• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1995년도 춘계학술대회
• /
• pp.123-126
• /
• 1995

The purpose of this paper is to improve ultrasound images using motion estimation and recursive filtering. Although averaging without motion correction can make image blurring, the proposed estimation method improves image SNR without motion blurring by recursively averaging images with motion correction. Computer simulation on the proposed method has been performed to improve phantom and ultrasound fish images and the results show the utility of the proposed method.

• Journal of the Optical Society of Korea
• /
• 제18권4호
• /
• pp.414-418
• /
• 2014

In this paper, we present a method to detect the position of a 3D object in scattering media by using the axially distributed sensing (ADS) method. Due to the scattering noise of the elemental images recorded by the ADS method, we apply a statistical image processing algorithm where the scattering elemental images are converted into scatter-reduced ones. With the scatter-reduced elemental images, we reconstruct the 3D images using the digital reconstruction algorithm based on ray back-projection. The reconstructed images are used for the position detection of a 3D object in the scattering medium. We perform the preliminary experiments and present experimental results.

• 한국멀티미디어학회논문지
• /
• 제18권1호
• /
• pp.17-24
• /
• 2015

In this paper, a novel scheme for correcting rotated region in medical images using SIFT(Scale Invariant Feature Transform) algorithm is presented. Using the feature extraction function of SIFT, the rotation angle of rotated object in medical images is calculated as follows. First, keypoints of both reference and rotated medical images are extracted by SIFT. Second, the matching process is performed to the keypoints located at the predetermined ROI(Region Of Interest) at which objects are not cropped or added by rotating the image. Finally, degrees of matched keypoints are calculated and the rotation angle of the rotated object is determined by averaging the difference of the degrees. The simulation results show that the proposed scheme has excellent performance for correcting the rotated region in medical images.

• Journal of the Optical Society of Korea
• /
• 제16권4호
• /
• pp.365-371
• /
• 2012

A three-dimensional integral-floating display with 360 degree horizontal viewing angle is proposed. A lens array integrates two-dimensional elemental images projected by a digital micro-mirror device, reconstructing three-dimensional images. The three-dimensional images are then relayed to a mirror via double floating lenses. The mirror rotates in synchronization with the digital micro-mirror device to direct the relayed three-dimensional images to corresponding horizontal directions. By combining integral imaging and the rotating mirror scheme, the proposed method displays full-parallax three-dimensional images with 360 degree horizontal viewing angle.

• 반도체디스플레이기술학회지
• /
• 제23권2호
• /
• pp.23-27
• /
• 2024

Underwater images are typically degraded due to color distortion, light absorption, scattering, and noise from artificial light sources. Restoration of these images is an essential task in many underwater applications. In this paper, we propose a two-phase deep learning-based method, Underwater Deep Curve Estimation (UWDCE), designed to effectively enhance the quality of underwater images. The first phase involves a white balancing and color correction technique to compensate for color imbalances. The second phase introduces a novel deep learning model, UWDCE, to learn the mapping between the color-corrected image and its best-fitting curve parameter maps. The model operates iteratively, applying light-enhancement curves to achieve better contrast and maintain pixel values within a normalized range. The results demonstrate the effectiveness of our method, producing higher-quality images compared to state-of-the-art methods.

• 한국ITS학회 논문지
• /
• 제20권4호
• /
• pp.95-105
• /
• 2021

도로 노면 파손 탐지는 쾌적한 주행 환경과 안전사고의 예방을 위해 필요하다. 도로 관리 기관은 자동화 기술 기반의 검사 장비와 시스템을 활용하고 있다. 이러한 자동화 기술 중에서도 도로 노면의 파손을 탐지하는 기술은 중요한 역할을 수행한다. 최근 들어 딥러닝을 이용한 기술에 대한 연구가 활발하게 진행 중이다. 이러한 딥러닝 기술 개발을 위해서는 도로 영상과 라벨 영상이 필요하다. 하지만 라벨 영상을 확보하기 위해서는 많은 시간과 노동력이 요구된다. 본 논문에서는 이러한 문제를 해결하기 위하여 준지도 학습 기법 중 하나인 적대적 학습 방법을 제안했다. 이를 구현하기 위해서 5,327장의 도로 영상과 1,327장의 라벨 영상을 사용하여 경량화 심층 신경망 모델을 학습했다. 그리고 이를 400장의 도로 영상으로 실험한 결과 80.54%의 mean intersection over union과 77.85%의 F1 score를 갖는 모델을 개발하였다. 결과적으로 라벨 영상 없이 도로 영상만을 학습에 추가하여 인식 성능을 향상시킬 수 있는 기술을 개발하였고, 향후 도로 노면 관리를 위한 기술로 활용되길 기대한다.

• 한국광학회:학술대회논문집
• /
• 한국광학회 2009년도 동계학술발표회 논문집
• /
• pp.167-168
• /
• 2009

We propose a new computing method for Fourier hologram of 3D objects captured by lens array. Fourier hologram of the two objects which positioned at different distances can be calculated using multiple orthographic view images. The size of the Fourier hologram is in proportion to the number of the orthographic view images. By repeating the orthographic view images, the size of the Fourier hologram can be increased. The principle is verified by numerically reconstructing the hologram which is synthesized from the orthographic images captured optically.

• 한국멀티미디어학회논문지
• /
• 제24권4호
• /
• pp.550-557
• /
• 2021

Image steganalysis is a technique for detecting images with steganographic algorithms applied, called stego images. With state-of-the-art CNN-based steganalysis methods, we can detect stego images with high accuracy, but it is not possible to know which steganographic algorithm is used. Identifying stego images is essential for extracting embedded data. In this paper, as the first step for extracting data from stego images, we propose a hierarchical CNN structure for senary classification of steganographic algorithms. The hierarchical CNN structure consists of multiple CNN networks which are trained to classify each steganographic algorithm and performs binary or ternary classification. Thus, it classifies multiple steganogrphic algorithms hierarchically and stepwise, rather than classifying them at the same time. In experiments of comparing with several conventional methods, including those of classifying multiple steganographic algorithms at the same time, it is verified that using the hierarchical CNN structure can greatly improve the classification accuracy.

• 한국의상디자인학회지
• /
• 제4권1호
• /
• pp.5-17
• /
• 2002

This study aimed to investigate the relationship between ideal images of women and women's clothing fashion England between 1820s and 1850s. The age was divided into two periods, which were 1820-1836 and 1837-1850. During the first period, the ideal images of women were those of fairy, spirit, and angels, which were expressed by tight waist belt, wider and shorter skirt, top expanded sleeve, wide and flat pelerine collar, feather decoration, elaborate and curly hair style, narrow and light ballerina shoes etc.. During the second period, the ideal images for women were those of lady with modesty, quietness, and weakness. They were expressed by long and full skirt, tight or bulge over the lower arm sleeve, dropped sleeve, poke bonnet, body wrapping large shawl and sober color etc.. The result shows that the ideal images of women in 19th century England were concretely expressed by various clothing fashion including hair style, shoes, and decoration. This study sheds light on psychological, historical, and theoretical approaches to clothing.

• 한국군사과학기술학회지
• /
• 제12권4호
• /
• pp.524-531
• /
• 2009

In this paper, we propose an automatic image registration method for multi-sensor image fusion such as visible and infrared images. The registration is achieved by finding corresponding feature points in both input images. In general, the global statistical correlation is not guaranteed between multi-sensor images, which bring out difficulties on the image registration for multi-sensor images. To cope with this problem, mutual information is adopted to measure correspondence of features and to select faithful points. An update algorithm for projective transform is also proposed. Experimental results show that the proposed method provides robust and accurate registration results.