Binarized image

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.

Key	MIME	Filename in ZIP
`binarized-image`	`application/cbor`	`018-binarized-image.cbor`

Visualization

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 image in semitransparent cyan with original fingerprint in the background — 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.

Format

Binarized image is a matrix (2-dimensional array) of boolean values, one boolean value per pixel. Value true represents black pixel. Value false represents white pixel. Binarized image is encoded in CBOR:

width - Image width in pixels.
height - Image height in pixels.
cells - Array of width * height boolean values representing pixels in the binarized image. The 2-dimensional pixel space is mapped into 1-dimensional array by sorting pixels by Y position top to bottom and then by X position left to right.

Example: 018-binarized-image.cbor

{
  "width": 388,
  "height": 374,
  "cells": [
    false,
    false,
    "... skipped 145,108 items ...",
    false,
    false
  ]
}