Computation of Intrinsic Perceptual Saliency in Visual Environments, and Applications. Koch, C. & Itti, L. Jul 2001. Patent pending. Filed July 23, 2001, following provisional applications No. 60/274,674 filed March 8, 2001 and 60/288,724 filed May 4, 2001.
abstract   bibtex   
Detection of image salience in a visual display of an image. The image is analyzed at multiple spatial scales and over multiple feature channels to determine the likely salience of different portions of the image. One application for the system is in an advertising context. The detection may be improved by second order statistics, e.g. mean and standard deviations of different image portions relative to other portions. Different edges may be considered as being extended edges by looking at the edges over multiple spatial scales. One set of feature channels can be optimized for use in moving images, and can detect motion or flicker. The images can be obtained over multiple spectral ranges and the user can be instructed about how to maximize the saliency. This can be applied to automatically evaluate and optimize sales or advertisement displays.
@patent{ Koch_Itti01,
  author = { C. Koch and L. Itti },
  title = { Computation of Intrinsic Perceptual Saliency in Visual Environments,
                        and Applications },
  month = { Jul },
  year = {2001},
  abstract = { Detection of image salience in a visual display of an image.
                        The image is analyzed at multiple spatial scales and over
                        multiple
                        feature channels to determine the likely salience of different
                        portions of the image. One application for the system is
                        in an
                        advertising context. The detection may be improved by second
                        order
                        statistics, e.g. mean and standard deviations of different
                        image
                        portions relative to other portions. Different edges may
                        be
                        considered as being extended edges by looking at the edges
                        over
                        multiple spatial scales. One set of feature channels can
                        be optimized
                        for use in moving images, and can detect motion or flicker.
                        The
                        images can be obtained over multiple spectral ranges and
                        the user can
                        be instructed about how to maximize the saliency. This can
                        be applied
                        to automatically evaluate and optimize sales or advertisement
                        displays. },
  note = { Patent pending. Filed July 23, 2001, following provisional
                        applications No. 60/274,674 filed March 8, 2001 and 60/288,724
                        filed May 4, 2001. },
  organization = { California Institute of Technology, Pasadena, California },
  type = { bu;mod;cv }
}

Downloads: 0