Autors: Hristov, P. A., Boumbarov, O. L., Vachev, K. E.
Title: Personal Identification Based Automatic Face Annotation in Multi-View Systems
Keywords: incremental learning; active learning; automatic face identi

Abstract: We propose a method for automatic face annotation in a closed multi-view environment. In such an environment faces are automatically detected and images are collected from several sources. Then, for the purpose of realtime labelling, a model is incrementally trained with every new person who enters the environment. The incremental learning model is validated on the Pandora dataset, which is split into different classes for each incremental step. Active learning is used to determine the type of images needed for training based on a predefined budget.

References

    Issue

    ET 2022, pp. 1-6, 2022, Bulgaria, IEEE, DOI 10.1109/ET55967.2022.9920284

    Copyright IEEE

    Full text of the publication

    Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus