Bilateral

The Bilateral (also known as conditional mean) filter is very similar to the Mean filter but better perserves edges while averaging/blurring other parts of the image. The filter accomplishes this task by only averaging the values around the current pixel that are close in color value to the current pixel. The 'closeness' of other neighborhood pixels to the current pixels is determined by the specified threshold. I.e. for a value of 10 each pixel that contributes to the current mean have to be within 10 values of the current pixel.

The Bilateral mean filter can be used to remove image noise but still preserve edge boundries.

Interface

Instructions

1. Specify the window size to use for the averaging filter. The greater the window size the more blurring will occur in the image
2. Specify the 'closeness' threshold. The smaller the threshold the less distant pixels will contribute to the current mean. Larger thresholds will allow more pixels to contribute to the mean but will also start blurring over less defined edges.

Example

Source	Bilateral

See Also

Mean
Median
Kuwahara

For more information

Bilateral Filtering for Gray and Color Images
Jiangjian Xiao - Bilateral Filter and Applications

New Post

Bilateral Related Forum Posts	Last post	Posts	Views
None