Scaled image

Scaled image, a part of algorithm transparency, is computed from decoded image during feature extraction by scaling it to 500dpi. If decoded image is at (or almost at) 500dpi, no scaling is performed and scaled image is identical to decoded image.

All other parts of the algorithm assume they work with 500dpi images. Scaled image coordinate space is used to measure all pixel positions and distances in all other transparency data, especially block map. Scaled image itself is used to compute clipped contrast and equalized image.



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

Black fingerprint image on white background
Fingerprint image scaled to 500dpi.

Binary data

Image size can be obtained from dimensions field in the associated json data, height first, or from block map's pixels field. 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 0 (white) to 1 (black).

Example: 004-scaled-image.dat (145,112 scalars, range 0 to 1, average 0.11)


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

Example: 003-scaled-image.json

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