Parallel smoothing

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

KeywordSuffixZip
parallel-smoothing.json028-parallel-smoothing.json
parallel-smoothing.dat029-parallel-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 along ridges
Fingerprint image after parallel smoothing. Only areas within mask are computed.

Binary data

Binary data structure is identical to that of equalized image.

Example: 029-parallel-smoothing.dat (145,112 scalars, range -1 to 0.98, average -0.2)

Json

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

Example: 028-parallel-smoothing.json

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