Computerized recognition of biological objects using the Hotelling transform

The authors present contour based techniques, for automatic object recognition, that avoid the difficulties that arise as a consequence of translation, rotation and scaling. Their techniques do not require the use of any representation of shape. The first technique uses the scale-space filtered coordinate functions of the contours of the objects to be recognized as well as what the authors define as the “largest diameter” of the contour. The second technique uses the Hotelling transform of the vector representations of the points of contours. The authors describe and use to advantage some interesting properties this transform that make it an important tool for image processing