Translating Journalists' Requirements into Features for Image Search

Abstract

Abstract-This paper illustrates how taking advantage of user studies highlighting the user requirements can lead to the selection of suitable visual features in image search systems. The results of a study to identify pertinent visual features to enhance a text-based press photo search system used by journalists are presented. A requirement was that the visual features should be intuitively understandable by the journalists. This feature selection task is approached by first determining the journalists' photo searching requirements based on a published user study. These requirements are then mapped to suitable visual features. The emphasis was on identifying suitable and intuitive low-level features, as these can be rapidly implemented in the existing text-based image search system. Results demonstrating the use of the selected features are shown.

Affective image classification using features inspired by psychology and art theory

“…We introduce features based on the experimentally-determined relation between color saturation and brightness, and emotion dimensions [26], as well as features based on relations between color combinations and induced emotional effects from art theory [15]. We complement these features by a selection of features, some of which are shown to be of use in similar image retrieval [24] and classification tasks [7,32]. In this work, features representing the color, texture, composition and content were implemented.…”

Survey on visual sentiment analysis

“…In 2010 Machajdik and Hanbury [30] performed an intensive study on image emotion classification by properly combining the use of several low and high visual features. These features have been obtained by exploiting concepts from and art theory [12, 16], or exploited in image retrieval [78] and image classification [9, 17] tasks. They selected 17 visual features, categorised into four groups: Colour: mean saturation and brightness, 3D emotion representation by Valdez and Mehrabian [16], hue statistics, colourfulness measure according to [17], number of pixels of each of the 11 basic colours [79], Itten contrast [12], colour histogram designed by Wei‐ning et al [9].…”

The Waterfall Hierarchy on Weighted Graphs

“…It has been used not only on images but also on probability distribution functions used for the stochastic watershed of multipectral images [2] or on triangular meshes [9]. The domain of application is broad going from multimedia images [21] to SAR imagery [19].…”