• Journal of the Korea Computer Graphics Society
• /
• v.21 no.5
• /
• pp.37-44
• /
• 2015

This paper presents a novel 3D model representation, called hybrid model representation, to overcome existing 3D volume-based indoor scene reconstruction mechanism. In indoor 3D scene reconstruction, volume-based model representation can reconstruct detailed 3D model for the narrow scene. However it cannot reconstruct large-scale indoor scene due to its memory consumption. This paper presents a memory efficient plane-hash model representation to enlarge the scalability of the indoor scene reconstruction. Also, the proposed method uses plane-hash model representation to reconstruct large, structural planar objects, and at the same time it uses volume-based model representation to recover small detailed region. Proposed method can be implemented in GPU to accelerate the computation and reconstruct the indoor scene in real-time.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.241-247
• /
• 2007

자궁 경부 세포진 영상의 핵 추출을 위해서는 영상의 배경과 핵 그리고 세포질 영역의 구분이 중요하다. 또한 정상 세포핵과 암종 세포핵의 구분 및 인식을 위해서는 세포핵들의 형태학적 특징을 이용한 분류 기준을 세워야한다. 본 논문에서는 자궁 경부 세포진 영상에서 세포핵의 후보 영역과 핵을 추출하기 위해 현미경 400배율 확대 사진을 획득하는 과정에서 훼손된 컬러 영상을 복원하기 위한 방법으로 Lighting Compensation을 적용하여 영상을 보정한다. 그리고 배경 영역과 세포핵 영역을 구분하기 위해 영상의 R,G,B 영역의 히스토그램의 분포를 이용하여 배경을 제거한다. 배경이 제거된 영상을 그레이 영상으로 변환 한 후, 히스토그램 명암도의 값을 이용하여 세포핵 영역과 세포질을 분류하여 세포핵 영역을 추출한다. 그리고 Kapur 방법을 적용하여 세포핵 영역의 엔트로피 누적확률을 구한 후, 영상을 이진화 한다. Kapur 방법이 적용된 이진화 영상에서 세포핵 영역의 중심과 주위 화소를 비교하는 $3\times3$ 마스크를 적용하여 영상의 미세한 잡음을 제거 한 후, 8방향 윤곽선 추적 알고리즘을 적용하여 최종적으로 세포핵 영역을 추출한다. 추출된 세포핵의 영역을 분류 및 인식하는 과정으로 세포의 외각의 방향성 정보, 핵의 크기, 그리고 면적 비율의 특징을 이용하여 퍼지 소속 함수를 설계한 후, 소속 함수의 소속도를 구하고 퍼지 추론 규칙을 적용하여 자궁 경부 세포진 영상에서 정상 세포핵 및 암종 세포핵을 인식한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.205-207
• /
• 2020

This paper proposes a novel deep learning-based method to upsample a depth map. Most conventional methods estimate high-resolution depth map by modifying pixel value of given depth map using high-resolution color image and low-resolution depth map. However, these methods cause under- or over-shooting problems that restrict performance improvement. To overcome these problems, the proposed method iteratively performs grid warping scheme which shifts pixel values to restore blurred image for estimating high-resolution depth map. Experimental results show that the proposed method improves both quantitative and visual quality compared to the existing method.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.5
• /
• pp.645-652
• /
• 2015

In underwater, such as fish farm and sea, turbidity is increased by water droplets and various suspended, therefore light attenuation occurs depending on the depth also caused by the scattering effect of light float. In this paper, in order to improve the visibility of underwater images obtained from these aquatic environment, we propose a visibility enhancement method using a haze removal method based on dark channel prior and a trained color transform model. In order to train a color transform model, we used underwater pattern images captured from Pohang and Yeosu, and to measure the performance of the proposed method, we carried out experiment of visibility enhancement using underwater images collected from Yeosu, Geomundo and Philippines. The results show that the proposed method can improve the visibility of underwater images of various locations.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.1
• /
• pp.44-49
• /
• 2016

This paper proposed the method to improve performance of a pixel, which has low accuracy, by applying image segmentation methods based on color and multi-threshold of brightness. Stereo matching is the process to find the corresponding point on the right image with the point on the left image. For this process, distance(depth) information in stereo images is calculated. However, in the case of a region which has textureless, stereo matching has low accuracy and bad pixels occur on the disparity map. In the proposed method, the relationship between adjacent pixels is considered for compensating bad pixels. Generally, the object has similar color and brightness. Therefore, by considering the relationship between regions based on segmented regions by means of color and multi-threshold of brightness respectively, the region which is considered as parts of same object is re-segmented. According to relationship information of segmented sets of pixels, bad pixels in the disparity map are compensated efficiently. By applying the proposed method, the results show a decrease of nearly 28% in the number of bad pixels of the image applied the method which is established.

• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.837-841
• /
• 2007

최근 영상을 중심으로 여러 형태의 정보를 결합하여 저장하거나 전송하는 멀티미디어가 많은 관심을 받고 있다. 현재 카메라와 관련된 동영상 캡처기술은 Motion JPEG이 주류를 이루고 있으며, 텔레비전, DMB 등의 방송 분야 및 DVD, VCR 분야에서는 MPEG-2, MPEG-4, H.264 및 WMV9 등의 압축 코덱이 채용되고 사용되고 있다. 그러나 이러한 다양한 영상 표준방식은 디코딩시 호환성 문제가 발생하게 되고 이에 따라 통합 코덱 연구가 필요하다. 이에 본 논문은 일반적 스텝 양자화외에 데드존 양자화를 사용하고 "$4{\times}4$", "$4{\times}8$", "$8{\times}4$", "$8{\times}8$"의 다양한 블록크기의 변환을 지원하는 VC-1을 기반으로 한 ITIQ C언어를 통해 시뮬레이션하고 최적화된 결과를 VHDL로 구현하여 향후 통합코덱 연구에 응용 가능하도록 연구 및 분석평가 하였다. 설계결과 4:2:0의 YCbCr포맷의 최초 $16{\times}16$블록을 복원하는데 483~510클록이 소요되었고 Xilinx XCVPC100 FF1696-6 환경에서 93,128개의 게이트 수와 71.469MHz의 동작속도를 나타내었다. 이는 640*480 크기의 컬러영상을 디코딩 하는데 프레임 당 최대 0.0074초가 소요됨을 의미하며 초당 30프레임의 영상에서도 0.222초면 디코딩이 가능한 결과이다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.6
• /
• pp.1398-1415
• /
• 1996

Instead of using three charge-coupled devices (CCDs) for the corresponding color channels, most consumer's most consummer's color macmorders reconstruct color images by using only one CCD with a color filter array (CFA), which periodically samples different color signals. By this reson the resulting image cannot produce the full resolution of the input image. More sepecifically, a single-CCD color camcorder reconstructs red, greed, and blue color channels from a color filter array followed by a CCD. During the reconstruction process, color cross-talk among channels (interchannel distortion) and eriodically space-verying blur (intrachannel distortion) occur. The proposed restoration system reduces distortions due to interchannel interference, and then restores each color channel by removing the corresponding intrachannel distortion. Experimental results show that the proposedsystem provides the improved image in oth objective and subjective senses. A major advantage of the proposed system is feasible to real-time image improvement because it can be implemented by a finite impulse response (FIR) filter structure.

• Spatial Information Research
• /
• v.14 no.1 s.36
• /
• pp.85-94
• /
• 2006

Image fusion techniques are widely used to integrate a lower spatial resolution multispectral image with a higher spatial resolution panchromatic image. However, the existing techniques either cannot avoid distorting the image spectral properties or involve complicated and time-consuming decomposition and reconstruction processing in the case of wavelet transform-based fusion. In this study a simple spectral preserve fusion technique: the Smoothing Filter-based Replacement(SFR) is proposed based on a simplified solar radiation and land surface reflection model. By using a ratio between a higher resolution image and its low pass filtered (with a smoothing filter) image, spatial details can be injected to a co-registered lower resolution multispectral image minimizing its spectral properties and contrast. The technique can be applied to improve spatial resolution for either colour composites or individual bands. The fidelity to spectral property and the spatial quality of SFM are convincingly demonstrated by an image fusion experiment using IKONOS panchromatic and multispectral images. The visual evaluation and statistical analysis compared with other image fusion techniques confirmed that SFR is a better fusion technique for preserving spectral information.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.3
• /
• pp.179-187
• /
• 2008

In this paper, we apply a set of algorithms to classily normal and cancer nucleus from uterine cervical pap-smear images. First, we use lightening compensation algorithm to restore color images that have defamation through the process of obtaining $1{\times}400$ microscope magnification. Then, we remove the background from images with the histogram distributions of RGB regions. We extract nucleus areas from candidates by applying histogram brightness, Kapur method, and our own 8-direction contour tracing algorithm. Various binarization, cumulative entropy, masking algorithms are used in that process. Then, we are able to recognize normal and cancer nucleus from those areas by using three morphological features - directional information, the size of nucleus, and area ratio - with fuzzy membership functions and deciding rules we devised. The experimental result shows our method has low false recognition rate.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.1
• /
• pp.15-31
• /
• 2013

This paper proposes an intermediate image generation method for the viewer's view point by tracking the viewer's face, which is converted to a digital hologram. Its purpose is to increase the viewing angle of a digital hologram, which is gathering higher and higher interest these days. The method assumes that the image information for the leftmost and the rightmost view points within the viewing angle to be controlled are given. It uses a stereo-matching method between the leftmost and the rightmost depth images to obtain the pseudo-disparity increment per depth value. With this increment, the positional informations from both the leftmost view point and the rightmost view point are generated, which are blended to get the information at the wanted intermediate viewpoint. The occurrable dis-occlusion region in this case is defined and a inpainting method is proposed. The results from implementing and experimenting this method showed that the average image qualities of the generated depth and RGB image were 33.83[dB] and 29.5[dB], respectively, and the average execution time was 250[ms] per frame. Also, we propose a prototype system to service digital hologram interactively to the viewer by using the proposed intermediate view generation method. It includes the operations of data acquisition for the leftmost and the rightmost viewpoints, camera calibration and image rectification, intermediate view image generation, computer-generated hologram (CGH) generation, and reconstruction of the hologram image. This system is implemented in the LabView(R) environments, in which CGH generation and hologram image reconstruction are implemented with GPGPUs, while others are implemented in software. The implemented system showed the execution speed to process about 5 frames per second.