Neural Network for Modeling Esthetic Selection

Gedeon, Tamás D.

doi:10.1007/978-3-540-69162-4_69

Cited by 5 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most studies taking this approach have targeted the construction of an automatic aesthetic evaluation system or an image classification system. Studies by Matsuura and Matsui, Ogawa et al ., Gedeon, Datta et al ., and Desnoyer and Wettergreen exemplify this approach.…”

Section: Research Backgroundmentioning

confidence: 99%

“…Another study on personal aesthetic preference to color images is that of Gedeon. By constructing three candidate neural network models that differed slightly in architectural complexity and learning procedure, the study tried to extract the aesthetic idiosyncrasy of a certain subject (Subject T) to pictures of Piet Mondrian's style.…”

Section: Research Backgroundmentioning

confidence: 99%

“…(10), as mentioned previously, x is the input value from the node Stability, y is the input value from the node Heaviness, and z is the input value from the node Presence. The indirect effect of the node Stability on the output node Pleasure is depicted by the function FIE S,PL : where G x; y; z ð Þ5exp 2:6312 5:180 exp 0:059z20:455y20:006x10:032 ð Þ 11 (11) The function value of FIE S,P is always greater than zero, which means that regardless of the values taken by x, y, and z, the node Stability consistently possesses a stimulatory indirect effect on the output node Pleasure. where G x; y; z ð Þ5exp 2:6312 5:180 exp 0:059z20:455y20:006x10:032 ð Þ 11…”

Section: Microstructure Analysis Of Bpnnmentioning

confidence: 99%

See 2 more Smart Citations

A computational model simulating the mental function of multicolor aesthetic evaluation

Fang

Muramatsu

Matsui

2016

Color Research & Application

View full text Add to dashboard Cite

In this research, a computational model that simulates the mental function of multicolor aesthetic evaluation through backpropagation neural networks was constructed. Helmut Leder's psychological model served as the theoretical framework. We determined the macro‐architecture of the computational model through two psychological experiments using the semantic differential (SD) method. The aesthetic score of a multicolor stimulus is defined as the inverse of its factor score on the factor “Pleasure” extracted in the first experiment, and each of the three factors extracted in the second experiment—i.e., “Stability,” “Heaviness,” and “Presence”—is regarded as a simple perceptual feature. The genetic algorithm was then employed to optimize the hidden layer node number, the learning rate, and the momentum constant of each neural network. In two simulation tests, this computational model exhibited some predictive power, implying that the model can be regarded as a relatively successful approximation of the psychological mechanism of multicolor aesthetic evaluation. In addition, the results of the second simulation also show that the perceptual feature “Heaviness” possesses the principal impact on the aesthetic evaluation of multicolor objects, whereas the other two perceptual features “Stability” and “Presence” have a minor influence. The heavier and/or more stable a multicolor object is perceived to be, the less aesthetically pleasing it is. Conversely, the stronger the sense of matter presence a multicolor object elicits, the more aesthetically appealing it is. © 2016 Wiley Periodicals, Inc. Col Res Appl, 42, 216–235, 2017

show abstract

Section: Research Backgroundmentioning

confidence: 99%

Section: Research Backgroundmentioning

confidence: 99%

Section: Microstructure Analysis Of Bpnnmentioning

confidence: 99%

See 1 more Smart Citation