Evaluation of local and global descriptors for emotional impact recognition

• We studied an emotion extraction based on image low level features on a new natural image database and on IAPS.
• We organized subjective evaluations on the new database and the emotions are described through their nature and their power.
• We used Bag of words and VLAD for the compact representation of our features.
• Negative emotions are easy to recognize with our algorithm.

In order to model the concept of emotion and to extract the emotional impact from images, one may search suitable image processing features. However, in the literature, there is no consensus on the ones to consider since they are often linked to the application. Obviously, the perception of emotion is not only influenced by the content of the images, it is also modified by some personal experiences like cultural aspects and semantic associated to some colours or objects. In this paper, we choose low level features frequently used in CBIR especially those based on SIFT descriptors. To take into account the complex process of emotion perception, we also consider colour and texture features and one global scene descriptor: GIST. We supposed the chosen features could implicitly encode high-level information about emotions due to their accuracy in the different CBIR applications of the literature.We test our methodology on two databases: SENSE and IAPS.

Figure optionsDownload high-quality image (213 K)Download as PowerPoint slide