AI Facial Recognition Security System FaceMe Security

**Improvement of Spoofing Prevention Accuracy and Performance** With FaceMe SDK 7.8, we enhance measures against increasingly sophisticated spoofing attacks by improving authentication accuracy and processing speed, thereby increasing the safety and reliability of facial recognition. - IR + RGB Spoofing Prevention: Detection accuracy improved by up to 35%, processing speed improved by up to 15% - 3D Spoofing Prevention: Detection accuracy improved by up to 56.8% for Intel RealSense D415 **Reducing Development Burden with the New Integrated API "FaceMe Authenticator"** We have integrated multiple processes that previously required individual implementation into a single API. Integrated Functions: - Face Detection + Feature Point Extraction + Spoofing Prevention + Authentication Processing Features: - Compatible with Windows / Ubuntu x64 / Android - 2D cameras, 3D depth cameras, and IR + RGB cameras can be used through a single interface - Significantly reduces development burden while maintaining high-accuracy authentication

CyberLink announces the start of a no-code integration between its AI facial recognition security system "FaceMe Security" and Asteria's no-code AI/IoT platform "Gravio." ■ Features Realized through the Integration of "FaceMe Security" and "Gravio" - Balancing privacy protection and high-speed processing Facial images are analyzed on an edge PC without being sent to the cloud, ensuring privacy protection through on-memory processing. - High-precision, low-latency walkthrough authentication that allows facial recognition while walking Thanks to high-speed processing at the edge, users can smoothly undergo facial recognition without having to stop. - Flexible integration with various external services through no-code Gravio integrates with over 60 external services (such as Slack, Teams, kintone, BI tools, etc.) without code, enabling immediate notification of authentication results and data analysis, thus achieving automation tailored to the field. - Realization of short-term, low-cost implementation No-code construction eliminates the need for dedicated development, allowing for the rapid implementation of the facial recognition system without requiring large-scale infrastructure, thus enabling low-cost deployment.

CyberLink Corp. (hereinafter referred to as CyberLink) announces that its online identity verification solution "FaceMe eKYC" has won the "Silver Award" at the 34th Taiwan Excellence Awards. The "Taiwan Excellence Awards" is often referred to as the "Academy Awards" of the Taiwanese industry. The Ministry of Economic Affairs of Taiwan (equivalent to Japan's Ministry of Economy, Trade and Industry) invites experts from various fields to evaluate products from multiple perspectives, including research and development, design, quality, and marketing, with only outstanding products being selected for this highly prestigious award. This year, over 1,000 products entered the competition, and FaceMe eKYC was chosen as one of the top 30, receiving the "Silver Award." This recognition reflects the advanced AI facial recognition technology that CyberLink has developed and the high reliability and convenience that FaceMe eKYC offers in the field of online identity verification.

In the latest "Age Estimation Evaluation Test" conducted by NIST, the AI facial recognition engine "FaceMe" ranked 5th in the world. 【What is the NIST FATE Age Estimation Evaluation Test?】 The NIST FATE Age Estimation Evaluation Test is one of the international benchmarks for facial analysis technology conducted by the National Institute of Standards and Technology (NIST) in the United States, which evaluates the age estimation accuracy of AI algorithms using a large-scale facial image dataset. 【Evaluation Results of FaceMe】 - World Ranking: 5th Among 20 vendors worldwide, FaceMe ranked 5th, demonstrating top-class accuracy in an international competitive environment. - Mean Absolute Error (MAE): 2.87 years FaceMe's average error in estimated age is 2.87 years, with only a 0.35-year difference from the top-ranked algorithm, achieving world-class accuracy. *MAE (Mean Absolute Error): A numerical representation of the error in estimated age (the smaller the number, the higher the accuracy). *NIST conducted the evaluation using 1 million facial images of individuals aged 18 to 30.