The huge number of images shared on the Web makes effective cataloguing methods for efficient storage and retrieval procedures specifically tailored on the end-user needs a very demanding and crucial issue. In this paper, we investigate the applicability of Automatic Image Annotation (AIA) for image tagging with a focus on the needs of database expansion for a news broadcasting company. First, we determine the feasibility of using AIA in such a context with the aim of minimizing an extensive retraining whenever a new tag needs to be incorporated in the tag set population. Then, an image annotation tool integrating a Convolutional Neural Network model (AlexNet) for feature extraction and a K-Nearest-Neighbours classifier for tag assignment to images is introduced and tested. The obtained performances are very promising addressing the proposed approach as valuable to tackle the problem of image tagging in the framework of a broadcasting company, whilst not yet optimal for integration in the business process.
DOCUMENT
This publication gives an account of the Public Annotation of Cultural Heritage research project (PACE) conducted at the Crossmedialab. The project was carried out between 1 January 2008 and 31 December 2009, and was funded by the Ministry of Education, Culture, and Science. Three members of the Dutch Association of Science Centres (Vereniging Science Centra) actively participated in the execution of the project: the Utrecht University Museum, the National Museum of Natural History (Naturalis), and Museon. In addition, two more knowledge institutes participated: Novay and the Utrecht University of Applied Sciences. BMC Consultancy and Manage¬ment also took part in the project. This broad consortium has enabled us to base the project on both knowledge and experience from a practical and scientific perspective. The purpose of the PACE project was to examine the ways in which social tagging could be deployed as a tool to enrich collections, improve their acces¬sibility and to increase visitor group involvement. The museums’ guiding question for the project was: ‘When is it useful to deploy social tagging as a tool for the benefit of museums and what kind of effect can be expected from such deployment?’ For the Crossmedialab the PACE project presented a unique opportunity to conduct concrete research into the highly interesting phenomenon of social tagging with parties and experts in the field.
DOCUMENT
In January 2008 the online photo-hosting site Flickr introduced a new section entitled The Commons. Its two key goals were to show the hidden treasures in the world’s public photography archives to the general public and to give Flickr community members the opportunity to contribute and describe these photos in order to enrich these collections. Surprisingly enough, little empirical research has been done on the actual usage of The Commons by the institutes and Flickr members. In our research we harvested a rich data sample over a 14-week period: 196,822 photos with user-generated content of 1.3 million tags, almost 130,000 comments and more than 22,000 notes. In total, 165,401 members from 188 different countries actively “did something” with the photos. This presentation will analyze this large data sample. In addition to the quantitative findings, we will discuss the qualitative findings regarding the content analysis of tags and comments.
DOCUMENT
