The problem of signal extraction from received data contaminated with stron
g chaotic interference has been investigated and a novel approach to this p
roblem is proposed based on the geometry of chaotic interference. According
to this approach, chaotic attractor is first reconstructed from the receiv
ed data, then in the way of projecting chaotic interference and harmonic si
gnals into the local tangent space and its transverse space of the manifold
in which the attractor lies, the two signals are successfully separated. E
xcellent results were achieved from the computer simulation experiments, wh
ich verify the effectiveness of the approach.