Neurotechnologija Announces SentiSight SDK Universal Object Recognition Technology for Robotics and Computer Vision Applications
Sophisticated Algorithm Provides Versatile and Accurate Recognition Using Still or Video Images from a Wide Variety of Cameras
Vilnius, Lithuania – June 4, 2007 – Neurotechnologija, a company widely recognized for their high-precision biometric identification technologies, today announced their entry into the AI and Robotics market with the introduction of the new SentiSight Software Development Kit (SDK) object recognition technology. Designed for the development of computer-based vision systems, the SentiSight algorithm provides versatile, fast and accurate 2D and 3D object recognition for use in a wide variety of applications, including image search engines, security systems, manufacturing and robot and machine vision. SentiSight object recognition technology is tolerant to object scale, rotation and pose and works with still and video images from most digital cameras, including Webcams. It can process video streams in real time, enabling its use in real-time applications such as autonomous robot navigation, parts identification on an assembly line or road sign recognition in a moving vehicle.
"We are very pleased to announce the availability of SentiSight SDK, the product of years of research and development by our AI and Robotics Division," said Algimantas Malickas, CEO of Neurotechnologija. "For the past 17 years we have developed algorithms that provide fast, accurate and reliable recognition of fingerprints and faces for biometric applications. Building on that experience, SentiSight SDK is a natural progression for us into the AI and computer vision space with a product that offers both the reliability and reasonable pricing our customers have come to rely on." Malickas continued.
Humans have a natural ability to learn and recognize objects, even when the objects are presented in different environments, scales, rotations and poses. There are a growing number of tasks – for example environmental object recognition for navigation or product recognition and classification in assembly manufacturing – where automating the process of recognizing objects provides an extra measure of safety, efficiency and cost-effectiveness. For these applications a computer system or robot with object recognition capabilities is used in conjunction with a camera or other visual input device. SentiSight SDK provides the sophisticated algorithms that enable such a computer or robot to learn an object, store its unique features in a database and later recognize that object from a live camera, still image or video stream.
SentiSight SDK enables fully automatic and manual object learning as well as simultaneous multiple object detection and recognition. Using a live camera, series of still images or video, SentiSight first learns an object by extracting specific features or descriptors of the object from different sides, distances from the camera and angles of view. This enables SentiSight to develop a 2D or 3D object model that can be stored (e.g. in a database). When that same object is later presented in a photograph, video, on the Web or from a real-time live video camera, the SentiSight algorithm compares the new images to the existing object model, recognizes the object and outputs the object's name and coordinates.
Because the SentiSight algorithm is tolerant to a large variation of object scale, rotation, translation and lighting conditions, it can recognize objects in a variety of different situations with a high degree of accuracy. Results can vary somewhat based on the qualities of the initial learning and the conditions in which the object is to be later recognized.
SentiSight can recognize an object at an average of 10 video frames per second for a single object model at 320 x 240 or better resolution. However for tasks when an even faster response is required, the SentiSight Library includes a tracking mode that enables SentiSight to track an object at speeds of up to 20 frames per second. SentiSight SDK also includes a Camera Manager Library for Microsoft Windows, which allows simultaneous capture from multiple cameras.
SentiSight gives developers complete control over SDK data input and output, enabling the functions to be used with most cameras, with any database and with any user interface. Reliability tests and additional technical specifications are available at: http://www.neurotechnologija.com/sentisight.html.
Neurotechnologija's algorithms consistently have won awards and top honors in numerous international biometrics competitions, including the recent FVC2006, in which the company's VeriFinger 5.0-based fingerprint recognition algorithm achieved the best score for average zero false match rate. Last month Neurotechnologija announced that their MegaMatcher 2.0 large-scale AFIS fingerprint technology received full NIST-MINEX Certification from the U.S. Government. MegaMatcher 2.0 also provides multi-biometric face and fingerprint recognition. Neurotechnologija's other biometric products include VeriLook SDK for facial recognition and FaceCell and FingerCell for embedded facial and fingerprint recognition on compact devices.
SentiSight SDK is available now with highly competitive licensing options from Neurotechnologija: http://www.neurotechnologija.com/. A 30-day trial version with full functionality is also available for download.
Neurotechnologija provides algorithms and software development products for biometric fingerprint and face identification, computer-based vision and object recognition to security companies, system integrators and hardware manufacturers. More than 1000 system integrators and sensor providers worldwide integrate Neurotechnologija's technologies into their own products.
Drawing from years of academic research in the fields of neuroinformatics, image processing and pattern recognition, Neurotechnologija was founded in 1990 in Vilnius, Lithuania and released its first fingerprint identification system in 1991. Since that time Neurotechnologija has released more than 30 products and version upgrades for identification and verification of personal identity. For more information, visit: http://www.neurotechnologija.com/
Jennifer Allen Newton
Bluehouse Consulting Group, Inc.
jennifer (at) bluehousecg.com