Binarized image (SourceAFIS transparency data)

SourceAFIS » Algorithm » Transparency » Binarized image

Binarized image, a part of algorithm transparency, is a version of fingerprint image that has all pixels set either to black or white with no shades of gray. It is computed during feature extraction by comparing parallel smoothing of the image to orthogonal smoothing. Binarized image is refined to filtered binary image before it is used as binarized skeleton image.



Visualization of binarized 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 is shown in semitransparent cyan color with original fingerprint visible behind it. Some errors can be seen near fingerprint boundary and at points of high curvature.

Binary data

Binary data is a 2D array with dimensions that can be found in the associated json data, height first, or in block map's pixels field. Binary data consists of rows of pixels ordered from top to bottom. Every row is a sequence of pixels from left to right. Every pixel is a single byte with value 1 (black foreground) or 0 (white background).

Example: 034-binarized-image.dat


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

Example: 033-binarized-image.json

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