• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권11호
• /
• pp.5506-5521
• /
• 2017

Three-dimensional video (3DV), as the new generation of video format standard, can provide the viewers with a vivid screen sense and a realistic stereo impression. Meanwhile the view synthesis has become an important issue for 3DV application. Differently from the conventional methods based on depth, in this paper we propose a new view synthesis algorithm, which can employ the correlation among views and warp in the image domain only. There are mainly two contributions. One is the incorporation of sobel edge points into feature extraction and matching, which can obtain a better stable homography and then a visual comfortable synthesis view compared to SIFT points only. The other is a novel image blending method proposed to obtain a better synthesis image. Experimental results demonstrate that the proposed method can improve the synthesis quality both in subjectivity and objectivity.

• Journal of the Optical Society of Korea
• /
• 제17권2호
• /
• pp.148-161
• /
• 2013

We propose one- and two-dimensional reference functions for processing of integral/multiview imaging. The functions provide the synthesis/analysis of the integral image by distance, as an alternative to the composition/decomposition by view images (directions). The synthesized image was observed experimentally. In analysis confirmed by simulation in a qualitative sense, the distance was obtained by convolution of the integral image with the reference functions.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1989년도 한국자동제어학술회의논문집; Seoul, Korea; 27-28 Oct. 1989
• /
• pp.451-456
• /
• 1989

New image coding system for facial images called 'Knowledge-based image coding' is described, in which input image is analyzed and output image is synthesized using analysis results. Analysis and synthesis method of facial expressions are presented. Synthesis rules are determined on the basis of facial muscles and are also used in analysis process to produce a faithful reconstruction of the original image. A number of examples are shown.

• 한국HCI학회논문지
• /
• 제6권1호
• /
• pp.21-26
• /
• 2011

본 논문은 얼굴 영상을 합성할 때 조명 변화에 강인하도록 조명 보정 기법과 푸아송 영상 처리 기법을 결합한 얼굴 합성 방법을 제시한다. 제시된 방법은 얼굴 영상으로부터 자동적으로 피부 영역을 검출하고, 합성할 부위에서 합성 결과에 영향을 주는 세츄레이션된 부분을 보정한 후 최종적으로 대상 얼굴 영상에 합성하게 된다. 개발된 방법은 카메라가 부착된 모바일 기기에서 촬영된 영상 등에서 자주 발생할 수 있는 조명변화를 보완하여 다양한 얼굴합성 응용 분야에 활용될 수 있다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2007년도 하계종합학술대회 논문집
• /
• pp.355-356
• /
• 2007

This paper proposes a new panoramic image synthesis method using flash and no-flash image pairs, which reduces undesirable artifacts. Generally, in panoramic images, it is difficult to determine to use a flash in indoor environment. A flash image has unwanted artifacts such as hot spots and tunnel effect whereas a no-flash image also has artifacts like glass reflection. We derive cross projection tensors using flash and no-flash image pairs and transform the gradient field of a no-flash image using them. The image reconstructed from the modified gradient provides enhanced results, which are applied to synthesis of panoramic images. The proposed method can provide a better panoramic image than the conventional method. Experimental results show the effectiveness of the proposed method.

• 전자공학회논문지S
• /
• 제35S권7호
• /
• 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.

• 인터넷정보학회논문지
• /
• 제7권2호
• /
• pp.1-8
• /
• 2006

본 논문은 포스트프로덕션부분에 해당되는 실무적인 영상제작 작업과정중의 하나로 효과적인 합성 기법에 대해 연구하였다. 영상합성의 전체적인 흐름을 인식하지 못하고 구체적인 합성방식에 대한 다양성과 복잡성에 대한 연구가 미비한 상태이다. 그러므로 영상의 흐름을 이해 할 수 있는 전체적인 패턴을 형상화하고 규격화의 필요성이 요구된다. 따라서 실제로 구현해 보기 위해서는 리소스라는 형식으로 자료화하여 작업의 효율성과 편이성을 높이는 것이 바람직 할 것이다. 영상작업을 하는데 있어 매트, 키, 모션, 스케일, 포지션, 불투명도(opacity)등등과 같은 여러 가지 속성 값들을 그래픽 이미지로 제시함으로써 이전에 개인의 몫으로 주어졌던 영상합성시의 어려움을 해결할 수 있는 방향을 제시하고 구체적인 사례들을 통해 입증하였다.

• Journal of information and communication convergence engineering
• /
• 제9권2호
• /
• pp.197-200
• /
• 2011

In this paper, we propose a multi-view stereoscopic image synthesis algorithm for 3DTV system using depth information with an RGB texture from a depth camera. The proposed algorithm synthesizes multi-view images which a virtual convergence camera model could generate. Experimental results showed that the performance of the proposed algorithm is better than those of conventional methods.

• 한국군사과학기술학회지
• /
• 제16권2호
• /
• pp.207-213
• /
• 2013

An infrared image synthetic method is proposed for infrared system simulation. The synthesis image uses a background IR image captured from real scene and a target IR modeling image. The radiances related with maximum and minimum temperatures of the background and target images are calculated from the Planck's blackbody equation. Based on them, the background and target images are compensated and synthesized. The proposed method is simulated and the IR target images are generated by RadThermIR software.

• 한국자동차공학회논문집
• /
• 제24권6호
• /
• pp.627-634
• /
• 2016

In this paper, an augmented video generation method to evaluate the performance of lane departure warning system is proposed. In our system, the input is a video which have road scene with general clean lane, and the content of output video is the same but the lane is synthesized with contamination image. In order to synthesize the contamination lane image, two approaches were used. One is example-based image synthesis, and the other is background-based image synthesis. Example-based image synthesis is generated in the assumption of the situation that contamination is applied to the lane, and background-based image synthesis is for the situation that the lane is erased due to aging. In this paper, a new contamination pattern generation method using Gaussian function is also proposed in order to produce contamination with various shape and size. The contamination lane video can be generated by shifting synthesized image as lane movement amount obtained empirically. Our experiment showed that the similarity between the generated contamination lane image and real lane image is over 90 %. Futhermore, we can verify the reliability of the video generated from the proposed method through the analysis of the change of lane recognition rate. In other words, the recognition rate based on the video generated from the proposed method is very similar to that of the real contamination lane video.