To precisely re-identify a person is a daunting task due to various conditions such as pose variation, illumination variation, and uncontrolled environment. The methods addressed in related work were insufficient for correctly identifying the targeted person. There has been a lot of exploration in the domain of deep learning, convolutional neural network (CNN) and computer vision for extracting features. In this paper, FaceNet network is used to detect face and extract facial features and these features are used for re-identifying person. Accuracy of FaceNet is compared with Histogram of Oriented Gradients (HOG) method. Euclidean distance is used for checking similarity between faces.
CITATION STYLE
Hendre, A., & Charniya, N. N. (2020). Person re-identification from videos using facial features. In Lecture Notes on Data Engineering and Communications Technologies (Vol. 46, pp. 380–387). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-38040-3_43
Mendeley helps you to discover research relevant for your work.