• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1996-1999
• /
• 2003

Stereo matching is an important technique in the are of computer vision. There are already many theorems to find disparity map using stereo images. Usually, disparity is searched by using block matching. However block matching result in blocking effects caused by using fixed size window for computing pixel correlations. This paper suggests an efficient method to remove the blocking effect in stereo matching procedures.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.11a
• /
• pp.55-57
• /
• 2011

본 논문에서는 텍스쳐 최적화 기법을 사용하는 동영상 프레임 비율 상향 변환 방법을 제안한다. 제안하는 기법은 입력 영상의 텍스쳐 특성을 분석하여 블록 매칭에 의해 예측된 움직임 벡터의 정확도를 향상시킨다. 또한 패치 단위의 영상 합성을 통해 블록 경계에서 발생하는 화질 열화 현상을 최소화한다. 실험 결과를 통하여 제안하는 기법은 자연스러운 중간 시점 영상을 생성함을 확인한다.

• Journal of Broadcast Engineering
• /
• v.20 no.2
• /
• pp.257-264
• /
• 2015

In this paper, Enhanced binary block matching method for Constrained one-bit transform (C1BT) based motion estimation is proposed. Binary motion estimation exploits the Number of non-matched points (NNMP) as a block matching criterion instead of the Sum of Absolute Differences (SAD) for low complex motion estimation. The motion estimation using SAD could use the smaller block for more accurate motion estimation. In this paper the enhanced binary block matching method using smaller motion estimation block for C1BT is proposed to the more accurate binary matching. Experimental results shows that the proposed algorithm has better Peak Signal to Noise Ration (PSNR) results compared with conventional binary transform algorithms.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.2 s.40
• /
• pp.159-167
• /
• 2006

Lipreading has been suggested as one of the methods to improve the performance of speech recognition in noisy environment. However, existing methods are developed and implemented only in software. This paper suggests a hardware design for real-time lipreading. For real-time processing and feasible implementation, we decompose the lipreading system into three parts; image acquisition module, feature vector extraction module, and recognition module. Image acquisition module capture input image by using CMOS image sensor. The feature vector extraction module extracts feature vector from the input image by using parallel block matching algorithm. The parallel block matching algorithm is coded and simulated for FPGA circuit. Recognition module uses HMM based recognition algorithm. The recognition algorithm is coded and simulated by using DSP chip. The simulation results show that a real-time lipreading system can be implemented in hardware.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 2004.11a
• /
• pp.117-117
• /
• 2004

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.5
• /
• pp.1119-1128
• /
• 2013

In this paper, we propose an algorithm to detect and track the human face with a GPU-based high speed. Basically the detection algorithm uses the existing Adaboost algorithm but the search area is dramatically reduced by detecting movement and skin color region. Differently from detection process, tracking algorithm uses only depth information. Basically it uses a template matching method such that it searches a matched block to the template. Also, In order to fast track the face, it was computed in parallel using GPU about the template matching. Experimental results show that the GPU speed when compared with the CPU has been increased to up to 49 times.

• Journal of the Institute of Convergence Signal Processing
• /
• v.7 no.4
• /
• pp.155-160
• /
• 2006

This paper presents the hierarchical block matching algorithm using the 4 subbands of the wavelet transformation and the thresholding method. The proposed algorithm improves the PSNR performance of the reconstructed image using the 4 subbands of the wavelet transformation and reduces the computational complexity by thresholding the motion vector. The experimental results of the proposed algorithm for 'Carphone' image and 'Mother and Daughter' image show that if the thresholding value is 0, the computational complexity is increasing up to 16% and the PSNR performance of the reconstructed image improves the 0.16dB in comparison with that of the existing. hierarchical motion estimation algorithm. In addition, as the thresholding value is increasing, the computational complexity reduces up to 8% and the PSNR performance of the reconstructed image is similar.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.357-360
• /
• 2011

모자이크는 여러 개의 작은 영상들을 모아서 하나의 큰 영상을 만드는 것을 말한다. 본 논문에서는 모자이크 방법 중 하나인 사진을 이용하여 영상을 만드는 포토 모자이크 방법을 컴퓨터 알고리즘으로 구현하는 기술 제안을 한다. 이미지를 원하는 사이즈의 타일로 나눈 다음, 나눠진 타일을 16등분을 한다. 16등분된 이미지 각 요소들에 대하여 RGB 평균값을 계산하여 총 48개 특징값을 추출하여 데이터베이스에 저장해둔다. 그리고 타일과 비교가 될 이미지들은 이미 똑같은 작업을 통하여 데이터베이스에 저장이 되어 있다. 이렇게 저장된 값들을 통하여 유클리드 거리를 통하여 두 이미지의 유사도를 측정하게 된다. 최적의 값을 찾으면 바로 대입하는 것이 아니라 이전에 있던 타일 이미지의 명암값을 새로 삽입되는 타일에 부여를 하여, 부드러운 영상을 만들게 된다. 그리고 타일을 삽입할 때 이전에 사용된 이미지는 배열의 마지막으로 옮겨지게 되며 사용횟수를 체크하여 반복적 사용을 제한하였다.

• Journal of KIISE:Information Networking
• /
• v.31 no.3
• /
• pp.298-304
• /
• 2004

In transmitting a compressed video bit-stream over Internet, a packet loss causes an error propagation in both spatial and temporal domain, which in turn leads to a severe degradation in image quality. In this paper, a new error concealment algorithm is proposed to repair damaged portions of the video frames in the receiver. Conventional BMA(Boundary Matching Algorithm) assumes that the pixels on the boundary of the missing block and its neighboring blocks are very similar, but has no consideration of edges t)r discontinuity across the boundary. In our approach, the edges are detected across the boundary of the lost or erroneous block. Once the edges are detected and the orientation of each edge is found, only the pixel difference along the expected edges across the boundary is measured instead of calculating differences between all adjacent pixels on the boundary. Therefore, the proposed approach needs very few computations and the experiment shows an improvement of the performance over the conventional BMA in terms of both subjective and objective quality of video sequences.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.245-247
• /
• 1999

본 논문은 MPEG-2 TM 5 비디오 부호기의 움직임 예측(motion estimation) 처리과정을 소개한다. 비디오에는 공간의 중복성보다 시간의 중복성이 훨씬 많다. 따라서 시간의 중복성을 찾아내는 것이 압축의 효율을 높이는 중요한 척도가 된다. MPEG-2 부호기는 움직임 예측 알고리즘을 사용하여 시간의 중복성을 줄여 압축 효율을 높인다. 움직임 예측은 참조 블록의 위치로부터 원래 블록의 위치를 추정하여 최적의 움직임 벡터를 찾는 과정이다. PMEG-2에서의 움직임 예측은 full search 알고리즘을 사용하여 마지막으로 hlaf pel로 산출한다. 본 논문에서는 MPEG-2 움직임 예측 과정을 frame estimation, field estimation, picture 타입에 따른 estimation, 움직임 예측을 위한 블록 매칭 알고리즘, full search 방법 및 움직임 벡터에 대하여 소개한다.