Using face detection in photographs and cluster analysis to support exploration of social relationships between historical personages in a biographical database
Background. The Taiwan Biographical Database (TBDB) assembles biographical information of historical personages in Taiwan. It is a digital-humanities-oriented system that supports relational database operations, fulltext search, social network analysis, and geographic information system functions...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/154748 |
| _version_ | 1811681314060894208 |
|---|---|
| author | Sie, Shun-Hong Ke, Hao-Ren Chang, Su-Bing |
| author2 | National Taiwan Normal University |
| author_facet | National Taiwan Normal University Sie, Shun-Hong Ke, Hao-Ren Chang, Su-Bing |
| author_sort | Sie, Shun-Hong |
| collection | NTU |
| description | Background. The Taiwan Biographical Database (TBDB) assembles biographical
information of historical personages in Taiwan. It is a digital-humanities-oriented
system that supports relational database operations, fulltext search, social network
analysis, and geographic information system functions.
Objectives.Through semi-automatic named entity recognition from the fulltext of
biographies, TBDB assists historians to construct networks of social relationships.
However, the fulltext of biographies may not describe all social relationships. Taking
advantage of the fact that historical photographs were usually taken on formal
occasions, historical photographs may be exploited to uncover additional relationships.
This paper describes and evaluates a face detection function in TBDB that utilizes the
OpenCV Library to detect faces of historical persons in old photographs. Furthermore,
it employs hierarchical agglomerative clustering to combine fragmentary social
networks.
Results. An experiment using 45 historical photographs found that the face detection
function achieved an average recall of 98% recall, but with low precision. To address
the low precision rate, a user interface has been implemented in TBDB to facilitate
review and deletion of false-positive faces in the photographs. Furthermore, cluster
analysis is used to integrate social relationships found in biographies, those detected
from historical photographs, and even relationships harvested from external sources, to
produce comprehensive social networks for historical research. |
| first_indexed | 2024-10-01T03:38:58Z |
| format | Journal Article |
| id | ntu-10356/154748 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:38:58Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1547482022-01-12T20:10:23Z Using face detection in photographs and cluster analysis to support exploration of social relationships between historical personages in a biographical database Sie, Shun-Hong Ke, Hao-Ren Chang, Su-Bing National Taiwan Normal University Library and information science Background. The Taiwan Biographical Database (TBDB) assembles biographical information of historical personages in Taiwan. It is a digital-humanities-oriented system that supports relational database operations, fulltext search, social network analysis, and geographic information system functions. Objectives.Through semi-automatic named entity recognition from the fulltext of biographies, TBDB assists historians to construct networks of social relationships. However, the fulltext of biographies may not describe all social relationships. Taking advantage of the fact that historical photographs were usually taken on formal occasions, historical photographs may be exploited to uncover additional relationships. This paper describes and evaluates a face detection function in TBDB that utilizes the OpenCV Library to detect faces of historical persons in old photographs. Furthermore, it employs hierarchical agglomerative clustering to combine fragmentary social networks. Results. An experiment using 45 historical photographs found that the face detection function achieved an average recall of 98% recall, but with low precision. To address the low precision rate, a user interface has been implemented in TBDB to facilitate review and deletion of false-positive faces in the photographs. Furthermore, cluster analysis is used to integrate social relationships found in biographies, those detected from historical photographs, and even relationships harvested from external sources, to produce comprehensive social networks for historical research. Published version This work is a partial result of a project funded by the Ministry of Science and Technology (MOST 107-2410-H-003-142 -MY2). 2022-01-06T05:07:52Z 2022-01-06T05:07:52Z 2021 Journal Article Sie, S., Ke, H. & Chang, S. (2021). Using face detection in photographs and cluster analysis to support exploration of social relationships between historical personages in a biographical database. Library and Information Science Research E-Journal, 31(1), 42-55. https://dx.doi.org/10.32655/LIBRES.2021.1.4 1058-6768 https://hdl.handle.net/10356/154748 10.32655/LIBRES.2021.1.4 1 31 42 55 en Library and Information Science Research E-Journal © 2021 Shun-Hong Sie, Hao-Ren Ke and Su-Bing Chang. All rights reserved. application/pdf |
| spellingShingle | Library and information science Sie, Shun-Hong Ke, Hao-Ren Chang, Su-Bing Using face detection in photographs and cluster analysis to support exploration of social relationships between historical personages in a biographical database |
| title | Using face detection in photographs and cluster analysis to support exploration of social relationships between historical personages in a biographical database |
| title_full | Using face detection in photographs and cluster analysis to support exploration of social relationships between historical personages in a biographical database |
| title_fullStr | Using face detection in photographs and cluster analysis to support exploration of social relationships between historical personages in a biographical database |
| title_full_unstemmed | Using face detection in photographs and cluster analysis to support exploration of social relationships between historical personages in a biographical database |
| title_short | Using face detection in photographs and cluster analysis to support exploration of social relationships between historical personages in a biographical database |
| title_sort | using face detection in photographs and cluster analysis to support exploration of social relationships between historical personages in a biographical database |
| topic | Library and information science |
| url | https://hdl.handle.net/10356/154748 |
| work_keys_str_mv | AT sieshunhong usingfacedetectioninphotographsandclusteranalysistosupportexplorationofsocialrelationshipsbetweenhistoricalpersonagesinabiographicaldatabase AT kehaoren usingfacedetectioninphotographsandclusteranalysistosupportexplorationofsocialrelationshipsbetweenhistoricalpersonagesinabiographicaldatabase AT changsubing usingfacedetectioninphotographsandclusteranalysistosupportexplorationofsocialrelationshipsbetweenhistoricalpersonagesinabiographicaldatabase |