Smoothed orientation

Smoothed orientation, a part of algorithm transparency, is computed from block orientation during feature extraction by adding orientation vectors of four edge-neighboring blocks to every primary block that is within mask. Smoothed orientation is used in parallel smoothing and orthogonal smoothing.

Visualization

Visualization of smoothed block orientations was constructed from this stage's binary data mapped onto blocks, masked, and overlaid on the original fingerprint image. Visualization itself is not part of transparency data.

Format

Smoothed orientation format is identical to that of block orientation.

Example: 015-smoothed-orientation.cbor

{
  "width": 26,
  "height": 25,
  "vectors": [
    0.0,
    0.0,
    "... skipped 1,296 items in range -3.87e+03 to 3.16e+03 ...",
    0.0,
    0.0
  ]
}