Facial Photo Recognition Using Deep Learning in Archival Record Management System
- Authors
- Togtokh, Gantur; G.; Kim, Kyung-chang; K.C.; Lee; K.W.
- Issue Date
- 2020
- Publisher
- Springer
- Keywords
- Deep learning; Face recognition; Photo metadata; Record management system
- Citation
- Lecture Notes in Electrical Engineering, v.536 LNEE, pp.376 - 380
- Journal Title
- Lecture Notes in Electrical Engineering
- Volume
- 536 LNEE
- Start Page
- 376
- End Page
- 380
- URI
- https://scholarworks.bwise.kr/hongik/handle/2020.sw.hongik/12436
- DOI
- 10.1007/978-981-13-9341-9_64
- ISSN
- 1876-1100
- Abstract
- A lot of information is stored in the archival record management system (archive), including photos and pictures. It is important to intelligently organize photos in the archive. Current approaches use face recognition technology based on deep learning to manage photos. However, due to the rapid growth of the volume of photos in the archive, face recognition processes on large photoset take lots of processing time. In addition, low resolution photo with small faces in the archive is difficult to identify and recognize. In this paper, we propose a method to identify and retrieve facial photos from the archive. In our approach, photo metadata is used for searching photos in the archive, and resolution enhancement step based on DCSCN model is used to reconstruct photos of low resolution to high resolution. Experiment shows that the proposed approach can search and retrieve facial photo quickly from large photoset and is efficient for identifying small faces of low resolution photos. © 2020, Springer Nature Singapore Pte Ltd.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > Computer Engineering Major > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.