Visual Access for Retrieving Emotional Content of Pictures

The traditional and still pervasive way of access to image information is through descriptive keyword searching. However, many studies in image indexing and retrieval have reached a consensus on the difficulties and limitations of text-based image description. This situation is more obvious when the description involves subjective interpretation of the content of images. One of the best examples that depend on relatively high degree of subjective interpretation is emotion. This research investigates the feasibility of using visual browsing, that is being used comparatively much less than keyword searching, for the retrieval of emotional content of pictures. The effectiveness of keyword access versus visual access were examined through experiments in which participants searched for pictures of specified emotions using different access modes: keywords only, visual browsing only, and the combination of both. Findings and results can guide design of image retrieval systems, especially the retrieval system of subjective and interpretive information.