Jianli Liu, Edwin Lughofer, Xianyi Zeng,
"Aesthetic Perception of Visual Textures: A Holistic Exploration using Texture Analysis, Psychological Experiment and Perception Modeling"
, in Frontiers in Computational Neuroscience, Vol. 9, Nummer 134, Seite(n) 1-14, 2015, ISSN: 1662-5188
Original Titel:
Aesthetic Perception of Visual Textures: A Holistic Exploration using Texture Analysis, Psychological Experiment and Perception Modeling
Sprache des Titels:
Englisch
Original Kurzfassung:
Aesthetics, in the world of art and photography, refers to the principles of the nature and appreciation of beauty. Beauty appreciation and judgement is a highly subjective task. To explore aesthetic appreciation could be computed and modeled, we try to use linear model to bridge the gap between low-level statistical features and aesthetic emotions of visual textures. Firstly, we use four different algorithms to calculate the low-level texture features including color features, statistical moments of gray-level co-occurrence matrix, Tamura texture features, and wavelet energy signatures in frequency domain, to fully represent the characteristics of visual textures. Then, each visual texture is represented in a high-dimensional space by 106 features after feature extraction stage. Secondly, stochastic neighbor embedding (SNE) is used to reduce the information redundancy of the feature set and the complexity of the prediction model before model building. Thirdly, the semantic differential rating experiment is conducted to collect the aesthetic perceptions of selected texture stimuli from participants, and then the aesthetic properties are assigned to a hierarchical feed-forward model based on the neural mechanisms of aesthetic appreciation. Finally, model building of beauty appreciation of visual textures using multiple linear regression methods are detailed. Experimental results indicate that the hierarchical feed-forward layer model of aesthetic texture perception proposed in our research can successfully bridge the gap between low-level statistical features and aesthetic emotions of visual textures.