| Abstrakt: |
This paper presents a comprehensive survey of digital image face detection techniques within the evolving landscape of technology and Human-Computer Interaction (HCI). With a focus on both feature-based and image-based approaches, the review encompasses innovative methodologies proposed by researchers, such as the integration of Convolutional Neural Networks (CNNs) with tracking techniques and novel approaches like ACF-GSVM. The challenges inherent in face detection, including complex backgrounds, unconventional facial expressions, and varying environmental conditions, are thoroughly examined. The applications of face detection systems across diverse domains, ranging from biometric attendance to marketing strategies, highlight its versatile utility. The survey meticulously explores feature-based techniques, including Active Shape Model (ASM) and Point Distribution Model (PDM), as well as image-based methods like neural networks, Support Vector Machines (SVM), and Convolutional Neural Networks (CNNs). The paper also categorizes and discusses relevant face detection datasets, providing essential insights into testing environments. In conclusion, the paper not only contributes a detailed analysis of existing methodologies but also proposes future research directions, advocating for the integration of multiple networks and exploration of diverse optimizers for enhanced face detection performance. [ABSTRACT FROM AUTHOR] |
