Please use this identifier to cite or link to this item:

Title: Identifying user profile using facebook photos
Authors: Liao, Wen-Hung;Chang, Ting-Ya;Wu, Yi-Chieh
Contributors: 資訊科學系
Keywords: Behavioral research;Classification (of information);Face recognition;Image classification;Information management;Social networking (online);Computer vision techniques;Facebook;Hier-archical clustering;Image tag;Outdoor scenes;Scene understanding;User classification;User profile;Image analysis
Date: 2017-01
Issue Date: 2017-08-03 14:13:27 (UTC+8)
Abstract: Apart from text messages, photo posting is a popular function of Facebook. The uploaded photos are of various natures, including selfie, outdoor scenes, food, etc. In this paper, we employ state-ofthe-art computer vision techniques to analyze image content and establish the relationship between user profile and the type of photos posted. We collected photos from 32 Facebook users. We then applied techniques such as face detection, scene understanding and saliency map identification to gather information for automatic image tagging and classification. Grouping of users can be achieved either by tag statistics or photo classes. Characteristics of each group can be further investigated based on the results of hierarchical clustering. We wish to identify profiles of different users and respond to questions such as the type of photos most frequently posted, gender differentiation in photo posting behavior and user classification according to image content, which will promote our understanding of photo uploading activities on Facebook. © 2017 ACM.
Relation: Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017,
11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017; Beppu; Japan; 5 January 2017 到 7 January 2017; 代碼 126221
Data Type: conference
DOI 連結:
Appears in Collections:[資訊科學系] 會議論文

Files in This Item:

File Description SizeFormat
a41-liao.pdf892KbAdobe PDF286View/Open

All items in 學術集成 are protected by copyright, with all rights reserved.

社群 sharing