Image Matching Using Local Phase Features and Its Application to Biometrics

2015 Fiscal Year Final Research Report

• Project/Area Number: 25280055
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Partial Multi-year Fund
• Section: 一般
• Research Field: Perceptual information processing
• Research Institution: Tohoku University
• Principal Investigator: Koichi Ito 東北大学, 情報科学研究科, 助教 (70400299)
• Co-Investigator(Kenkyū-buntansha): AOKI TAKAFUMI 東北大学, 大学院情報科学研究科, 教授 (80241529)
• Project Period (FY): 2013-04-01 – 2016-03-31
• Keywords: 画像，文章，音声等認識 / ディジタル信号処理 / 画像照合 / 位相限定相関法 / 個人認証

Outline of Final Research Achievements

This project have defined a new image feature called "Local phase feature" to evaluate the similarity between images accurately and developed a variety of fundamental image matching algorithms using local phase features. We have applied local phase features to biometrics, which is required to accurate evaluation of the similarity between images. We have demonstrated the effectiveness of the image matching methods using local phase features on face, iris, plamprint and finger knuckle print recognition.

Free Research Field

計算機学