Biometrics & Machine Vision


SoloMetrics is a company dedicated to envisioning and implementing the latest cutting edge products based on advanced Computer Vision and Image Processing technologies. We are a company headquartered in Chicago, Illinois USA. Our team of accomplished scientists and engineers is continuously striving to create products and services that help us serve our clients better.

SoloMetrics has developed algorithms and software / hardware products for biometric fingerprint, face, iris, retina, voice and palm print recognition, computer-based vision and object recognition for security companies and system integrators. Our products serve both civil and forensic applications, including border crossings, criminal investigations, systems for voter registration, verification and duplication checking, passport issuance and other national-scale projects.

With years of research in the fields of image processing, pattern recognition and neuroinformatics we are dedicated to develop custom products related to identification and verification of objects and personal identity.

Big Data Biometrics 

The need for biometric identification systems is increasing in civil and forensic fields of applications. Fast and accurate identifcation becomes particularly critical for large-scale projects, such as passport and visa documentation, border crossings, election control systems, credit card transaction control and crime scene investigations. Many countries, including the US, European and others, incorporate biometric data into passports, ID cards, visas and other documents for use in large national-scale automatic biometric identification systems. Automated fingerprint identification systems (AFIS) have been widely used in forensics for the past two decades, and recently they have become relevant for civil applications as well. Whereas large-scale biometric applications require high identification speed and reliability, multi-biometric systems that incorporate both face and fingerprint recognition offer a number of advantages for improving identification quality and usability. System scalability is important, as the system might be extended in the future, a high productivity level should be kept by adding new units to the existing system.  The daily number of identification requests could be very high. Identification requests should ideally be processed in a very short time, thus high computational power would be required. The system must be tolerant to hardware failures, as even temporary pauses in its work may cause big problems taking into account the application size. 
Biometric identification systems tend to accumulate False Acceptance Rates when the database size increases while using a single fingerprint, face or retina / iris image for identification and it becomes unreliable for a large-scale application. Our Multi-biometric technologies (i.e. collecting fingerprint, face and/or retina / iris templates from the same person) can be employed for greater reliability and precision. A multi-biometric hardware with fused algorithm is used to create a single identification decision based on the results.  Our systems support major biometric standards. This allows using the system-generated templates or databases with systems from other vendors and vice versa. And our systems work within the client network, as in most cases client workstations are remote from the server with the central database. 
Many existing AFIS are specialized for criminalistics or other particular applications and are quite expensive. Solometrics offers IDXS customised solutions that includes hardware and software for large-scale AFIS or multi-biometric fingerprint, retina / iris, face, and voice identification products while meeting all of the above requirements.

Eye Algorithm Engine

Our fast matching configurable matching speed varies from 60,000 to 1,200,000 comparisons per second. You can choose between the Iris only, two Irises, Retina only and Retina + Iris options or Retina + Face depending on your needs and requirements. Retina / irises are detected even when the images have obstructions, visual noise and different levels of illumination. Light reflections, eyelids and eyelash obstructions are eliminated. Images with narrowed eyelids or eyes that are gazing away are also accepted. Performs Eye template matching in 1-to-1 (verification) and 1-to-many (identification) modes. The Eye matcher component allows to increase template matching reliability by: matching templates that contain 2 retina and/or iris records; matching templates that contain fngerprint, face, voiceprint and/or retina and/or iris records.The Eye template integrates with existing standards and additional image formats with new or existing biometric systems. 

Face Algorithm Engine

With our robust 2D photo and 3D facial authentication engine, a template generalization is used to generate a better quality template from several face angles. Better quality templates result in higher identification quality. Tolerance to face posture assures face enrollment convenience. IDXS allows 360 degrees head roll. Head pitch can be up to 15 degrees in each direction from the frontal position. Head yaw can be up to 45 degrees in each direction from the frontal position. 

Reliable face detection assures convenient face enrollment from cameras, webcams and especially various scanned documents: faces will be found on scanned pages from passports, files etc. multiple faces can be also detected in a scene or a scanned document and are simultaneously processed. A conventional face identification system can be easily cheated by placing a photo of another person in front of a camera. IDXS is able to prevent this kind of security breach by using 3D face recognition algorithm. 
The biometric template record can contain several face samples belonging to the same person. These samples can be enrolled from different sources and in different time, thus allowing improvement in matching quality. For example a person could be enrolled with and without eyeglasses or with different eyeglasses, with and without beard or moustache. Facial template matching in 1-to-1 (verification) and 1-to-many (identification) modes. The IDXS face engine includes a fused matching algorithm that allows increased template matching reliability by matching templates that contain fingerprint, face, voiceprints and/or retina / iris records. 
Fingerprint Algorithm Engine
The IDXS fingerprint engine matches rolled and fat fingerprints between themselves. Usually conventional ‘fat’ fingerprint identification algorithms perform matching between fat and rolled fingerprints less reliably due to the specific deformations of rolled fingerprints. IDXS allows matching of fat-fat, fat-rolled or rolled-rolled fingerprints with high reliability. The algorithm matches up to 145,000 fat fingerprint records per second. IDXS includes fingerprint image quality determination, which can be used during enrollment to ensure that only the best quality fingerprint template will be stored into database. Template generalization is used to generate a better quality template from several fingerprints. Better quality templates result in higher identification quality. IDXS is tolerant to fingerprint translation, rotation and deformation. It uses a proprietary fingerprint matching algorithm that identifies fingerprints even if they are rotated, translated and have deformations. 
For some identification tasks IDXS’s fingerprint engine matching speed can be increased to up to 700,000 fingerprints per second by pre-sorting database entries using certain global features. In 
most cases there is a fairly good chance that the correct match will be found at the beginning of the search. As a result, the number of comparisons required to achieve fingerprint identification decreases drastically, and the effective matching speed increases correspondingly. Adaptive image filtration algorithm eliminates noise, ridge ruptures and stuck ridges and extracts minutiae reliably even from poor quality fingerprints, with processing time of less than 1 second. 
Local template storage on hardware not only increases the matching efficiency and speed whereas decreases the extra transactions load on the network. The templates that are unavailable on local storage require an online data connection to download the required templates on demand, matching and storing the processed data. 
Palm Print Authentication Engine

Palm print template extraction and matching require much more time than fingerprints, as palm images are much larger compared to fingerprint images, but have similar feature density. An image of fingerprint, which was scanned with AFIS-class scanner at 500 dpi resolution, is usually at least 500 x 500 pixels (0.25 Megapixels). Full palm image, scanned at the same resolution, is 160 times bigger (40 Megapixels). After excluding white space, palm image is still about 50 times bigger than fingerprint image. The full palm print templates may contain about 2,000 minutiae compared to about 50 for fingerprint templates. IDXS palm print can be also run on more than one processor core allowing to process several templates in parallel.

Vascular Scanning Engine
Vascular Technology uses the vascular patterns of the palm as a personal identification data.  Compared with Fingerprint, a palm has a broader and more complicated vascular pattern thus contains the most secure wealth of differentiating features in human identification. The palm is an ideal part of the body for biometric technology as it normally does not have hair which can be an obstacle for photographing the blood vessel pattern. IDXS fully supports this highly-accurate, user-friendly biometrics technology that uses the vein patterns of a palm to authenticate an individual's identity. 
Voice-print Algorithm Engine
The IDXS Voiceprint is based on a propreitary voice matching algorithm which determines if a voice sample matches the template that was extracted from a specific phrase. During enrollment, one or more phrases are required to be said by the person being enrolled. Later that person may be asked to pronounce a specific phrase for verification. This method assures protection against the use of a covertly recorded random phrase from that person. A two-factor authentication with a password phrase is performed when a person is asked to say a unique phrase (such as password phrase or an answer to a secret question that is known only by the person being enrolled). The overall system security increases as both voice authenticity and password are checked. A system may request each user to enroll a set of unique phrases. Later the user will be requested to say a specific phrase from the enrolled set. This way the system can ensure that an actual person is being verified as opposed to somebody using a voice recording. Several voice records with the same phrase may be stored to improve speaker recognition reliability. Certain natural voice variations (i.e. hoarse voice) or environment changes (i.e. office and outdoors) can also be stored in the same template. An adaptive voice filtration algorithm surpasses background noises etc., and extracts reliable voice data with processing time of less than 1 second. Local template storage on hardware is a proprietary feature of IDXS, which not only increases the matching efficiency and speed whereas decreases the extra transactions load on the network. The templates that are unavailable on local storage will require an online data connection to download the required templates on demand, matching and storing the processed data. 
IDXS Template on Smartcard Engine
IDXS Smartcard Engine offers matching-on-card technology that stores a person’s fingerprint, iris / retina and face templates on a smart card and performs template matching in a microprocessor embedded in the card instead of matching biometric information on external hardware. This method ensures that personal biometric information does not transfer to an external computer as it would in a more basic template-on-card system. Smartcard Engine is developed utilizing a set of ISO/IEC standards to enable interoperability with and easy integration into existing smart card and/or biometric systems. The face and iris / retina matching engines can be used as an additional or alternative factor of authentication that enhances the fingerprint verification. Fingerprint, iris / retina and face templates can be stored on a single card together with the fingerprint, iris / retina and face matching algorithms. 
Smartcard can be integrated at different stages of the card life cycle for various smart cards platforms. The post-issuance library gives the possibility to rapidly integrate matching on card in projects where time constraints are critical. Biometric verification can also be replaced or be combined with less secure (e.g., PIN) authentication techniques to achieve higher security. Smartcard brings huge reduction in back and forth data transactions to the main server, hence offers utmost security to the main system as well as brings down the connectivity costs. 
BXS Template in Barcode Engine 
BXS is a variable-size, variable-density two-dimensional (2D) symbology offering high user data capacity at a guaranteed minimum level of error correction. BXS is the most secure 2D barcode available in today’s market. BXS can store more non-text information than any other barcode symbology in much less space and without sacrificing error correction. Each BXS barcode is composed of an array of black and white rectangular modules that can represent compressed image, text and binary information. BXS supports the storage of multiple biometric information such as fingerprint, iris, signature, facial and hand geometry, as well as photographic images and text data. BXS’s encoding methodology utilizes proprietary error correction, making it a trustworthy and robust barcode. BXS’s aggressive error correction means that random areas can be destroyed while still recovering 100 percent of the information. BXS is a cost-efficient, printed technology that reduces the overall cost of your card or passport production system. Compared to other data storage technologies, BXS adds no cost to the overall system.