Binarized skeleton

Binarized skeleton, a part of algorithm transparency, is a monochromatic (black and white) image, from which skeleton construction starts. Two skeletons are built during feature extraction, one for ridges and one for valleys. Binarized skeleton for ridges is a copy of filtered binary image while binarized skeleton for valleys is its inverted version filtered through pixel mask. Binarized skeleton is processed into thinned skeleton.

KeywordSuffixZip
ridges-binarized-skeleton.json040-ridges-binarized-skeleton.json
ridges-binarized-skeleton.dat041-ridges-binarized-skeleton.dat
valleys-binarized-skeleton.json056-valleys-binarized-skeleton.json
valleys-binarized-skeleton.dat057-valleys-binarized-skeleton.dat

Visualization

Visualization of binarized skeleton image below was constructed from this stage's binary data with original fingerprint in the background. Visualization itself is not part of transparency data.

Binarized fingerprint image in semitransparent cyan with original fingerprint in the background
Binarized skeleton for ridges is shown in cyan color. Original fingerprint image can be seen in the background.

Binary data

Binary data has the same structure as for binarized image except that it gets inverted for valley skeleton.

Example: 041-ridges-binarized-skeleton.dat

Json

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

Example: 040-ridges-binarized-skeleton.json

{
  "axes": [
    "y",
    "x"
  ],
  "dimensions": [
    374,
    388
  ],
  "scalar": "boolean",
  "bitness": 8,
  "format": "false as 0, true as 1"
}