Abstract In this paper, quantitative spatial context estimation method is proposed which can affect human emotion by analyzing environmental image acquired from the frontal camera. In psychology and marketing fields, visual factors such as color and image complexity have been well-known for influencing human emotion. Based on these factors, a method for real-time extracting temporal complexity, spatial complexity, and specific color information is implemented. In detail, temporal and spatial complexities are extracted by subtracting adjacent image frames and edge detection method, respectively. Then, the color information is obtained by counting pixels in the specific color bands which inducing positive and negative human emotions.
[1]
Daniel Gooch,et al.
Communications of the ACM
,
2011,
XRDS.
[2]
Rafael C. González,et al.
Local Determination of a Moving Contrast Edge
,
1985,
IEEE Transactions on Pattern Analysis and Machine Intelligence.
[3]
Goran Milas,et al.
Psychology of Marketing
,
2007
.
[4]
Hervé Jégou,et al.
A Group Testing Framework for Similarity Search in High-dimensional Spaces
,
2014,
ACM Multimedia.
[5]
Nicu Sebe,et al.
Proceedings of the 21st ACM international conference on Multimedia
,
2013,
MM 2013.