Neurotechnology company logo
Menu button

SlapSeg III Evaluation

These comments provided by Neurotechnology are based on the submission results, reviewed on July 25, 2025.

Neurotechnology's slap fingerprint segmentation algorithm showed off as a top performer in the SlapSeg III evaluation, featuring the fastest performance and almost the best accuracy in most categories of the SlapSeg III evaluation.

What is SlapSeg III?

SlapSeg III Evaluation is a NIST-run public test of automated slap fingerprint segmentation algorithms. Output from the tested automated algorithms is compared to output from a human examiner and analyzed for similarity.

See SlapSeg III official page for more information.

Fingerprint segmentation is the act of separating or segmenting an image of the friction ridge structure of the hand into individual images of the upper-most finger joints, known as distal phalanges.

Currently there are 11 vendors participating in the evaluation. Our latest submission is Neurotechnology+0017. The submitted algorithm is available in MegaMatcher SDK and VeriFinger SDK.

Neurotechnology evaluation results in all 4 categories of the SlapSeg III are presented below:

Tenprint Cards Category

This category uses "TwoInch" scanned images of inked ten-print card slaps. Segmentation accuracy in this category is measured by the percentage that at least 8 fingers were segmented correctly.

Our algorithm is the third most accurate among this category's participants, showing:

  • 86.8% correct segmentation ratio versus 90.8% for the most accurate contender.
  • 203 ms mean combined segmentation time versus 175 ms by the most accurate contender.

Identification Flats Category

This category uses "ThreeInch" live scan images captured using devices with a 3-inch scanning surface. Segmentation accuracy in this category is measured by the percentage that all 10 fingers were segmented correctly.

Our algorithm is the second most accurate among this category's participants, showing:

  • 88.8% correct segmentation ratio versus 91.2% for the most accurate contender.
  • 296 ms mean combined segmentation time versus 127 ms by the most accurate contender.

Upper Palms Category

This category uses "FiveInch" half palm (upper palm) live scan images. Segmentation accuracy in this category is measured by percentage that at least 8 fingers were segmented correctly.

Our algorithm showed:

  • 61.1% correct segmentation ratio versus 67.1% for the most accurate contender.
  • 782 ms mean combined segmentation time versus 679 ms by the most accurate contender.

Full Palm Category

This category uses "EightInch" full palm live scan images. Segmentation accuracy in this category is measured by percentage that at least 8 fingers were segmented correctly.

Our algorithm is the second most accurate among this category's participants:

  • 94.3% correct segmentation ratio versus 97.2% for the most accurate contender.
  • 1135 ms mean combined segmentation time versus 549 ms by the most accurate contender.
Facebook icon   LinkedIn icon   Twitter icon   Youtube icon   Email newsletter icon
Copyright © 1998 - 2025 Neurotechnology