• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권1호
• /
• pp.366-381
• /
• 2020

Steganography has been successfully employed in various applications, e.g., copyright control of materials, smart identity cards, video error correction during transmission, etc. Deep learning-based steganography models can hide information adaptively through network learning, and they draw much more attention. However, the capacity, security, and robustness of the existing deep learning-based steganography models are still not fully satisfactory. In this paper, three models for different cases, i.e., a basic model, a secure model, a secure and robust model, have been proposed for different cases. In the basic model, the functions of high-capacity secret information hiding and extraction have been realized through an encoding network and a decoding network respectively. The high-capacity steganography is implemented by hiding a secret image into a carrier image having the same resolution with the help of concat operations, InceptionBlock and convolutional layers. Moreover, the secret image is hidden into the channel B of carrier image only to resolve the problem of color distortion. In the secure model, to enhance the security of the basic model, a steganalysis network has been added into the basic model to form an adversarial network. In the secure and robust model, an attack network has been inserted into the secure model to improve its robustness further. The experimental results have demonstrated that the proposed secure model and the secure and robust model have an overall better performance than some existing high-capacity deep learning-based steganography models. The secure model performs best in invisibility and security. The secure and robust model is the most robust against some attacks.

• 한국측량학회지
• /
• 제21권3호
• /
• pp.229-236
• /
• 2003

본 연구에서는 디지털 비디오 리코더를 이용하여 대상물을 촬영하고 이로부터 대상물의 3차원 위치정보 및 영상복원을 수행하고자 하였다. 이를 위하여 먼저 비디오 리코더에 의한 측량결과의 정확도를 분석함으로서 그 정도에 따른 활용성을 평가하는 한편, 실제 대상물에 적용시켜 3차원 복원을 수치적으로 수행하였다. 이때 비디오 리코더의 렌즈왜곡은 없고 모든 광속은 렌즈의 투영중심을 정확하게 지나가는 것으로 간주하였으며, 표정을 위한 영상의 크기는 CCD 칩의 크기와 영상소수를 이용하여 결정하였다. 디지털 비디오 리코더로부터 취득된 정보와 1초독 데오돌라이트를 이용하여 삼각측량한 성과를 비교한 결과 평균제곱근 오차가 평면오차 0.0173m로 나타났다. 또한 정확한 렌즈왜곡 정보나 투영중심의 좌표가 없음에도 불구하고 실제 대상물을 촬영하고 복원하는데 있어서 매우 양호한 결과를 나타내었으며, 디지털 비디오카메라에 의해 촬영된 영상과 카메라의 종류만 알면 대상물의 3차원 디지털복원이 가능하리라 사료된다.

• 정보과학회 논문지
• /
• 제42권10호
• /
• pp.1294-1302
• /
• 2015

현재까지 인간 시각 체계를 정확하게 반영하기 위한 이미지 평가 기법에 대한 연구가 많이 이루어져 오고 있다. SSIM은 인간의 시각 체계가 이미지의 구조적 정보에 예민하다는 점을 이용하여 구조적 정보를 이용하여 이미지를 평가하는 대표적인 인간 시각 체계를 만족시키는 평가 기법이다. 하지만 SSIM은 이미지의 색 차이를 반영하지 못하는 문제가 있다. 이러한 문제를 해결하기 위해, HSI 색 공간을 활용한 SHSIM 기법이 제안되었으나 두 컬러 이미지 간 인지적 색 차이를 충분히 반영하지는 못하고 있다. 본 논문에서는 CIE Lab 색 공간을 도입하여 대응 되는 픽셀들의 인지적 색 차이를 계산하여 이미지 평가에 활용하는 방법을 제안한다. 그리고 연구를 더 확장하여, SVM 분류기를 활용하여 왜곡 종류에 따라 최적의 평가 수식을 적용하는 최적화 시스템을 제안한다. 제안하는 기법을 평가하기 위해, 이미지 평가분야에서 가장 많이 알려진 LIVE 데이터베이스를 사용하였으며 네 종류의 평가 기준들을 이용하였다. 실험 결과에서는 제안하는 기법이 다른 기법들보다 인간 시각 체계와 더 상관성이 높다는 것을 보여준다.

• 한국통신학회논문지
• /
• 제38C권10호
• /
• pp.911-919
• /
• 2013

방사 왜곡이 홀로그래픽 스테레오그램에 미치는 영향을 알아보기 위해, 가상의 3차원 객체를 렌더링하고, 이 객체로부터 원근 투영 이미지를 획득하였다. 획득된 원근 투영 이미지를 재배열 하여 hogel 이미지를 만들고 복원되는 영상을 확인하기 위해 홀로그래픽 스테레오그램의 수학적 복원 알고리즘을 제안하였다. 광학 엔진에 의해 발생 할 수 있는 방사 왜곡을 포함하는 hogel 이미지를 왜곡 정도를 달리하여 만들고, 수학적 복원 알고리즘을 이용하여 복원 하였고, 복원된 영상을 PSNR을 이용하여 비교 하였다.

• 대한공간정보학회지
• /
• 제10권2호
• /
• pp.49-56
• /
• 2002

3D 가상도시 구축에 있어 사용자로 하여금 공간 객체 중심으로 지형 지물을 인식할 수 있게 해 줄 수 있는 요소로서 Texture Image를 들 수 있다. 본 연구에서는 디지틀 카메라를 통하여 건물 측면 Texture Image를 획득하고 이렇게 획득한 이미지가 가지고 있는 왜곡을 2D Projective Transformation방법을 사용하여 보정하였다. 보정이 끝난 Texture Image는 OpenGL을 이용하여 3D 건물 모델에 Mapping을 실시하였다. 본 연구를 통해 개발한 응용 프로그램은 가상도시를 구축하는 과정상에 자동화된 방법을 제공할 수 있다.

• 전자공학회논문지B
• /
• 제32B권12호
• /
• pp.1614-1623
• /
• 1995

In this paper we propose a region-adaptive CELP image coder for still images at low bit rates below 0.5 bpp. The proposed method partitions the image into stochastically similar regions by the minimum spanning tree method and finds prediction coefficients for each region using a 2- dimensional linear prediction model. Coding is carried out on 8$\times$8 blocks and when there are several regions included in a block, an image is synthesized using the prediction coefficients of each region. Computer simulation results show that the proposed method allows improved synthesized image over conventional block-adaptive CELP methods, especially at edges. In addition, performance comparison with the JPEG DCT method shows that while the JPEG method shows block distortion and staircase effects (ragged edges) at bit rates below 0.5 bpp, the proposed CELP method shows improved synthesized images with such effects reduced.

• 한국측량학회지
• /
• 제36권3호
• /
• pp.197-202
• /
• 2018

Drone has been continuously studied in the field of geography and remote sensing. The basic researches have been actively carried out before the utilization in the field of photogrammetry. In Korea, it is necessary to study the actual way of research in accordance with the drone utilization environment. In particular, analysis on the characteristics of DSM (Digital Surface Model) generated through drone are needed. In this study, the characteristic of drone DSM as a data acquisition method was analyzed for coastal management. The coastal area was selected as the study area, and data was acquired by using drone. As a result of the study, the terrain model and the ortho image of coastal area were produced. The accuracy of UAV (Unmanned Aerial Vehicle) results were very high about 10cm at check points. However, concavo-convex shapes appeared in very flat areas such as tidal flats and roads. To correct this terrain model distortion, a new terrain model was created through data processing and the results were evaluated. If additional studies are carried out and the construction and analysis of terrain model using drone image is done, drone data for coastal management will be available.

• 한국멀티미디어학회논문지
• /
• 제8권6호
• /
• pp.783-789
• /
• 2005

This paper is proposed a watermarking technique for copyright protection of multimedia contents. We proposed adaptive watermark detection algorithm using stochastic perceptual model and statistical decision method in DMWT(discrete multi wavelet transform) domain. The stochastic perceptual model calculates NVF(noise visibility function) based on statistical characteristic in the DMWT. Watermark detection algorithm used the likelihood ratio depend on Bayes' decision theory by reliable detection measure and Neyman-Pearson criterion. To reduce visual artifact of image, in this paper, adaptively decide the embedding number of watermark based on DMWT, and then the watermark embedding strength differently at edge and texture region and flat region embedded when watermark embedding minimize distortion of image. In experiment results, the proposed statistical decision method based on multiwavelet domain could decide watermark detection.

• 시스템엔지니어링학술지
• /
• 제16권1호
• /
• pp.51-57
• /
• 2020

The fighter pilot uses radar mounted on the fighter to obtain high-resolution SAR (Synthetic Aperture Radar) images for a specific area of distance, and then the pilot visually classifies targets within the image. However, the target configuration captured in the SAR image is relatively small in size, and distortion of that type occurs depending on the depression angle, making it difficult for pilot to classify the type of target. Also, being present with various types of clutters, there should be errors in target classification and pilots should be even worse if tasks such as navigation and situational awareness are carried out simultaneously. In this paper, the concept of operation and functional structure of radar system for fighter jets were presented to transfer the SAR image target classification task of fighter pilots to radar system, and the method of target classification with high accuracy was studied using the CNN ensemble model to archive higher classification accuracy than single CNN model.