Orthogonal smoothing

Orthogonal smoothing data, a part of algorithm transparency, is computed from equalized image during feature extraction by smoothing pixels orthogonally to smoothed ridge orientation in all primary blocks on the block map that are within mask. Orthogonal smoothing data is used together with parallel smoothing to produce binarized image.

KeywordSuffixZip
orthogonal-smoothing.json030-orthogonal-smoothing.json
orthogonal-smoothing.dat031-orthogonal-smoothing.dat

Visualization

The following image can be reconstructed from this stage's binary data. Visualization itself is not part of transparency data.

Fingerprint image with smoothing across ridges
Fingerprint image after orthogonal smoothing. Only areas within mask are computed.

Binary data

Binary data structure is identical to that of equalized image.

Example: 031-orthogonal-smoothing.dat (145,112 scalars, range -1 to 0.47, average -0.2)

Json

Json data describes basic properties of the binary data, most importantly dimensions of the image.

Example: 030-orthogonal-smoothing.json

{
  "axes": [
    "y",
    "x"
  ],
  "dimensions": [
    374,
    388
  ],
  "scalar": "double",
  "bitness": 64,
  "endianness": "big",
  "format": "IEEE754"
}