scispace - formally typeset
Y

Youngsam Kim

Researcher at Electronics and Telecommunications Research Institute

Publications -  19
Citations -  67

Youngsam Kim is an academic researcher from Electronics and Telecommunications Research Institute. The author has contributed to research in topics: Biometrics & Fingerprint (computing). The author has an hindex of 4, co-authored 17 publications receiving 58 citations.

Papers
More filters
Patent

Apparatus and system for managing transaction information of public organization using blockchain technology

TL;DR: In this article, a transaction information managing system including a plurality of servers and at least one third-party server is presented, where the plurality servers are configured to create, when transactions using the budget of the public organization occurs, a block based on transaction information of the transactions, add the block to the block chain, and share the block with the third party server.
Patent

Terminal apparatus, server apparatus, blockchain and method for FIDO universal authentication using the same

TL;DR: In this paper, the authors present a protocol for FIDO universal authentication using a blockchain, which includes sending, by the terminal apparatus, a FIDOD service request for any one of FIDOV registration, FIDOC authentication, and FIDOR deregistration for an application service provided by the server apparatus to the server, and verifying, by blockchain, a response message, which is created as a result of local authentication of a user in the user in response to the FOV service request.
Patent

Method and apparatus for key generation based on face recognition using CNN and RNN

TL;DR: In this article, a face recognition based key generation apparatus controls a key generation model that is formed of a CNN and an RNN to be learned to generate a desired key having a consistent value by using sample facial images of a key owner and a PIN of the key owner as inputs.
Proceedings ArticleDOI

A Performance Comparison of Loss Functions

TL;DR: The experiments show that the proposed loss function is visibly superior to the ability to classify digit images and the experimental results indicate that Arcface loss and Additive-Margin loss functions satisfy predefined test accuracy most quickly under two and three dimensional embedding, respectively.
Journal ArticleDOI

Construction of a New Biometric-Based Key Derivation Function and Its Application

TL;DR: This paper presents a new biometric-based key derivation function (BB-KDF), which users are able to derive cryptographic keys solely from their own biometric data: users do not need any other user-specific helper information.