Quantcast
Last updated on April 24, 2014 at 12:23 EDT
Gender Recognition of Human Faces Image 2
1746 of 3476

Gender Recognition of Human Faces (Image 2)

July 12, 2010
Classification images for gender categorization and their analysis. Results are separately presented for L*, a* and b* from top to bottom (that is, the luminance, red/green, and blue/yellow color channels). Each row displays in order, classification images for the three observers, significant clusters averaged across the three observers superimposed on a grayscale version of the base image, a map of objective color differences and its analysis. Lighter areas in classification images mark regions brighter, redder or more yellow in males while darker areas indicate corresponding regions in females. Cyan and magenta mark significant clusters in the same directions for males and females, respectively. [See related image Here.] More about this Image Michael J. Tarr, professor of cognitive and linguistic sciences at Brown University, has discovered a difference in skin tone associated with gender. Tarr and graduate student Adrian Nestor have discovered this color difference in an analysis of dozens of faces. They determined that men tend to have more reddish skin and greenish skin is more common for women. The finding has important implications in cognitive science research, such as the study of face perception. But the information also has a number of potential industry or consumer applications in areas such as facial recognition technology, advertising, and studies of how and why women apply makeup. Tarr said the idea that color may help us to identify objects better has been controversial. But, he said, his and related findings show that color can nonetheless provide useful information. To conduct the study, Tarr's lab analyzed about 200 images of Caucasian male and female faces (100 of each gender) compiled in a data bank at the Max Planck Institute in Tuebingen, Germany, photographed using a 3-D scanner under the same lighting conditions and with no makeup. He then used a MatLab program to analyze the amount of red and green pigment in the faces. Tar found that men proved to have more red in their faces and women have more green, contrary to prior assumptions. "If it is on the more red end of the spectrum (the face) had a higher probability of being male. Conversely, if it is on the green end of the spectrum (the face) had a higher probability of being female," Tarr said. Tarr has uploaded the facial images in a database called Face-Place, that includes multiple images of over 200 individuals, including many different races with consistent lighting, multiple views, real emotions and disguises. You can view the database Here. [This research was supported by National Science Foundation grants BCS 03-39122 and SBE 05-42013.] (Date of Image: 2008)