Filtered mask (SourceAFIS transparency data)

SourceAFIS » Algorithm » Transparency » Filtered mask

Filtered mask, a part of algorithm transparency, refines combined mask using a set of filters into a mask marking valid fingerprint area. It is computed during feature extraction. It is used to derive equalized image, block orientation and smoothed orientation, parallel smoothing and orthogonal smoothing, and binarized image and derived data. It is later processed into pixel mask and subsequently into inner mask.



Mask visualization can be computed from this stage's binary data combined with block map and original fingerprint image. Visualization itself is not part of transparency data.

Filtered contrast mask. Yellow color marks valid fingerprint area.

Binary data

Binary data has the same format as for absolute contrast mask except that it is inverted and value 1 now describes valid fingerprint area while value 0 describes low contrast area.

Example: 020-filtered-mask.dat


Json data describes basic properties of the binary data, most importantly dimensions of the mask, which is the same as the number of primary blocks.

Example: 019-filtered-mask.json

  "axes": [
  "dimensions": [
  "scalar": "boolean",
  "bitness": 8,
  "format": "false as 0, true as 1"