id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_bphzkrtkbrcmjiaeqq2byxsoom	Yael Eisenthal	Facial Attractiveness: Beauty and the Machine	2006	47	.pdf	application/pdf	8600	689	59	indicates that a machine producing human-like attractiveness rating could be rating of faces of different ethnicities (Cunningham, Roberts, Wu, Barbee & Druen, 1995; Jones, 1996; Perrett, May & Yoshikawa, 1994; Perrett, Lee, PentonVoak, Rowland, Yoshikawa, Burt, Henzi, Castles & Akamatsu, 1998). differed from the average female composite resulted in a more attractive face learning facial attractiveness, presenting prediction results and analyses. proportions of facial features such as distance between eyes, width of lips, size of representation of a face will be referred to as its "pixel image". the facial images and their respective human ratings. representation, the features found most correlated with the attractiveness ratings discerning "attractive" faces (the class comprised of highest 25% rated images) Figure 5: Prediction results obtained with pixel images (left) and with feature-based facial images and their respective average human ratings. feature-based representation produced better results than the pixel images, it is, attractive faces are not average Psychological Science, 2, 123-125.	./cache/work_bphzkrtkbrcmjiaeqq2byxsoom.pdf	./txt/work_bphzkrtkbrcmjiaeqq2byxsoom.txt