Fingerprint identification for embedded platforms
FingerCell technology is designed for embedded biometric systems developers and features compact, sensor-independent and cross-platform fingerprint recognition algorithm. It offers decent performance on various embedded devices based on low-power microcontrollers or processors.
FingerCell is available for integrators as Software Development Kits (SDK) with FingerCell library or source code for developing a fast and reliable system on embedded or mobile platform.
Features and Capabilities
- Fast performance even on low speed processors.
- Verification (1-to-1 matching) and identification (1-to-many matching) are provided.
- Compact fingerprint template and unlimited database size.
- ISO biometric standards support.
- Cross platform algorithm with compact portable source code.
- FingerCell Demo Unit with pre-installed algorithm is optionally available.
- VeriFinger SDK for desktop and mobile platforms is optionally available.
- Reasonable prices, flexible licensing and free customer support.
FingerCell is designed to provide decent reliability and identification speed for various embedded devices and platforms. The FingerCell algorithm includes these proprietary solutions:
- Fast performance. Fingerprint template extraction from an image and verification against another template can be performed in less than less than 0.7 seconds on a 168 MHz ARM Cortex-M4 family processor, which is acceptable for embedded systems.
- Identification ability. FingerCell is suitable not only for fingerprint verification (1-to-1 matching), but also for identification (1-to-many matching). The algorithm matches about 250 fingerprints per second in 1-to-many mode on a 168 MHz ARM Cortex-M4 family processor.
- Adaptive image filtration. This algorithm eliminates noises, ridge ruptures and stuck ridges for reliable minutiae extraction even from poor quality fingerprints.
- Compact fingerprint template. FingerCell template size depends on the number of stored minutiae – for example, a template with 16 minutiae needs only 152 bytes of memory, whereas a template with 64 minutiae needs 448 bytes. Combined with configurable maximal number of minutiae in a template and unlimited database size, the target system size and performance can be optimized according to customers requirements.
- ISO/IEC standards support. FingerCell SDK can generate and match fingerprint templates in the ISO/IEC 19794 family formats.
- Tolerance to fingerprint translation and rotation. Such tolerance is achieved by FingerCell proprietary fingerprint matching algorithm. The algorithm is able to identify fingerprints even if they are rotated and translated.
- Compact portable software. FingerCell is designed for easy implementation into very various and specific applications. The algorithm's source code is sensor independent; therefore it can be ported to various platforms and hardware. Compiled code and internal data arrays require only 128 kB of memory and therefore can be implemented in low memory microchips, thus reducing hardware costs.
- FingerCell Demo Unit. Neurotechnology offers pre-installed FingerCell algorithm on testing hardware for the technology evaluation. The Demo Unit is available on request.