Avaliação do instrumento SAM para a etiquetagem colaborativa em ambiente web de imagens segundo critérios afetivos

• Wellton C. Costa UTFPR
• Álvaro R. Cantieri UTFPR
• Gustavo B. Borba UTFPR
• Humberto R. Gamba UTFPR

Abstract

In a visual information retrieval process that considers the images semantics, several levels of query can emerge, from simple statements as "find pictures with a boat", to more abstract ones, such as "find pictures depicting happy atmospheres". Usually, the abstract level refers to the affective or emotional content of the images and is considered a relevant dimension in which users specify their queries. Clearly, due to its inherent complexity, affect is difficult to model and consequently quite difficult to be handled by a retrieval system. In this work, we present a preliminary evaluation of the Self Assessment Manikin (SAM) method for the affective description of images, in a collaborative tagging environment. Images from the International Affective Picture System (IAPS) dataset were used in the study. The results show that the affective dimensions valence and arousal and the SAM method can be effciently used for tagging and further retrieval of images.

Keywords: Affective tagging, image retrieval, valence/arousal, SAM, IAPS