Annotating Images with Suggestions - User Study of a Tagging System

Annotating Images with Suggestions - User Study of a Tagging System
复制标题

用建议注释图像 - 标签系统的用户研究

DOI:
10.1007/978-3-642-33140-4_14
复制
发表时间:
2012
期刊:
--
影响因子:
--
通讯作者:
P. Smrz
P. Smrz
中科院分区:
--
文献类型:
--
作者:
Michal Hradiš;Martin Kolář;Ales Láník;J. Král;P. Zemčík;P. Smrz

文献摘要

被引文献

相似文献

本文探讨了图像智能标注的概念。它引入了一个基于web的图像注释用户界面,以及一种使用受限玻尔兹曼机器对标签依赖性建模的新方法,该方法能够根据先前分配的标签为图像建议可能的标签。根据我们的用户研究,我们的标签建议方法提高了用户体验和标注速度。我们的结果表明,与当前的类-领域智能方法相比,使用本文提出的方法可以更有效地注释带有语义标签的大型数据集(例如在TRECVID语义索引中),并产生更高质量的数据。
This paper explores the concept of image-wise tagging. It introduces a web-based user interface for image annotation, and a novel method for modeling dependencies of tags using Restricted Boltzmann Machines which is able to suggest probable tags for an image based on previously assigned tags. According to our user study, our tag suggestion methods improve both user experience and annotation speed. Our results demonstrate that large datasets with semantic labels (such as in TRECVID Semantic Indexing) can be annotated much more efficiently with the proposed approach than with current class-domain-wise methods, and produce higher quality data.