• Proceedings of the KIEE Conference
• /
• 1990.11a
• /
• pp.460-464
• /
• 1990

Texture provides an important source of information about the local orientation of visible surfaces. An important task that arises in many computer vision systems is the reconstruction of three-dimensional depth information from two-dimensional images. The surface orientation of texel is classified by the Artificial Neural Network. The classification method to recognize the shape of 3D object with artificial neural network requires less developing time comparing to conventional method. The segmentation problem is assumed to be solved. The surface in view is smooth and is covered with repeated texture elements. In this study, 3D shape reconstruct using interpolation method.

• Proceedings of the KSME Conference
• /
• 2001.06c
• /
• pp.482-484
• /
• 2001

In orthopedics, hip arthroplasty is the operation that replaces damaged hip joint to artificial joint. In hip arthroplasty, quite better result can be achieved if robot is applied to machine cavity in bone, especially when cementless stem is used. So several kinds of robots were introduced for hip arthroplasty, but they used MRI, CT Scan, vision analysis and real time tracking of bone position for registration of robot. To overcome shortage of conventional robot surgery, gauge based registration method was proposed and small robot was designed. In this method, small robot is mounted on femur, and its position is determined by gauge registration method. Operation procedure was performed on model femur and result was analyzed. This robotic hip surgery system is expected to more adaptable in operation room.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.3
• /
• pp.81-87
• /
• 2007

It is important to investigate the relationship between weld process parameters and weld bead geometry for adaptive arc robot welding. However, it is difficult to predict an exact back-bead owing to gap in process of butt welding. In this paper, the quantitative prediction system to specify the relationship external weld conditions and weld bead geometry was developed to get suitable back-bead in butt welding which is widely applied on industrial field. Multiple regression analysis and artificial neural network were used as the research methods. And, the results of two prediction methods were compared and analyzed.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.3
• /
• pp.255-263
• /
• 2006

In the last decade, face analysis, e.g. face detection, face recognition, facial expression recognition, is a very lively and expanding research field. As computer animated agents and robots bring a social dimension to human computer interaction, interest in this research field is increasing rapidly. In this paper, we introduce an artificial emotion mimic system which can recognize human facial expressions and also generate the recognized facial expression. In order to recognize human facial expression in real-time, we propose a facial expression classification method that is performed by weak classifiers obtained by using new rectangular feature types. In addition, we make the artificial facial expression using the developed robotic system based on biological observation. Finally, experimental results of facial expression recognition and generation are shown for the validity of our robotic system.

• Electronics and Telecommunications Trends
• /
• v.36 no.1
• /
• pp.12-21
• /
• 2021

This article presents the future vision and core technologies of the "Life Companion Robot," which is one of the 12 future concepts introduced in the ETRI Technology Roadmap published in November 2020. Assistant robots, care robots, and life support robots were proposed as the development stages of life companion robots. Further, core technologies for each of the ten major roles that must be directly or indirectly performed by life companion robots are introduced. Finally, this article describes in detail three major artificial intelligence technologies for autonomous robots.

• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.453-461
• /
• 2021

Many deep learning approaches have been studied for image classification in computer vision. However, there are not enough data to generate accurate models in medical fields, and many datasets are not annotated. This study presents a new method that can use both unlabeled and labeled data. The proposed method is applied to classify cervix images into normal versus cancerous, and we demonstrate the results. First, we use a patch self-supervised learning for training the global context of the image using an unlabeled image dataset. Second, we generate a classifier model by using the transferred knowledge from self-supervised learning. We also apply attention learning to capture the local features of the image. The combined method provides better performance than state-of-the-art approaches in accuracy and sensitivity.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.35 no.3
• /
• pp.215-222
• /
• 2022

Artificial neuromorphic devices are considered the key component in realizing energy-efficient and brain-inspired computing systems. For the artificial neuromorphic devices, various material candidates and device architectures have been reported, including two-dimensional materials, metal-oxide semiconductors, organic semiconductors, and halide perovskite materials. In addition to conventional electrical neuromorphic devices, optoelectronic neuromorphic devices, which operate under a light stimulus, have received significant interest due to their potential advantages such as low power consumption, parallel processing, and high bandwidth. This article reviews the recent progress in optoelectronic neuromorphic devices using various active materials such as two-dimensional materials, metal-oxide semiconductors, organic semiconductors, and halide perovskites

• Electronics and Telecommunications Trends
• /
• v.37 no.4
• /
• pp.60-69
• /
• 2022

So far, artificial intelligence (AI)/machine learning (ML) has produced impressive results in speech recognition, computer vision, and natural language processing. AI/ML has recently begun to show promise as a viable means for improving the performance of 5G mobile telecommunication systems. This paper investigates standardization activities in 3GPP and O-RAN Alliance regarding AI/ML applications on mobile telecommunication system. Future trends in AI/ML technologies are also summarized. As an overarching technology in 6G, there appears to be no doubt that AI/ML could contribute to every part of mobile systems, including core, RAN, and air-interface, in terms of performance enhancement, automation, cost reduction, and energy consumption reduction.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.417-419
• /
• 2022

감각대체기술은 손상된 감각 정보를 다른 감각으로 전환하여 전달하는 기술로써 기존의 시각장애인을 위한 시각 정보의 촉각 대체 기술은 주로 거리 정보나 물체의 윤곽선 정보를 전달하여 사용자가 주변 환경을 이해하는 데 어려움이 있었다. 이를 해결하기 위해 본 논문에서는 딥러닝을 사용하여 사용자 주변의 모션 정보를 분석하고, 이를 촉각 정보로 전달함으로써 사용자가 주변 상황 정보를 인지 할 수 있는 방법을 제안하였다. 제안 방법과 기존의 윤곽선 정보 전달 방법을 사용자 실험을 통하여 비교하였을 때, 제안 방법이 영상 속 물체의 움직임 정보를 이해하는 데에 더욱 효과적임을 확인하였다.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.615-618
• /
• 2023

최근 computer vision 기술 발달이 가속화되고 있으나, 특정 산업의 경우 산업 적용의 어려움과 데이터적 특성으로 인하여 기술 발전의 속도를 따라가지 못하고 있다. 특히, CCTV 는 대부분 실외 환경에 운영되어 다양한 환경의 변화 및 데이터 고유 특성상 노이즈가 많기 때문에 데이터 산포가 커서 기술의 현장 적용에 어려움이 있다. 본 논문에서는 CCTV 데이터의 특성을 고려하여 CCTV 운용 환경에 강건한 객체탐지(object detector) 학습을 위한 데이터 설계 방안을 제안한다. 제안 기법은 대용량의 CCTV 영상에서 객체탐지에 효과적인 샘플링을 유도하는 방안과 소수의 CCTV 레이블 데이터 외 MS COCO 등 다수 오픈 레이블 데이터를 혼합학습 하여 일반화 성능을 높이는 방안을 제안한다. 다수의 실험을 통해 제안 기법의 우수성을 입증하였으며, 특히 mAP 기준 13.39%의 성능 향상을 꾀할 수 있음을 선보였다.