Reference:

He Zhang, Eimontas Augilius, Timo Honkela, Jorma Laaksonen, Hannes Gamper, and Henok Alene. Analyzing emotional semantics of abstract art using low-level image features. In Joao Gama, Elizabeth Bradley, and Jaakko Hollmen, editors, Advances in Intelligent Data Analysis X, volume 7014 of Lecture Notes in Computer Science, pages 413–423, Berlin/Heidelberg, 2011. Springer.

Abstract:

In this work, we study people’s emotions evoked by viewing abstract art images based on traditional low-level image features within a binary classification framework. Abstract art is used here instead of artistic or photographic images because those contain contextual information that influences the emotional assessment in a highly individual manner. Whether an image of a cat or a mountain elicits a negative or positive response is subjective. After discussing challenges concerning image emotional semantics research, we empirically demonstrate that the emotions triggered by viewing abstract art images can be predicted with reasonable accuracy by machine using a variety of low-level image descriptors such as color, shape, and texture. The abstract art dataset that we created for this work has been made downloadable to the public.

Suggested BibTeX entry:

@inproceedings{Zhang11,
    address = {Berlin/Heidelberg},
    author = {Zhang, He and Augilius, Eimontas and Honkela, Timo and Laaksonen, Jorma and Gamper, Hannes and Alene, Henok},
    booktitle = {Advances in Intelligent Data Analysis X},
    editor = {Gama, Joao and Bradley, Elizabeth and Hollmen, Jaakko},
    language = {eng},
    pages = {413-423},
    publisher = {Springer},
    series = {Lecture Notes in Computer Science},
    title = {Analyzing Emotional Semantics of Abstract Art Using Low-Level Image Features},
    volume = {7014},
    year = {2011},
}