Image analysis is applied to characterize fashion designs depicted by high school students. The sensory values of fashion designs are evaluated by ten high school teachers for the homemaking course. A digitized gray level image for a fashion design is captured by a color scanner. A one-dimensional power spectrum, P( f ), is derived from a two-dimensional power spectrum obtained from the frequency analysis of a gray level image. The co-occurrence entropy and fractal dimension are also determined as image information parameters. Since there is a good linear relation between log P( f ) and log f for all of the fashion designs used in this study, the slope of a line(α) is estimated for each of them. The α-value is the coefficient of the 1/f α fluctuation. The fashion designs are mainly divided into three groups by the α-value. Their sensory evaluation values are discussed in relation to the 1/ f α fluctuation and image information.