In applied mathematics, a steerable filter [1] is an orientation-selective convolution kernel used for image enhancement and feature extraction that can be expressed via a linear combination of a small set of rotated versions of itself.
As an example, the oriented first derivative of a 2D Gaussian is a steerable filter.
The oriented first order derivative can be obtained by taking the dot product of a unit vector oriented in a specific direction with the gradient.
The basis filters are the partial derivatives of a 2D Gaussian with respect to
Applications of steerable filters include edge detection, oriented texture analysis and shape from shading.