• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권3호
• /
• pp.877-893
• /
• 2022

With the development of deep learning, face inpainting has been significantly enhanced in the past few years. Although image inpainting framework integrated with generative adversarial network or attention mechanism enhanced the semantic understanding among facial components, the issues of reconstruction on corrupted regions are still worthy to explore, such as blurred edge structure, excessive smoothness, unreasonable semantic understanding and visual artifacts, etc. To address these issues, we propose a Learnable Structure Knowledge of Fusion Network (LSK-FNet), which learns a prior knowledge by edge generation network for image inpainting. The architecture involves two steps: Firstly, structure information obtained by edge generation network is used as the prior knowledge for face inpainting network. Secondly, both the generated prior knowledge and the incomplete image are fed into the face inpainting network together to get the fusion information. To improve the accuracy of inpainting, both of gated convolution and region normalization are applied in our proposed model. We evaluate our LSK-FNet qualitatively and quantitatively on the CelebA-HQ dataset. The experimental results demonstrate that the edge structure and details of facial images can be improved by using LSK-FNet. Our model surpasses the compared models on L1, PSNR and SSIM metrics. When the masked region is less than 20%, L1 loss reduce by more than 4.3%.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제16권2호
• /
• pp.166-171
• /
• 2016

Nickel silicide is main issue in Polycrystalline silicon Thin Film Transistor (TFT) which is made by Metal Induced Lateral Crystallization (MILC) method. This Nickel silicide acts as a defect center, and this defect is one of the biggest reason of the high leakage current. In this research, we fabricated polycrystalline TFTs with novel method called Edge Cut (EC). With this new fabrication method, we assumed that nickel silicide at the edge of the channel region is reduced. Electrical properties are measured and trap state density also calculated using Levinson & Proano method.

• Journal of information and communication convergence engineering
• /
• 제7권4호
• /
• pp.535-538
• /
• 2009

Speckle noise reduction for ultrasound CT image using morphological adaptive median filtering based on edge preservation is presented in this paper. Speckle noise is multiplicative feature and causes ultrasound image to degrade widely from transducer. An input image is classified into edge region and homogeneous region in preprocessing. The speckle is reduced by morphological operation on the 2D gray scale by using convolution and correlation, and edges are preserved. The adaptive median is processed to reduce an impulse noise to preserve edges. As the result, MAM of the proposed method enhances the image to about 10% in comparison with Winner filter by Edge Preservation Index and PSNR, and 10% to only adaptive median filtering.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 추계학술대회논문집A
• /
• pp.389-395
• /
• 2001

To restrain contact failure, present study investigates the influence of edge machining of an indenter (punch). As for the edge machining, rounding, chamfering, and chamfering and rounding are considered. Contact mechanics is consulted to examine the traction profile and the size of the contact region which are directly influenced by the end profile of the indenter. The effect of rounding size (i.e., radius) in the case of the chamfering and rounding edge-indenter is studied. Shear traction is also evaluated within the regime of partial slip. Size of slip region and its expansion rate due to the increase of shear force are considered to investigate the shape effect of the indenter on contact failure.

• 로봇학회논문지
• /
• 제5권2호
• /
• pp.85-92
• /
• 2010

In this paper, we propose a digital image stabilization technique using edge detection and Lucas-Kanade optical flow in order to minimize the motion of the shaken image. The accuracy of motion estimation based on block matching technique depends on the size of search window, which results in long calculation time. Therefore it is not applicable to real-time system. In addition, since the size of vector depends on that of block, it is difficult to estimate the motion which is bigger than the block size. The proposed method extracts the trust region using edge detection, to estimate the motion of some critical points in trust region based on Lucas-Kanade optical flow algorithm. The experimental results show that the proposed method stabilizes the shaking of motion image effectively in real time.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2009년도 추계학술대회
• /
• pp.329-332
• /
• 2009

Speckle noise reduction for ultrasound CT image using morphological adaptive median filtering based on edge preservation is presented in this paper. Speckle noise is multiplicative feature and causes ultrasound image to degrade widely from transducer. An input image is classified into edge region and homogeneous region in preprocessing. The speckle is reduced by morphological operation on the 2D gray scale by using convolution and correlation, and edges are preserved. The adaptive median is processed to reduce an impulse noise. As the result the proposed method enhances the image to about 20% in comparison with Winer filter by Edge Preservation Index and PSNR.

• 한국항공운항학회지
• /
• 제11권2호
• /
• pp.33-42
• /
• 2003

In this paper, we propose an enhancement of the ultrasonic image for non-destructive inspection of aircraft composite materials. The ultrasonic images are corrupted by a speckle noise which has the characteristic of granular pattern noise and is in all types of coherent imaging systems, the signal independent and multiplicative noise. In this paper, we derive a filter, called the AWLF(Adaptive Window Log Filter), from the nature of the speckle. The filter is made of the MEAN Filter in the edge region and Log Filter in the flat or noise region. To make a distinction between edge and flat region, we calculate the inclination around the local window instead of computing the local statistics of pixels such as local mean ${\bar{M}}$ and standard deviation ${\sigma}_s$. According to the obtained region, edge region is performed by the mean filter and flat region by the Log filter. Performance of the proposed filter is evaluated by the Enhanced Factor$(F_e)$ and the Speckle Index(SI).

• 한국멀티미디어학회논문지
• /
• 제6권1호
• /
• pp.78-88
• /
• 2003

본 논문에서는 연산 영역 가변 알고리즘을 적용한 MPEG-4 부호화 기반의 적응적 오류 은닉 (error concealment) 기법을 제안하였다. 이 알고리즘에서는 손실 블록을 그의 주변 정보를 이용하여 이들을 평탄블록 (flat block) 및 에지 블록 (edge block)으로 분류한다. 즉, 손실된 블록의 주변 블록들에 대해서 블록 경계 영역의 인접 화소들의 차를 이용하여 평탄 블록을 분류하고, 평탄 블록으로 분류되지 않은 블록들에 대해서는 인접 화소의 차가 정해진 임계값을 넘어서는 개수에 따라 가변적인 연산 영역 (variable operating region, VOR)을 설정한 후, Sobel 연산자를 적용하여 우세 에지 방향 성분을 추정한다. 이렇게 분류된 각 블록에 대하여 적응적 오류 은닉을 수행한다. 평탄 블록에 대해서는 시각적 성능 향상을 위해 평균값을 기반으로 한 가중치에 따른 양선형 보간(mean based weighted bilinear interpolation, MWBLI) 방법을 적용하고, 에지 블록에 대해서는 8가지 방향에 대하여 경계 픽셀을 이용한 방향성 보간 (boundary directional interpolation, BDI) 방법을 적용하여 오류 은닉을 수행한다. 모의 실험 결과를 통하여 제안한 방법이 객관적 화질 및 주관적 화질 측면에서 기존의 방법보다 그 성능이 우수함을 확인하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2007년도 하계종합학술대회 논문집
• /
• pp.389-390
• /
• 2007

In this paper, we propose a modified watershed algorithm to obtain exact edge of region. The proposed method adjusts priority at zero-crossing point of gradient in order to make the point of region decision time postponed. We compare the proposed method with a previous method and prove that this method can extract more correct edge of region.

• 한국멀티미디어학회논문지
• /
• 제13권10호
• /
• pp.1463-1473
• /
• 2010

본 논문에서는 정확한 경계 추출 및 수행시간 단축을 위한 개선된 워터쉐드 알고리즘을 제안한다. 본 논문에서는 두 가지 새로운 알고리즘을 제안한다. 첫 번째는 기존 강우방식과 침수방식의 워터쉐드 확장 방식을 복합적으로 적용한 것이다. 먼저 각 방식의 장점과 단점을 규명하고 장점은 유지하고 단점은 보완하여 정확한 경계를 추출하면서도 수행시간을 단축할 수 있는 새로운 확장방식을 제안한다. 두 번째는 보다 정확한 경계를 얻기 위한 새로운 우선순위 결정 알고리즘이다. 기울기의 영교차점은 경계로 예상되는 위치이지만 기존의 워터쉐드 알고리즘은 이러한 위치를 경계로 추출하지 못하는 한계를 가지고 있다. 따라서 보다 정확한 경계를 추출할 수 있도록 워터쉐드를 위한 새로운 우선순위 결정 알고리즘을 제안한다. 모의실험을 통해 제안된 알고리즘과 기존 알고리즘을 비교하고 제안된 방법이 보다 정확한 경계를 추출할 수 있음을 보인다.