November 29, 2016 -
Neurotechnology has released FingerCell 3.0, a software development kit (SDK) for fingerprint recognition solutions that run on low-power, low-memory microcontrollers.
According to a company statement, FingerCell can extract a fingerprint template using less than 128KB of memory, enabling it to be used in compact devices that have limited on-board resources, such as: mobile phones, fingerprint door locks, access control panels, time and attendance systems, handheld payment and point-of-sale terminals. It can also be used in various logon subsystems and small device components that can be integrated into cars and home electronics, among others.
“Fingerprint scanners are being integrated into smaller and more compact devices we use in everyday life,” said Dr. Justas Kranauskas, project lead for Neurotechnology. “Now these devices can run our fingerprint recognition algorithms on board, with both accuracy and the smallest possible resource consumption.”
FingerCell includes a template extractor, template matcher and template stitching functionality, all optimized to run on embedded CPUs and microcontrollers. The template generator in FingerCell creates either proprietary or ANSI/ISO standard templates. The template stitching algorithm is specially designed for use with small area sensors. It combines multiple fingerprint templates into a single template, which can significantly improve recognition accuracy.
FingerCell 3.0 can be used for both 1:1 matching and 1:many (1:N) identification in embedded applications. It provides fast image processing and feature extraction, is fully tolerant to fingerprint translation and rotation and can recognize a fingerprint from a small portion of it.
On an ARM Cortex-M4 or similar microcontroller, FingerCell can create a fingerprint template in 650 milliseconds (ms) from a 234×332 pixel 500 dpi image and it can match two fingerprint templates in less than four ms.
FingerCell SDK can be provided as source code or as a static library package. The static library can be compiled for the required platform, which can be with or without an operating system. Neurotechnology can also provide a sample hardware evaluation kit on request with the preinstalled FingerCell algorithm.