Free boundary condition
From HandWiki
In image processing, the free boundary condition is the convention used when applying a convolution kernel to a digital image in which pixel locations that lie outside the image boundaries are interpreted as having a value of zero.[1] The question of what value to assign out-of-bounds pixels may arise, for instance, when applying a 3×3 kernel to the corner pixel in an image.
 | This article uses only URLs for external sources. (2021) (Learn how and when to remove this template message) |
 | This article does not cite any external source. HandWiki requires at least one external source. See citing external sources. (2021) (Learn how and when to remove this template message) |
 |  |
