• Korean Journal of Optics and Photonics
• /
• v.14 no.4
• /
• pp.383-391
• /
• 2003

A new optical security system for the protection of personal identification information is proposed. Personal identification information consisting of a pure face image and an identification number is used for verification and authentication. Image encryption is performed by a fully phase image encryption technique with two random phase masks located in the input and the Fourier plane of 4-f correlator. The personal information, however, can be leaked out in the decryption process. To cope with this possibility, the encrypted image itself is used in the identification process. An encrypted personal identification number is discriminated and recognized by using the proposed MMACE_p (multiplexed MACE_p) filter, and then authenticity of the personal information is verified by correlation of the face image using the optical wavelet matched filter (OWMF). MMACE_p filter is a synthetic filter with four MACE_p (minimum average correlation energy_phase encrypted) filters multiplexed in one filter plane to recognize 10 different encrypted-numbers at a time. OWMF can improve discrimination capability and SNR (signal to noise ratio). Computer simulations confirmed that the proposed security technique can be applied to the protection of personal identification information.

• Journal of the Korea Computer Graphics Society
• /
• v.21 no.3
• /
• pp.55-61
• /
• 2015

In this paper, we introduce a method to synthesize realistic make-up effects on input images efficiently. In particular, we focus on shading on the make-up effects due to the lighting and face curvature. By doing this, we can synthesize a wider range of effects realistically than the previous methods. To do this, the information about lighting information together with the normal vectors on all pixels over the face region in the input image. Since the previous methods that compute lighting information and normal vectors require relatively heavy computation cost, we introduce an approach to approximate lighting information using cascade pose regression process and normal vectors by transforming, rendering, and warping a standard 3D face model. The proposed method consumes much less computation time than the previous methods. In our experiment, we show the proposed approximation technique can produce naturally looking virtual make-up effects.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.1
• /
• pp.67-74
• /
• 2023

The images acquired from the speaker's mouth region revealed the unique patterns according to the corresponding voices. By using this principle, the several methods were proposed in which speech signals were recognized or synthesized from the images acquired at the speaker's lower face. In this study, an image-based speech synthesis method was proposed in which the depth images were cooperatively used. Since depth images yielded depth information that cannot be acquired from optical image, it can be used for the purpose of supplementing flat optical images. In this paper, the usefulness of depth images from the perspective of speech synthesis was evaluated. The validation experiment was carried out on 60 Korean isolated words, it was confirmed that the performance in terms of both subjective and objective evaluation was comparable to the optical image-based method. When the two images were used in combination, performance improvements were observed compared with when each image was used alone.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.55-58
• /
• 2024

최근 각 기업의 AI 면접시스템 도입이 증가하고 있으며, AI 면접에 대한 실효성 논란 또한 많은 상황이다. 본 논문에서는 AI 면접 과정에서 지원자를 평가하는 방식을 시각, 음성, 자연어처리 3영역에서 구현함으로써, 면접 지원자를 다방면으로 분석 방법론의 적절성에 대해 평가하고자 한다. 첫째, 시각적 측면에서, 면접 지원자의 감정을 인식하기 위해, 합성곱 신경망(CNN) 기법을 활용해, 지원자 얼굴에서 6가지 감정을 인식했으며, 지원자가 카메라를 응시하고 있는지를 시계열로 도출하였다. 이를 통해 지원자가 면접에 임하는 태도와 특히 얼굴에서 드러나는 감정을 분석하는 데 주력했다. 둘째, 시각적 효과만으로 면접자의 태도를 파악하는 데 한계가 있기 때문에, 지원자 음성을 주파수로 환산해 특성을 추출하고, Bidirectional LSTM을 활용해 훈련해 지원자 음성에 따른 6가지 감정을 추출했다. 셋째, 지원자의 발언 내용과 관련해 맥락적 의미를 파악해 지원자의 상태를 파악하기 위해, 음성을 STT(Speech-to-Text) 기법을 이용하여 텍스트로 변환하고, 사용 단어의 빈도를 분석하여 지원자의 언어 습관을 파악했다. 이와 함께, 지원자의 발언 내용에 대한 감정 분석을 위해 KoBERT 모델을 적용했으며, 지원자의 성격, 태도, 직무에 대한 이해도를 파악하기 위해 객관적인 평가지표를 제작하여 적용했다. 논문의 분석 결과 AI 면접의 다면적 평가시스템의 적절성과 관련해, 시각화 부분에서는 상당 부분 정확도가 객관적으로 입증되었다고 판단된다. 음성에서 감정분석 분야는 면접자가 제한된 시간에 모든 유형의 감정을 드러내지 않고, 또 유사한 톤의 말이 진행되다 보니 특정 감정을 나타내는 주파수가 다소 집중되는 현상이 나타났다. 마지막으로 자연어처리 영역은 면접자의 발언에서 나오는 말투, 특정 단어의 빈도수를 넘어, 전체적인 맥락과 느낌을 이해할 수 있는 자연어처리 분석모델의 필요성이 더욱 커졌음을 판단했다.

• Korean Journal of Cognitive Science
• /
• v.14 no.1
• /
• pp.41-50
• /
• 2003

We tested the capability of the pleasure and arousal dimension-based facial expression synthesis system and proposed the most effective interface for it. First, we tried to confirm the adequateness of the dimensional model as a basic structure of the internal states for the system. Fer it, subjects compared the 17 facial expressions on the two axes. The results validated the fundamental hypothesis of the system. Second, we chose 21 representative expressions from the system to test its performance and had subjects rate their similarities. We analyzed these data using multidimensional scaling methods and these results verified the system's reliability. Third, we compared the efficiencies of two interfaces -coordinate values and slide bars- to find the most suitable interface for the system. Subjects synthesise 25 facial expressions with each interface of it. The results showed that the visualization of two dimensional values into Cartesian coordinate is more stable as an input display of facial expression synthesis system based on dimensions.

• Journal of the Korean Society for Library and Information Science
• /
• v.50 no.1
• /
• pp.417-435
• /
• 2016

Relevance judgment is important in terms of improving the effectiveness of information retrieval systems, and it has been dominant for users to search and use images utilizing internet and digital technologies. However, in the field of image retrieval, there have been only a few studies in terms of identifying relevance criteria. The purpose of this study aims to identify and characterize the non-relevance criteria from the failed image searches. In order to achieve the purpose of this study, a total of 135 participants were recruited and a total of 1,452 criteria items were collected for this study. Analyses and identification on the data set found thirteen criteria such as 'topicality', 'visual content', 'accuracy', 'visual feature', 'completeness', 'appeal to user', 'focal point', 'bibliographic information', 'impression', 'posture', 'face feature', 'novelty', and 'time frame'. Among these criteria, 'visual content' and 'focal point' were introduced in this current study, while 'action' criterion identified in previous studies was not shown in this current study. When image needs and image uses are analyzed with these criteria, there are distinctive differences depending on different image needs and uses.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.7
• /
• pp.95-102
• /
• 1998

This paper proposes a synchronization method of synthetic facial iamge sequences and synthetic speech. The LP-PSOLA synthesizes the speech for each demi-syllable. We provide the 3,040 demi-syllables for unlimited synthesis of the Korean speech. For synthesis of the Facial image sequences, the paper defines the total 11 fundermental patterns for the lip shapes of the Korean consonants and vowels. The fundermental lip shapes allow us to pronounce all Korean sentences. Image synthesis method assigns the fundermental lip shapes to the key frames according to the initial, the middle and the final sound of each syllable in korean input text. The method interpolates the naturally changing lip shapes in inbetween frames. The number of the inbetween frames is estimated from the duration time of each syllable of the synthetic speech. The estimation accomplishes synchronization of the facial image sequences and speech. In speech synthesis, disk memory is required to store 3,040 demi-syllable. In synthesis of the facial image sequences, however, the disk memory is required to store only one image, because all frames are synthesized from the neutral face. Above method realizes synchronization of system which can real the Korean sentences with the synthetic speech and the synthetic facial iage sequences.

• 한국HCI학회:학술대회논문집
• /
• 2006.02b
• /
• pp.362-369
• /
• 2006

3 차원 그래픽스에 적용하는 한국어 립씽크 합성 체계를 연구하여, 말소리에 대응하는 자연스러운 립씽크를 자동적으로 생성하도록 하는 디자인 시스템을 연구 개발하였다. 페이셜애니메이션은 크게 나누어 감정 표현, 즉 표정의 애니메이션과 대화 시 입술 모양의 변화를 중심으로 하는 대화 애니메이션 부분으로 구분할 수 있다. 표정 애니메이션의 경우 약간의 문화적 차이를 제외한다면 거의 세계 공통의 보편적인 요소들로 이루어지는 반면 대화 애니메이션의 경우는 언어에 따른 차이를 고려해야 한다. 이와 같은 문제로 인해 영어권 및 일본어 권에서 제안되는 음성에 따른 립싱크 합성방법을 한국어에 그대로 적용하면 청각 정보와 시각 정보의 부조화로 인해 지각의 왜곡을 일으킬 수 있다. 본 연구에서는 이와 같은 문제점을 해결하기 위해 표기된 텍스트를 한국어 발음열로 변환, HMM 알고리듬을 이용한 입력 음성의 시분할, 한국어 음소에 따른 얼굴특징점의 3 차원 움직임을 정의하는 과정을 거쳐 텍스트와 음성를 통해 3 차원 대화 애니메이션을 생성하는 한국어 립싱크합성 시스템을 개발 실제 캐릭터 디자인과정에 적용하도록 하였다. 또한 본 연구는 즉시 적용이 가능한 3 차원 캐릭터 애니메이션뿐만 아니라 아바타를 활용한 동적 인터페이스의 요소기술로서 사용될 수 있는 선행연구이기도 하다. 즉 3 차원 그래픽스 기술을 활용하는 영상디자인 분야와 HCI 에 적용할 수 있는 양면적 특성을 지니고 있다. 휴먼 커뮤니케이션은 언어적 대화 커뮤니케이션과 시각적 표정 커뮤니케이션으로 이루어진다. 즉 페이셜애니메이션의 적용은 보다 인간적인 휴먼 커뮤니케이션의 양상을 지니고 있다. 결국 인간적인 상호작용성이 강조되고, 보다 편한 인간적 대화 방식의 휴먼 인터페이스로 그 미래적 양상이 변화할 것으로 예측되는 아바타를 활용한 인터페이스 디자인과 가상현실 분야에 보다 폭넓게 활용될 수 있다.

• 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.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.173-178
• /
• 2022

Recently, various computing technologies such as artificial intelligence, big data, and IoT are developing. In particular, artificial intelligence-based deepfake technology is being used in various fields such as the content and medical industry. Deepfake technology is a combination of deep learning and fake, and is a technology that synthesizes a person's face or body through deep learning, which is a core technology of AI, to imitate accents and voices. This paper uses deepfake technology to study the creation of virtual characters through the synthesis of animation models and real person photos. Through this, it is possible to minimize various cost losses occurring in the animation production process and support writers' work. In addition, as deepfake open source spreads on the Internet, many problems emerge, and crimes that abuse deepfake technology are prevalent. Through this study, we propose a new perspective on this technology by applying the deepfake technology to children's material rather than adult material.