Equalized image

Equalized image, a part of algorithm transparency, is computed from scaled image during feature extraction. Every primary block on the block map is equalized separately using data from smoothed histogram to produce high-contrast image. Equalized image is used to compute pixelwise orientation. It is later processed using parallel smoothing and orthogonal smoothing.



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

Equalized fingerprint image
Equalized fingerprint image. Only areas within mask are computed.

Binary data

Image size can be obtained from dimensions field in the associated json data, height first, or from pixels field in block map. Binary data consists of rows of pixels ordered from top to bottom. Every row consists of pixels ordered left to right. Every pixel is a 64-bit IEEE754-encoded big-endian floating-point number in range from -1 (white) to 1 (black). Areas outside the mask are zeroed.

Example: 021-equalized-image.dat (145,112 scalars, range -1 to 1, average -0.58)


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

Example: 020-equalized-image.json

  "axes": [
  "dimensions": [
  "scalar": "double",
  "bitness": 64,
  "endianness": "big",
  "format": "IEEE754"