A Study of High-Performance Biometric Recognition Using Local Phase Features

2021 Fiscal Year Final Research Report

• Project/Area Number: 19H04106
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Review Section: Basic Section 60070:Information security-related
• Research Institution: Tohoku University
• Principal Investigator: Ito Koichi 東北大学, 情報科学研究科, 准教授 (70400299)
• Co-Investigator(Kenkyū-buntansha): 青木 孝文 東北大学, 情報科学研究科, 教授 (80241529)
• Project Period (FY): 2019-04-01 – 2022-03-31
• Keywords: 画像，文章，音声等認識 / バイオメトリクス / 画像照合 / ディジタル信号処理 / 局所位相特徴

Outline of Final Research Achievements

Based on the knowledge obtained from our previous research on the "Phase-Only Correlation," which is a high-accuracy image matching technique that utilizes the phase information of images, we investigated local phase features dedicated to biometric recognition in this research project. We developed a set of basic algorithms for similarity evaluation based on multi-resolution local phase features, and studied various high-performance algorithms required for biometric recognition systems to meet the requirements of "anytime, anywhere, anyone, easily, and securely". In addition, we applied local phase features to contactless palmprint/vein recognition, neonate fingerprint recognition, iris recognition, and face recognition in order to demonstrated their effectiveness.

Free Research Field

計算機システム

Academic Significance and Societal Importance of the Research Achievements

本研究代表者らが開発を進めてきた画像の位相情報に着目した画像マッチング技術（位相限定相関法）は，さまざまな生体特徴に有効であることを実証している．その知見に基づいて，生体認証に特化した新しい局所特徴記述子として局所位相特徴および基本アルゴリズムを本研究課題を通して検討した．また，掌紋認証や顔認証をはじめとする具体的な応用研究に適用することで実用化を見据えた研究開発を行った．これらの成果により，生体認証の学術的な深化および実用化に少なからず貢献したと考える．