組み合わせ分割照合法による日本語署名照合の高精度化

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2014/12/01

タイトル(英語): Improvement of Japanese Signature Verification by Combined Segmentation-verification Approach

著者名: 上平　裕太（三重大学 大学院工学研究科），大山　航（三重大学 大学院工学研究科），若林　哲史（三重大学 大学院工学研究科），木村　文隆（三重大学 大学院工学研究科）

著者名(英語): Yuta Kamihira (Graduate School of Engineering, Mie University), Wataru Ohyama (Graduate School of Engineering, Mie University), Tetsushi Wakabayashi (Graduate School of Engineering, Mie University), Fumitaka Kimura (Graduate School of Engineering, Mie University)

キーワード: 署名照合，濃度こう配特徴，DPマッチング，SVM，分割　　Signature Verification，Gradient-Based Features，Dynamic Programming Matching，Support Vector Machine，Segmentation

要約(英語): This paper proposes a signature verification technique called combined segmentation-verification based on off-line features and on-line features. We use three different off-line feature vectors extracted from full name Japanese signature image and from the sub-images of the first name and the last name. The Mahalanobis distance for each off-line feature vector is calculated for signature verification. The on-line feature based technique employs dynamic programming (DP) matching technique for time series data of the fullname signature and first name and last name. The final decision (verification) is performed by SVM (Support Vector Machine) based on the three Mahalanobis distances and three dissimilarity of the DP matching. In the evaluation test the proposed technique achieved 3.35% EER (Equal Error Rate) with even FRR (False Acceptance Rate) and FAR (False Rejection Rate), which is 3.10% lower than the best EER obtained by the individual technique. This result shows that the proposed combined segmentation-verification approach improves Japanese signature verification accuracy significantly.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.134 No.12 （2014） 特集：電気関係学会東海支部連合大会

本誌掲載ページ: 1809-1816 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/134/12/134_1809/_article/-char/ja/