Classifying postures of freely moving rodents with the help of Fourier descriptors and a neural network

A computerized method for classifying the postures of freely moving rodents is presented. The behavior of the rats was recorded on videotape by means of a camera hanging perpendicular to an open field. An automatic tracking s ystem (10 images/sec) was used to transform the video images of postures in to a binary image, thereby providing silhouettes in a computer format. The contours of these silhouettes were used for determining their characteristi c features with the help of a Fourier transformation. The resulting feature s were classified with the help of a Kohonen network composed of 32 neurons . The four best winning neurons, rather than the usual one, were used for t he classification. The resolution (11,090 distinct classes of postures), re liability (96.9%), and validity of this method mere determined. With the us e of the same approach, the effectiveness of this method for classifying be haviors was illustrated by analyzing grooming (247 grooming images vs. 4,95 0 nongrooming images). We found 15.4% false positives and 2.5% false negati ves.