In order to realize edge detection adaptively and effectively

this paper presents an edge detection algorithm based on odd Gabor filter and Rayleigh distribution.To obtain the edge response

an improved odd Gabor filter based edge response obtaining method was proposed

which increases the computational efficiency and avoids the estimation of gradient direction.For the differential property of odd Gabor filter

the edge response based on odd Gabor filter was fitted by a Rayleigh distribution.To overcome the shortcomings of existing threshold selection approaches

a Rayleigh distribution based nonlinear adaptive threshold determining method was given.Both the synthetic and natural images were tested in our case.The experimental results show that the proposed edge detection method has good detection property and adaptability.