• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권3호
• /
• pp.757-770
• /
• 2022

Palmprint recognition has drawn increasingly attentions in the past decade due to its uniqueness and reliability. Traditional palmprint recognition methods usually use high-resolution images as the identification basis so that they can achieve relatively high precision. However, high-resolution images mean more computation cost in the recognition process, which usually cannot be guaranteed in mobile computing. Therefore, this paper proposes an improved low-resolution palmprint image recognition method based on residual networks. The main contributions include: 1) We introduce a channel attention mechanism to refactor the extracted feature maps, which can pay more attention to the informative feature maps and suppress the useless ones. 2) The ResStage group structure proposed by us divides the original residual block into three stages, and we stabilize the signal characteristics before each stage by means of BN normalization operation to enhance the feature channel. Comparison experiments are conducted on a public dataset provided by the Hong Kong Polytechnic University. Experimental results show that the proposed method achieve a rank-1 accuracy of 98.17% when tested on low-resolution images with the size of 12dpi, which outperforms all the compared methods obviously.

• 전자공학회논문지CI
• /
• 제42권2호
• /
• pp.31-38
• /
• 2005

최근 생체인식기반의 개인인증은 인증의 자동화와 높은 성능으로 개인인증의 효과적인 방법으로 대두되고 있다. 본 논문에서는 Hu 불변 모멘트에 기초한 장문인식 방법을 제안하였다. 그리고 장문인식 알고리즘의 전체 실행 속도를 높여 효율성 있는 장문인식 시스템을 설계하기 위하여 저해상도(75dpi) 장문이미지$(5.5cm\times5.5cm)$를 사용한다. 제안된 시스템은 두 부분으로 이루어져 있는데 정확한 장문이미지를 획득하기 위한 장문 고정장치와 장문인증을 효과적으로 처리할 수 있는 알고리즘으로 구성되어 있다. 그리고 장문인증 단계는 3회로 제한되며, 그 결과 임계값 0.001일 때 FAR은 $(5.5cm\times5.5cm)$, GAR은 $98.1\%$이다. 이는 [3]과 비교하여, FAR은 $0.002\%$, GAR은 $0.1\%$ 향상되었음을 확인하였다.