Image Battle System: Collecting more trustable ground truth for Affect-based image indexing system

被引:0
|
作者
Akhmedjanov, Umid [1 ]
Ko, Eunjeong [1 ]
Kim, Eun Yi [1 ]
机构
[1] Konkuk Univ, Visual Informat Proc Lab, Seoul, South Korea
关键词
Image Battle System; Affect-based Image indexing; ImageRank; PageRank; Probabilistic Affective Model (PAM);
D O I
10.1016/j.sbspro.2013.10.275
中图分类号
C [社会科学总论];
学科分类号
03 ; 0303 ;
摘要
In recent years, the affect-based image indexing by visual features is going to be popular research area by increasing the importance of affective computing. So far many algorithms and systems have been developed to index images using affects and objects, then their performance is highly dependent on the training data with accurate labels. Most of the existing systems have generated the ground truth based on manually tagging by human, which is too time-consuming and costly subjective of image, Accordingly, a new mechanism to collect new trustable ground truth is presented, which is named by "Image Battle", to collect more trustable ground truth. The Image Battle system consists of three modules: image crawling, image voting and image ranking. First, for a text query, the images are first crawled then they are filtered to remove some noisy data. In the second stage, two images are randomly selected from the database and are evaluated by receiving votes from participants. After performing this process about several times over a period of two or three months, the system computes rank values for every images based on their number of wins and losses at the evaluation. These three procedures can be iterated whenever new data are added to the database, to update the ranks of images. To validity the effectiveness of the proposed system, the generated ground truth through image battle are used in some researches to train the affect-based image indexing system. When compared with the existing system, the proposed system can improve the accuracy. In addition, it is proven that the image battle system can provide more perspective and convenient interface to collect users' evaluations. (C) 2013 The Authors. Published by Elsevier Ltd.
引用
收藏
页码:571 / 579
页数:9
相关论文
共 50 条
  • [2] An Affect-Based Multimodal Video Recommendation System
    Kaklauskas, Arturas
    Gudauskas, Renaldas
    Kozlovas, Matas
    Peciure, Lina
    Lepkova, Natalija
    Cerkauskas, Justas
    Banaitis, Audrius
    [J]. STUDIES IN INFORMATICS AND CONTROL, 2016, 25 (01): : 5 - 14
  • [3] A miniature image collecting system for MAVs
    Xiao, X
    Xiong, SS
    Zhou, ZY
    Wei, Q
    [J]. ISTM/2005: 6TH INTERNATIONAL SYMPOSIUM ON TEST AND MEASUREMENT, VOLS 1-9, CONFERENCE PROCEEDINGS, 2005, : 6242 - 6244
  • [4] Ehipasiko: A content-based image indexing and retrieval system
    Teng, Shyh Wei
    Ting, Kai Ming
    [J]. Advances in Intelligent IT: Active Media Technology 2006, 2006, 138 : 436 - 437
  • [5] A text based indexing system for mammographic image retrieval and classification
    Farruggia, Alfonso
    Magro, Rosario
    Vitabile, Salvatore
    [J]. FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2014, 37 : 243 - 251
  • [6] RETIN: A Content-Based Image Indexing and Retrieval System
    J. Fournier
    M. Cord
    S. Philipp-Foliguet
    [J]. Pattern Analysis & Applications, 2001, 4 : 153 - 173
  • [7] An image indexing and searching system based both on keyword and content
    Zhang, Nan
    Song, Yonghua
    [J]. ADVANCED INTELLIGENT COMPUTING THEORIES AND APPLICATIONS, PROCEEDINGS: WITH ASPECTS OF THEORETICAL AND METHODOLOGICAL ISSUES, 2008, 5226 : 1032 - +
  • [8] RETIN: A content-based image indexing and retrieval system
    Fournier, J
    Cord, M
    Philipp-Foliguet, S
    [J]. PATTERN ANALYSIS AND APPLICATIONS, 2001, 4 (2-3) : 153 - 173
  • [9] System profiles in content-based image indexing and retrieval
    Guldogan, Esin
    Gabbouj, Moncef
    [J]. SIGNAL IMAGE AND VIDEO PROCESSING, 2010, 4 (04) : 463 - 480
  • [10] System profiles in content-based image indexing and retrieval
    Esin Guldogan
    Moncef Gabbouj
    [J]. Signal, Image and Video Processing, 2010, 4 : 463 - 480