http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Face Representation Method for 3D Model-Based Face Recognition
Kanghun Jeong,Hyeonjoon Moon 대한전자공학회 2008 ICEIC:International Conference on Electronics, Inf Vol.1 No.1
3D model based approach for face recognition has been spotlighted as a robust solution under variant conditions of pose and illumination. Since a generative 3D face model consists of a large number of vertices, a 3D model based face recognition system is generally inefficient in computation time. In this paper, we propose a novel 3D face representation algorithm to reduce the number of vertices and optimize its computation time. We evaluate the performance of proposed algorithm with the 3D face database.
( Kanghun Jeong ),( Hyeonjoon Moon ) 한국인터넷정보학회 2011 KSII Transactions on Internet and Information Syst Vol.5 No.1
A 3D model based approach for a face representation and recognition algorithm has been investigated as a robust solution for pose and illumination variation. Since a generative 3D face model consists of a large number of vertices, a 3D model based face recognition system is generally inefficient in computation time and complexity. In this paper, we propose a novel 3D face representation algorithm based on a pixel to vertex map (PVM) to optimize the number of vertices. We explore shape and texture coefficient vectors of the 3D model by fitting it to an input face using inverse compositional image alignment (ICIA) to evaluate face recognition performance. Experimental results show that the proposed face representation and recognition algorithm is efficient in computation time while maintaining reasonable accuracy.
Biometric Authentication for Border Control Applications
Taekyoung Kwon,Hyeonjoon Moon IEEE 2008 IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERIN Vol.20 No.8
<P>We propose an authentication methodology that combines multimodal biometrics and cryptographic mechanisms for border control applications. We accommodate faces and fingerprints without a mandatory requirement of (tamper-resistant) smart-card-level devices on e-passports for easier deployment. It is even allowable to imprint (publicly readable) bar codes on the passports. Additionally, we present a solution based on the certification and key management method to control the validity of passports within the current Public-Key Infrastructure (PKI) technology paradigm.</P>
비대면 안면 부정교합 진단을 위한 딥 러닝 기반 측면 표식점 탐지 모델
김민준(Minjun Kim),문현준(Hyeonjoon Moon) 대한전기학회 2021 대한전기학회 학술대회 논문집 Vol.2021 No.10
최근 코로나 등 여러 가지 상황으로 인해 원격 및 비대면 서비스들의 급격한 성장이 이루어지고 있다. 그중 의료 서비스에서도 비대면 서비스가 활성화되는 모습을 보이고 있지만 치의학적 진료는 아직 치과 의사에 의해 수동으로 이루어진다. 활발히 이루어지는 정면 표식점 탐지 기술과 달리 비대면 부정교합 진단에 필수적인 요소인 측면 표식점 탐지 연구가 비교적 더디기 때문이다. 이는 시간과 비용을 많이 필요로 하며, 치과마다 다른 주관적인 견해가 들어갈 수 있는 문제를 가지고 있다. 본 논문에서는 이를 해결하기 위해 측면 사진만으로 비대면 안면 부정교합을 진단할 수 있는 기술의 초석인 측면 표식점 데이터셋을 활용한 HRnet 및 GCN 기반 딥 러닝 기반의 측면 표식점 탐지 모델을 제안한다. NME를 측면 표식점 탐지 모델의 평가 지표로 사용하였으며, 20 epoch에서 2.8%의 NME를 보였다.
Robust and Explainable Sewer Crack Detection based on a Transformer
Minh Dang,Kyungbok Min,Hyeonjoon Moon 한국차세대컴퓨팅학회 2021 한국차세대컴퓨팅학회 학술대회 Vol.2021 No.11
Sewer pipes are an essential public infrastructure of countries worldwide. They support wastewater transportation for processing or disposal. The harsh environments inside the sewer pipes can lead to the occurrence of various defects. Current crack detection approaches mainly focus on the surveillance camera (CCTV) to assess the condition of the sewer pipes. This process is considered a tiresome and laborious process. Therefore, a robust and efficient sewer defect detection system based on the transformer architecture is introduced in this manuscript. In addition, the system can provide explainable visualization for its predictions using the transformer's attention.
Arailym Dosset,Muhammad Nadeem,Sukjun Lee,Hyeonjoon Moon 한국차세대컴퓨팅학회 2023 한국차세대컴퓨팅학회 학술대회 Vol.2023 No.06
Quality crop production plays an essential role in the financial stability of every country. Figuring out the damaging parts of plants can be the best way to prevent loss and improve production. Manually monitoring plant diseases is extremely difficult as it requires a significant amount of work, specialized knowledge of plant diseases, and extensive processing time. Therefore, image processing techniques are used for identifying plant diseases. In this paper, we provide a review on different advanced image processing methods using Machine Learning (ML) and Deep Learning (DL) Algorithms. We also discuss the accuracy of ML and DL methods used in previous studies.