regions, and the feature filter and the codebook of each region are individually learned. For the enrolment phase, the obtained learned filter and codebook are applied to each image to extract the histogram feature of each region. Then, the different histograms are concatenated in a single feature vector to represent the finger features. Finally, an SVM classifier is used for the identification phase. The experimental results clearly show that the learning principle offers a good gain in the system accuracy, which can provide an excellent identification rate and thus improve security.


  • Enhancing Security and Privacy in Enterprises Network by Using Biometrics Technologies

    by Abdallah Meraoumia, Hakim Bendjenna, Yahia Dris, Mohamed Amroune

  • Can a chaos system provide secure communication over insecure networks?—Online automatic teller machine services as a case study

    by Othaila Chergui, Hakim Bendjenna, Abdallah Meraoumia, Srikanta Patnaik

    Nowadays, with the proliferation of data exchange across the Internet and the storage of sensitive data on open networks, intensive works are done to secure data. Recently, researchers made more considerable effort to utilize biometric features instead of a memorable password to authenticate the user identity. Based on the theories of chaos map, which are known to possess desirable properties of pseudorandomness, high sensitivity to initial conditions, and very large key space, we propose a biometric cryptosystem for online users’ authentications. The biggest advantage of our proposal is the secure nature of the key. In fact, our system is designed first so that the key never needs to be transmitted or revealed but it will be derived from biometric template and second even if we introduce the same biometric template twice, our system generates different key values. In order to assess the effectiveness of our approach, a biometric-based online automatic teller machine system is proposed and evaluated. Experimental results and statistical analysis, using palmprint as well as palm-vein databases of 200 users, are presented. The obtained results show that the proposed scheme is more secure, fast, and points at increased authentication accuracy. Therefore, it can be implemented in real-time applications, which will undoubtedly help to promote more widespread use of biometric cryptosystems based on chaos theory.