top of page
이미지 제공: Mitchell Luo

DALTON Algorithm

Optimization of Swipe Fingerprint IC

dal01.png

FINGERPRINT IMAGE

dal02.png

CONVERT INTO FREQUENCY DOMAIN

dal03.png

ENCODE AND SAVE

  • Extract traditional minutia instead of characteristic of fingerprint image

  • Translate Data of Spatial Domain into Frequency Domain (Extract frequency)

  • Fast matching-speed to comparison of code level

Connecting Dots_edited.jpg

MUON Algorithm

Fast and Slim but Powerful !

FRR < 1.5% @ FAR 1:50,000 Time include image capture time  and all of process inside algorithm

“image processing  + extract features  + matching”

mu01.png
  • Support ultra small sized sensor (4mm x 4mm, 5mm x 2.8mm)

  • More than 400 features are extracted and can be matched within 0.3 second

mu02.png
  • Extracting abundant features from detailed ridge shape and pixel intensity change regardless of sensor size.

mu03.png
  • All users with scar or discontinued ridges can enroll and verify without any problem unlike traditional minutia or pattern based algorithms

  • No FPU, No math library are required !

  • Optimized for TrustZone as well as embedded environment consuming small memory

mu04.png
mu05.png
백색 파도

CALISTO Algorithm

IRIS Recognition Algorithm

cal01.png

VS

cal02.png
  • Iris recognition is a method of identifying people based on unique patterns within the ring-shaped region surrounding the pupil of the eye. The iris usually has a brown, blue, gray,
    or greenish color, with complex patterns that are visible upon close inspection. Because it makes use of a biological characteristic, iris recognition is considered a form of biometric verification.

  • Iris recognition is separated and extracted each different patterns through the algorithm, digitize them, and store them to identify users.

  • Everyone's iris patterns are different.
    even, the right and left iris of the same person are different.

  • Noncontact recognition at the same time both eyes

Connecting Dots_edited.jpg

Applied Industrial proven Algorithm and FIDO solution

over 10 Million on global smartphone

bottom of page