Kashkool, Hawraa Jaafar MuradFarhan, Hameed MutlagNaseri, Raghda Awad ShabanKurnaz, Sefer2024-07-192024-07-192024Kashkool, H. J. M., Farhan, H. M., Naseri, R. A. S., Kurnaz, S. (2024). Enhancing facial recognition accuracy and efficiency through integrated CNN, PCA, and SVM techniques. Lecture Notes in Networks and Systems, 1035 LNNS, 57-70. 10.1007/978-3-031-62871-9_69783031628702https://hdl.handle.net/20.500.12939/4770Facial recognition, as a paradigmatic instance of biometric identification, has witnessed escalating utilization across diverse domains, encompassing security, surveillance, human-computer interaction, and personalized user experiences. The fundamental premise underlying this technology resides in its capacity to extract discriminative features from facial images and subsequently classify them accurately. However, the precision and efficiency of such systems remain subject to an array of intricate challenges, necessitating innovative solutions. The overarching aim of this thesis is to enhance the performance and efficacy of facial recognition systems through the seamless integration of Convolutional Neural Networks (CNNs) for feature extraction, Principal Component Analysis (PCA) for dimensionality reduction, and Support Vector Machines (SVMs) for classification. This holistic approach seeks to optimize the accuracy, efficiency, and robustness of facial recognition, thereby contributing to the advancement of computer vision and biometric identification technologies.eninfo:eu-repo/semantics/closedAccessArtificial intelligenceDimensionality reductionFace recognitionFeature extractionMachine learningConference Object1035 LNNS57702-s2.0-85197756684Q4WOS:001286524700006N/A