Metadata Collection for Personal Multimedia Repositories Using GWAP

نویسنده

  • Balázs NAGY
چکیده

With the increasing number of personal albums and photos in them, users have more and more problems with their organization [4]. This is due to lack of descriptive data, however, their amount only depends on the abilities and will of the image owners. Tools for metadata creation are available – the main problem is with the user motivation: because tagging and annotating of photos is usually a boring activity and its execution takes extended time periods. Other methods for obtaining metadata to general images also exist (automated methods, crowd-based, games with a purpose [1]), but these are unable to deliver specific metadata needed for personal imagery. Our aim is to create a method to enrich personal photo albums with keywords and also named entities. To achieve this, we use tool that imports personal albums, allows creating annotations using a GWAP, extracts keywords and named entities from annotations and allows browsing in albums using obtained metadata. Earlier, we devised a game with a purpose called PexAce [2, 3] for harvesting textual annotations to general images. Earlier experiments showed that people playing with their own photos are more engaged to game and also interested in creating annotations. By merging our game with automatic approach of metadata acquisition from game-produced annotations, we found an appropriate solution for creating metadata for personal photo albums. The main contribution of this work is a framework for processing annotations written to personal photos. This framework is based on metadata extraction modules called extractors and is extensible from this perspective. Inputs of all extractors are following five entries: photo, album to which photo belongs, user who created the annotation, annotation, and timestamp. In addition to these information, extractors have access to all logs saved during games and use them to refine results of annotation processing. Extractors are divided to two groups depending on their output. While the first group includes extractors extracting

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Knowledge Discovery in Multimedia Repositories: the role of metadata

Data mining has recently emerged as an important issue of multimedia research. New trends are focused on knowledge discovery in large multimedia repositories, however, traditional data mining approaches do not seem to bear fruits. There is a need to use new techniques to mine knowledge from multimedia, link content top context and more importantly, to exploit them in real life applications. In ...

متن کامل

Metadata for Distributed Visual Database Access

With the advances in multimedia technology and the popularization of the Internet, it is now possible to access a large number of image or video repositories (visual databases) distributed throughout the world. To facilitate such access, a challenging problem is how the capability of each database can be adequately summarized to enable the query distributing server to perform an intelligent sel...

متن کامل

An Investigation into Automatically Captured Autobiographical Metadata, and the Support for Autobiographical Narrative Generation

FACULTY OF ENGINEERING, SCIENCE AND MATHEMATICS SCHOOL OF ELECTRONICS AND COMPUTER SCIENCE INTELLIGENCE, AGENTS, MULTIMEDIA GROUP A mini-thesis submitted for transfer from MPhil to PhD by Mischa M Tuffield Personal information and the act of publishing multimedia artifacts to the World Wide Web is becoming more and more observable. This report presents an infrastructure for the capturing and ex...

متن کامل

Collecting metadata from institutional repositories

The purpose of this article is to review metadata issues identified in recent research carried out in Scotland on services based on metadata aggregation via OAI-PMH, and to examine the role of collection-level description in managing ingest to harvested repositories, subsequent harvesting by secondary aggregators, and the contextualisation of institutional and aggregated repositories in the wid...

متن کامل

The design of puzzle selection strategies for GWAP systems

The Games With A Purpose (GWAP) genre is a type of Human Computation that outsources certain steps of the computational process to humans. By taking advantage of people’s desire to be entertained, GWAP attracts people to play voluntarily, and also produce useful metadata as a by-product. The games have shown promise in solving a variety of problems, which computer computation has been unable to...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2013