• Journal of Korea Multimedia Society
• /
• v.10 no.4
• /
• pp.506-515
• /
• 2007

In this paper, we propose a Real-time Interactive Shadow Avatar(RISA) which can express facial emotions changing as response of user's gestures. The avatar's shape is a virtual Shadow constructed from the real-time sampled picture of user's shape. Several predefined facial animations overlap on the face area of the virtual Shadow, according to the types of hand gestures. We use the background subtraction method to separate the virtual Shadow, and a simplified region-based tracking method is adopted for tracking hand positions and detecting hand gestures. In order to express smooth change of emotions, we use a refined morphing method which uses many more frames in contrast with traditional dynamic emoticons. RISA can be directly applied to the area of interface media arts and we expect the detecting scheme of RISA would be utilized as an alternative media interface for DMB and camera phones which need simple input devices, in the near future.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.6
• /
• pp.1053-1065
• /
• 2020

With the recent development of hardware performance and artificial intelligence technology, sophisticated fake videos that are difficult to distinguish with the human's eye are increasing. Face synthesis technology using artificial intelligence is called Deepfake, and anyone with a little programming skill and deep learning knowledge can produce sophisticated fake videos using Deepfake. A number of indiscriminate fake videos has been increased significantly, which may lead to problems such as privacy violations, fake news and fraud. Therefore, it is necessary to detect fake video clips that cannot be discriminated by a human eyes. Thus, in this paper, we propose a deep-fake detection model applied with Bidirectional Convolution LSTM and Attention Module. Unlike LSTM, which considers only the forward sequential procedure, the model proposed in this paper uses the reverse order procedure. The Attention Module is used with a Convolutional neural network model to use the characteristics of each frame for extraction. Experiments have shown that the model proposed has 93.5% accuracy and AUC is up to 50% higher than the results of pre-existing studies.

• Review of KIISC
• /
• v.27 no.3
• /
• pp.33-41
• /
• 2017

기계 학습(machine-learning) 분야의 분류 알고리즘(classification algorithms)은 의료 진단, 유전자 정보 해석, 스팸 탐지, 얼굴 인식 및 신용 평가와 같은 다양한 응용 서비스에서 사용되고 있다. 이와 같은 응용 서비스에서의 분류 알고리즘은 사용자의 민감한 정보를 포함하는 데이터를 이용하여 학습을 수행하는 경우가 많으며, 분류 결과도 사용자의 프라이버시와 연관된 경우가 많다. 따라서 학습에 필요한 데이터의 소유자, 응용 서비스 사용자, 그리고 서비스 제공자가 서로 다른 보안 도메인에 존재할 경우, 프라이버시 보호 문제가 발생할 수 있다. 본 논문에서는 이러한 문제를 해결하면서도 분류 서비스를 제공할 수 있도록 도와주는 프라이버시 보존 분류 프로토콜(privacy-preserving classification protocol: PPCP) 에 대해 소개한다. 구체적으로 PPCP의 프라이버시 보호 요구사항을 분석하고, 기존의 연구들이 프라이버시 보호를 위해 사용하는 암호학적 기본 도구(cryptographic primitive)들에 대해 소개한다. 최종적으로 그러한 암호학적 기본 도구를 사용하여 설계된 프라이버시 보존 분류 프로토콜에 대한 기존 연구들을 소개하고 분석한다.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.339-340
• /
• 2007

Face detection plays an important role in HCI and face recognition. In this paper, we propose a rotation-invariant real-time face detection algorithm for color images in complex background. It consists of four processing step: (1) motion detection, (2) skin color region filler, (3) Eyemap detector for rotated face, and (4) Adaboost face classifier. This system has been tested in in-door environments, such as office and achieves over 95% detection rate.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.4
• /
• pp.519-525
• /
• 2007

With the high interest on robot technology and application, the research on artificial auditory systems for robot is very active. In this paper we discuss sound source localization and tracing based on audio-visual information. For video signals we use face detection based on skin color model. Also, binaural-based DOA is used as audio information. We integrate both informations using Kalman filter. The experimental results show that audio-visual person tracking Is useful, specially in the case that some informations are not observed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.352-353
• /
• 2018

Many deep learning approaches are studied for face detection in these days. However, there is still a performance problem to run efficiently on devices with limited resources. Our method can enhance the detection speed by decreasing the number of scaling for detection methods that use many different scaling per image to detect the different size of faces. Also, we keep our deep learning model easy to implement and small as possible. Moreover, it can be used for other special object detection problems but not only for face detection.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.97-98
• /
• 2022

코로나바이러스-19 팬데믹 이후 매일 수만 명의 환자가 발생하고 있다. 보건당국은 사람들의 생활 안전을 보호하기 위해 공항, 정류장 등 공공장소에서는 반드시 마스크를 착용하라고 지시하고 있다. 마스크를 착용하는 목적은 감염으로부터 신체를 보호하고 바이러스 전파와 확산을 막기 위한 것이다. 공공장소에서는 많은 인원에 대한 일괄적인 마스크 착용 검사를 하기 어렵고, 육안으로 확인하는 마스크 착용 검사 방법은 인파가 몰리는 장소에서 검사 효율이 떨어지며 누락되는 경우도 많이 발생한다. 본 연구에서는 입력 이미지에 존재하는 얼굴 영역을 YOLOv4와 YOLOv5 모델을 통해 예측하여 마스크의 착용 여부를 판단하되, 앙상블 기법을 적용하여 보다 효과적인 BB(Bounding Box) 추출 및 마스크 착용 탐지 기법을 적용한다. 따라서 공공장소의 마스크 착용실태를 효과적으로 모니터링 할 수 있는 방법을 제안한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.705-708
• /
• 2018

Among biometrics commercialized for security, iris recognition technology has the most excellent security for the probability of the match between individuals is the lowest. Current commercialized iris recognition technology has excellent recognition ability, but this technology has a fatal drawback. Without the user's active cooperation, it cannot recognize the iris correctly. To make up for this weakness, recent trend of iris recognition development mounts a non-volunteering, unconstrained method. According to this information, the objective of this research is developing a module that can identify people iris from a video acquired by high performance infrared camera in a range of 3m and in a involuntary way. For this, we import images from the video and find people's face and eye positions from the images using Haar classifier trained through Cascade training method. finally, we crop the iris by Hough circle transform and compare it with data from the database to identify people.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.333-340
• /
• 2022

The COVID-19 has made everyone anxious and people need to keep their distance. It is necessary to conduct collective assessment and screening of college students' mental health in the opening season of every year. This study uses and trains a multi-layer perceptron neural network model for deep learning to identify facial emotions. After the training, real pictures and videos were input for face detection. After detecting the positions of faces in the samples, emotions were classified, and the predicted emotional results of the samples were sent back and displayed on the pictures. The results show that the accuracy is 93.2% in the test set and 95.57% in practice. The recognition rate of Anger is 95%, Disgust is 97%, Happiness is 96%, Fear is 96%, Sadness is 97%, Surprise is 95%, Neutral is 93%, such efficient emotion recognition can provide objective data support for capturing negative. Deep learning emotion recognition system can cooperate with traditional psychological activities to provide more dimensions of psychological indicators for health.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.6C
• /
• pp.349-354
• /
• 2011

Passive millimeter wave imaging has the capability of detecting concealed objects under clothing. Also, passive millimeter imaging can obtain interpretable images under low visibility conditions like rain, fog, smoke, and dust. However, the image quality is often degraded due to low spatial resolution, low signal level, and low temperature resolution. This paper addresses image registration and fusion between passive millimeter images and visual images. The goal of this study is to combine and visualize two different types of information together: human subject's identity and concealed objects. The image registration process is composed of body boundary detection and an affine transform maximizing cross-correlation coefficients of two edge images. The image fusion process comprises three stages: discrete wavelet transform for image decomposition, a fusion rule for merging the coefficients, and the inverse transform for image synthesis. In the experiments, various types of metallic and non-metallic objects such as a knife, gel or liquid type beauty aids and a phone are detected by passive millimeter wave imaging. The registration and fusion process can visualize the meaningful information from two different types of sensors.