In this paper we undertake a systematic investigation of affine invariant o
bject detection and image denoising. Edge detection is first presented from
the point of view of the affine invariant scale-space obtained by curvatur
e based motion of the image level-sets. In this case, affine invariant maps
are derived as a weighted difference of images at different scales. We the
n introduce the affine gradient as an affine invariant differential functio
n of lowest possible order with qualitative behavior similar to the Euclide
an gradient magnitude. These edge detectors are the basis for the extension
of the affine invariant scale-space to a complete affine flow for image de
noising and simplification, and to define affine invariant active contours
for object detection and edge integration. The active contours are obtained
as a gradient flow in a conformally Euclidean space defined by the image o
n which the object is to be detected. That is, we show that objects can be
segmented in an affine invariant manner by computing a path of minimal weig
hted affine distance, the weight being given by functions of the affine edg
e detectors. The gradient path is computed via an algorithm which allows to
simultaneously detect any number of objects independently of the initial c
urve topology. Based on the same theory of affine invariant gradient flows
we show that the affine geometric heat flow is minimizing, in an affine inv
ariant form, the area enclosed by the curve.