Abstract :
The research aims to develop an automatic sensational clothes search system. It is an application of visual-based knowledge extraction and cognitive science, helping women choose a garment which matches the desired visual impression using all what have already been in their closets. All garment essentials and fashion knowledge are from visual images. Users simply submit the desired image keywords, such as elegant, sporty, casual, and occasion type, such as formal meeting, outdoor dating, to the system. Then sensational cognition model is activated to search the desired clothes within the personal garment database. Category learning with supervised neural networking is applied to cluster garments into different impression groups. The input stimuli of the neural network are three sensations, warmness, loudness, and softness, which are transformed from the physical garment essentials like major color tone, print type, and fabric material. This paper focuses on the transformation between physical essentials and cognitive image.
Keywords :
knowledge acquisition; neural nets; social sciences computing; automatic sensation-based clothes search system; category learning; cognitive image; cognitive science; fashion knowledge; neural network; personal garment database; sensational cognition model; visual images; visual impression; visual-based knowledge extraction; Artificial neural networks; Clothing; Cognition; Cognitive science; Computer applications; Digital images; Image databases; Neural networks; Psychology; Visual databases; clothing match; intelligence information processing; knowledge extraction and discovery; neural networks;
