Automatic Tagging Suggestion for Database Enrichment

Authors Emanuele Cuono Amoruso, Sietske Tacoma, Huib Aldewereld
Published in Informal Proceedings of the Joint International Scientific Conferences on AI and Machine Learning (BNAIC/BeNeLearn 2023).
Publication date 2023
Research groups Artificial Intelligence
Type Article

Summary

The huge number of images shared on the Web makes effective cata loguing methods for efficient storage and retrieval procedures specifically tai lored on the end-user needs a very demanding and crucial issue. In this paper, we investigate the applicability of Automatic Image Annotation (AIA) for im age tagging with a focus on the needs of database expansion for a news broad casting company. First, we determine the feasibility of using AIA in such a con text 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 ad dressing the proposed approach as valuable to tackle the problem of image tag ging in the framework of a broadcasting company, whilst not yet optimal for in tegration in the business process.

On this publication contributed

Language English
Published in Informal Proceedings of the Joint International Scientific Conferences on AI and Machine Learning (BNAIC/BeNeLearn 2023).
Key words automatic image tagging, image database, news broadcasting

Artificial Intelligence