Date of Publication :30th May 2023

Abstract: This paper compares different feature extraction methods with different classification techniques of face recognition technology. The author starts by discussing the various steps involved in a typical face recognition system, including data visualization, feature extraction, training, and testing the model. After visualizing the dataset, the author then delves into the various feature extraction methods used in face recognition, including Principal Component Analysis (PCA), Independent Component Analysis (ICA), Locally Linear Embedding (LLE), Local Binary Pattern(LBP), and Simple Autoencoder. The author compares the performance of the above feature extraction methods by training the models using Support Vector Clustering(SVC), and Linear Discriminant Analysis(LDA) algorithms. The results of the experiments help in comparing various feature extraction methods and finding the best feature extraction method for an efficient face recognition system. The authors conclude by discussing the potential applications of face recognition technology, including security systems, biometrics, and human-computer interaction. They highlight the growing importance of face recognition in various domains, including law enforcement, healthcare, and entertainment, and emphasize the need for further research and development in this field. The paper provides valuable insights into the current state-of-the-art in face recognition technology and will be of interest to researchers, engineers, and practitioners working in the field of computer vision and pattern recognition

Reference :