Steerable filter

Uses your system voice; voice and rate in settings.

Snapshot

≈ 3 min read

Names in other languages

No names in other languages are held for this entry yet.

Article bodies are English and are not machine-translated. A name in another language is not a translation of the article.

In image processing, a steerable filter is an orientation-selective filter that can be computationally rotated to any direction. Rather than designing a new filter for each orientation, a steerable filter is synthesized from a linear combination of a small, fixed set of "basis filters". This approach is efficient and is widely used for tasks that involve directionality, such as edge detection, texture analysis, and shape-from-shading. The principle of steerability has been generalized in deep learning to create equivariant neural networks, which can recognize features in data regardless of their orientation or position.

In image processing, a steerable filter is an orientation-selective filter that can be computationally rotated to any direction. Rather than designing a new filter for each orientation, a steerable filter is synthesized from a linear combination of a small, fixed set of "basis filters". This approach is efficient and is widely used for tasks that involve directionality, such as edge detection, texture analysis, and shape-from-shading.

Evidence and sources

The principle of steerability has been generalized in deep learning to create equivariant neural networks, which can recognize features in data regardless of their orientation or position. G_\theta = \cos(\theta)G_x + \sin(\theta)G_y Here, the basis filters G_x and G_y are weighted by \cos(\theta) and \sin(\theta) to "steer" the filter's sensitivity to the desired orientation. This is equivalent to taking the dot product of the direction vector (\cos\theta, \sin\theta) with the filter's gradient, (G_x, G_y) .

The concept of steerability is foundational to equivariant neural networks, a class of models in deep learning designed to understand symmetries in data. A network is considered equivariant to a transformation (like a rotation) if transforming the input and then passing it through the network produces the same result as passing the input through the network first and then transforming the output. Formally, for a transformation T and a network f , this property is defined as f(T(\text{input})) = T(f(\text{input})) .

This built-in understanding of geometry makes models more data-efficient. For example, a network equivariant to rotation does not need to be shown an object in multiple orientations to learn to recognize it; it inherently understands that a rotated object is still the same object. This leads to better generalization and performance, particularly in scientific applications.

Text derived from https://en.wikipedia.org/w/index.php?oldid=1368852464 under CC BY-SA 4.0; modifications have been made.

Sources cited in this revision

5 named source(s) extracted from the cited revision. A source with no author is shown by its publication; nothing is invented.