KHEIRA FAIROUZ Bedjekina
بجقينة خيرة فيروز
kheira-fairouz.bedjekina@univ-msila.dz
0775141469
- Departement of ELECTRONICS
- Faculty of Technology
- Grade PHd
About Me
Science et Technologies
Location
Djelfa, Djelfa
Djelfa, ALGERIA
Code RFIDE- 1996-11-28 00:00:00
-
KHEIRA FAIROUZ Bedjekina birthday
- 2025-11-25
-
2025-11-25
A Hybrid ResNet50-PCA-SVM Model for Accurate Palmprint Recognition
Biometric authentication has demonstrated effectiveness in accurately verifying an individual’s identity. Specifically, palmprint-based biometric systems have gained growing interest in recent years because of their high security, feasibility, and user acceptance. Conventional palmprint recognition approaches involve extracting palmprint features prior to classification, which can influence the recognition performance. In this study, we propose a hybrid model combining deep learning and traditional machine learning techniques for palmprint identification. Features are first extracted using a pre-trained ResNet50 model, then reduced via Principal Component Analysis (PCA), and finally classified using a Support Vector Machine (SVM) with a linear kernel. The experiments are conducted on publicly available contactless datasets, namely Tongji and BMPD, under different data split ratios. Performance is evaluated using accuracy, precision, recall, F1-score, and ROC-AUC analysis. The experimental results show that the proposed approach achieves an accuracy exceeding 99.3% across all tests, with an AUC of 1.00, demonstrating the effectiveness of combining CNN-based feature extraction with classical machine learning techniques for palmprint recognition.
Citation
KHEIRA FAIROUZ Bedjekina , BILAL Attallah , BRIK Youcef , FAYEK Maarfi , ,(2025-11-25), A Hybrid ResNet50-PCA-SVM Model for Accurate Palmprint Recognition,The 2nd International Workshop on Machine Learning and Deep Learning (WMLDL25),University of Mohamed Boudiaf of M'sila
- 2025-06-11
-
2025-06-11
Palmprint recognition systems using transfer learning techniques: A comparative study
Biometrics has emerged as a pervasive technology for secure and non-invasive identity verification. Palmprint recognition, in particular, offers a rich set of creases and texture features that enhance robustness against spoofing. However, despite advances in deep learning, it remains unclear whether off-the-shelf transfer learning yields superior performance on palmprint datasets. In this work, we conduct a comparative study on the Birjand University Mobile Palmprint Database (BMPD) by applying transfer learning with pre-trained convolutional neural networks (VGG16, ResNeXt50, MobileNetV2, and DenseNet121), optimizing hyperparameters via grid search, and evaluating using accuracy, precision, recall, and F1 score. Our experiments show that DenseNet121 with the Adam optimizer achieved the highest accuracy of 99.38% compared to the other models used. However, with the RMSprop optimizer, MobileNetV2 achieved the best accuracy, also with a value of 99.38%. Our study demonstrates that transfer learning techniques can be a good choice for palmprint recognition.
Citation
KHEIRA FAIROUZ Bedjekina , BILAL Attallah , BRIK Youcef , Cheyma nadir , ,(2025-06-11), Palmprint recognition systems using transfer learning techniques: A comparative study,Third national Conference on Materials Sciences And Engineering, (MSE’25),University of Hassiba Benbouali of Chlef (online presentation)