• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권7호
• /
• pp.1888-1906
• /
• 2024

Aiming at the problems that the edge of melanoma image is fuzzy, the contrast with the background is low, and the hair occlusion makes it difficult to segment accurately, this paper proposes a model MSCNet for melanoma segmentation based on U-net frame. Firstly, a multi-scale pyramid fusion module is designed to reconstruct the skip connection and transmit global information to the decoder. Secondly, the contextural information conduction module is innovatively added to the top of the encoder. The module provides different receptive fields for the segmented target by using the hole convolution with different expansion rates, so as to better fuse multi-scale contextural information. In addition, in order to suppress redundant information in the input image and pay more attention to melanoma feature information, global channel attention mechanism is introduced into the decoder. Finally, In order to solve the problem of lesion class imbalance, this paper uses a combined loss function. The algorithm of this paper is verified on ISIC 2017 and ISIC 2018 public datasets. The experimental results indicate that the proposed algorithm has better accuracy for melanoma segmentation compared with other CNN-based image segmentation algorithms.

• 정보처리학회논문지B
• /
• 제15B권4호
• /
• pp.293-300
• /
• 2008

본 논문에서는 상향식 방식의 주의모듈을 사용하여 얻어지는 의미론적으로 중요한 영역에 워터마킹을 삽입하는 새로운 방법을 제안한다. 본 논문에서는 저작물을 공격하는 제3자가 영상 전체 정보가 아닌 몇몇 영역 및 물체에 관심을 가지고 있다는 사실에 착안하여 의미론적으로 중요하다고 생각되는 영역에 워터마크 정보를 삽입한다. 이는 전통적인 워터마킹 방법이 영상의 전체 영역에 걸쳐 워터마크를 삽입하는 것과는 다른 접근방법이다. 워터마크가 삽입되는 관심영역은 인간의 상향식 방식의 시각적 주의에 기반하여 모델링 된 주의모듈을 통해 얻는다. 본 논문을 통해 제안되는 워터마크 기법은 워터마크가 전체 영상이 아닌 몇몇 주요영역에 삽입되므로 중요부분이 공격당하기 어렵게 되며, 워터마크를 확인하여 소유권자를 구분할 때에도 워터마크가 관심영역 안에 있기 때문에 삽입된 워터마크의 탐지율이 높아진다. 실험결과를 통해 제안하는 방법의 효용성을 확인하였다.

• 한국콘텐츠학회논문지
• /
• 제7권2호
• /
• pp.63-72
• /
• 2007

교통 표지판은 먼거리에서도 교통 표지라는 것을 쉽게 판별하여 단시간 내에 그 내용을 파악할 수 있어야 한다. 교통 표지판의 도로의 안전 주행에 있어 아주 중요한 객체로 도로 상의 다른 그 무엇보다도 먼저 인간의 시선을 잡아끌어야 한다. 이에 본 논문에서는 인간의 도로 상의 어떤 물체보다도 교통 표지판에 가장 먼저 시선을 집중한다는 가정하에 주의 모듈(Attention Module)을 사용하여 교통 표지판 영역을 추출하는 시스템을 제안하고자 한다. 특히 본 논문에서는 인간의 대상(object)인식과정, 특히 색상처리과정에서 어떠한 특징들이 사용되어지는지를 기존의 정신물리학적, 생리학적 실험결과를 통해 분석하였고, 이 분석결과를 통해 얻어진 특징들을 사용하여 교통 표지판 영역을 추출하였다. 실제 도로위에서 찍은 실영상을 대상으로 실험하였으며, 실험을 통하여 평균 97.8%의 탐지율을 보임을 확인하였다.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2002년도 학술대회지
• /
• pp.729-732
• /
• 2002

This paper reports an experimental study around a module about forced air flow by blower($35{\times}35{\times}6mm^3$) in portable PC(10mm high, 200mm wide, and 235mm long). The channel inlet flow velocity has been varied between 0.26, 0.52 and 0.78m/s. The power input to the module is 4Wthis report, particular attention is directed to the fluid flow and adiabatic wall temperature($T_(ad)$) around a module which is under fluid mechanical and thermal influences of the module. The fluid flow around a module was visualized using PIV system. Liquid crystal thernography is used to determine the adiabatic wall temperature around a heated module on an acrylic board. Plots of $T_(ad)$ (or F) show marked effects of dispersion of thermal wake near the module.

• Journal of Information Processing Systems
• /
• 제18권4호
• /
• pp.575-586
• /
• 2022

Uneven light in real-world causes visual degradation for underexposed regions. For these regions, insufficient consideration during enhancement procedure will result in over-/under-exposure, loss of details and color distortion. Confronting such challenges, an unsupervised low-light image enhancement network is proposed in this paper based on the guidance of the unpaired low-/normal-light images. The key components in our network include super-resolution module (SRM), a GAN-based low-light image enhancement network (LLIEN), and denoising-scaling module (DSM). The SRM improves the resolution of the low-light input images before illumination enhancement. Such design philosophy improves the effectiveness of texture details preservation by operating in high-resolution space. Subsequently, local lightness attention module in LLIEN effectively distinguishes unevenly illuminated areas and puts emphasis on low-light areas, ensuring the spatial consistency of illumination for locally underexposed images. Then, multiple discriminators, i.e., global discriminator, local region discriminator, and color discriminator performs assessment from different perspectives to avoid over-/under-exposure and color distortion, which guides the network to generate images that in line with human aesthetic perception. Finally, the DSM performs noise removal and obtains high-quality enhanced images. Both qualitative and quantitative experiments demonstrate that our approach achieves favorable results, which indicates its superior capacity on illumination and texture details restoration.

• 대한안전경영과학회지
• /
• 제17권3호
• /
• pp.371-375
• /
• 2015

Smartphone industry grew rapidly enough to draw a close attention in a short period less than ten years. Accordingly, required camera module industry is getting increase. In this study, it will be shown how to improve the productivity of new product model for the camera module before the growth to maximize the company profits.

• 스마트미디어저널
• /
• 제13권3호
• /
• pp.53-61
• /
• 2024

본 논문은 기존 방법보다 우수한 성능을 달성하는 피부 병변 분할을 위한 새로운 M자 모양 인코더-디코더 아키텍처를 제안한다. 제안된 아키텍처는 왼쪽과 오른쪽 다리를 활용하여 다중 스케일 특징 추출을 가능하게 하고, 스킵 연결 내에서 어텐션 메커니즘을 통합하여 피부 병변 분할 성능을 더욱 향상시킨다. 입력 영상은 네 가지 다른 패치로 분할되어 입력되며 인코더-디코더 프레임워크 내에서 피부 병변 분할 성능의 향상된 처리를 가능하게 한다. 제안하는 방법에서 어텐션 메커니즘을 통해 입력 영상의 특징에 더 많은 초점을 맞추어 더욱 정교한 영상 분할 결과를 도출하는 것이다. 실험 결과는 제안된 방법의 효과를 강조하며, 기존 방법과 비교하여 우수한 정확도, 정밀도 및 Jaccard 지수를 보여준다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권10호
• /
• pp.2768-2787
• /
• 2023

As an important research direction of the application of computer science in the medical field, the automatic generation technology of radiology report has attracted wide attention in the academic community. Because the proportion of normal regions in radiology images is much larger than that of abnormal regions, words describing diseases are often masked by other words, resulting in significant feature loss during the calculation process, which affects the quality of generated reports. In addition, the huge difference between visual features and semantic features causes traditional multi-modal fusion method to fail to generate long narrative structures consisting of multiple sentences, which are required for medical reports. To address these challenges, we propose a multi-feature optimization Transformer (MFOT) for generating radiology reports. In detail, a multi-dimensional mapping attention (MDMA) module is designed to encode the visual grid features from different dimensions to reduce the loss of primary features in the encoding process; a feature pre-fusion (FP) module is constructed to enhance the interaction ability between multi-modal features, so as to generate a reasonably structured radiology report; a detail enhanced attention (DEA) module is proposed to enhance the extraction and utilization of key features and reduce the loss of key features. In conclusion, we evaluate the performance of our proposed model against prevailing mainstream models by utilizing widely-recognized radiology report datasets, namely IU X-Ray and MIMIC-CXR. The experimental outcomes demonstrate that our model achieves SOTA performance on both datasets, compared with the base model, the average improvement of six key indicators is 19.9% and 18.0% respectively. These findings substantiate the efficacy of our model in the domain of automated radiology report generation.

• 한국태양에너지학회:학술대회논문집
• /
• 한국태양에너지학회 2008년도 추계학술발표대회 논문집
• /
• pp.36-41
• /
• 2008

In this paper, we study The Effects of PV Cell's Electrical Characteristics for PV Module Application. Photovoltaic module consists of serially connected solar cell which has low open circuit voltage and high short circuit current characteristics. The whole current flow of PV module is restricted by lowest current of one solar cell. For the experiment, we make PV module composing the solar cells that have short circuit current difference of 0%, 1%, 3% and Random. The PV module exposed about 35days, its the maximum power drop ratio was 4.282% minimum and 6.657% maximum. And PV module of low current characteristics has electrical stress from other modules. The solar cell temperature of PV module was higher compared to PV cell. To prevent early degradation, it is need to have attention to PV cell selection.

• Journal of Information Processing Systems
• /
• 제19권1호
• /
• pp.130-138
• /
• 2023

The traffic flow in an urban area is affected by the date, weather, and regional traffic flow. The existing methods are weak to model the dynamic road network features, which results in inadequate long-term prediction performance. To solve the problems regarding insufficient capacity for dynamic modeling of road network structures and insufficient mining of dynamic spatio-temporal features. In this study, we propose a novel traffic flow prediction framework called shared spatio-temporal attention convolution optimization network (SSTACON). The shared spatio-temporal attention convolution layer shares a spatio-temporal attention structure, that is designed to extract dynamic spatio-temporal features from historical traffic conditions. Subsequently, the graph optimization module is used to model the dynamic road network structure. The experimental evaluation conducted on two datasets shows that the proposed method outperforms state-of-the-art methods at all time intervals.