• Journal of Advanced Information Technology and Convergence
• /
• v.8 no.2
• /
• pp.89-99
• /
• 2018

Due to global warming, various natural disasters such as floods and droughts are increasing. If we can detect the possibility of natural disasters in advance, we can prevent massive damages caused by natural disasters. Recent advances in visual sensor technologies have enabled remote monitoring of a variety of natural environments, including lakes, rivers, and shores. In this paper, we propose a method to segment an image obtained from video sensor networks into regions in order to monitor the environment effectively. In the proposed method, we first partition the image into superpixels and model the connections between superpixels as a graph. Then, initial seeds for each region are set by using the prior information, and the initial seeds are expanded to form regions using agglomerative clustering. Experimental results show that the proposed method extracts the regions from natural environment images easily and accurately.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.12
• /
• pp.35-41
• /
• 2018

In this paper, we propose a swarm-based possibilistic c-means(PCM) algorithm in order to overcome the problems of PCM, which are sensitiveness of clustering performance due to initial cluster center's values and producing coincident or close clusters. To settle the former problem of PCM, we adopt a swam-based global optimization method which can be provided the optimal initial cluster centers. Furthermore, to settle the latter problem of PCM, we design an adaptive thresholding model based on the optimized cluster centers that yields preliminary clustered and un-clustered dataset. The preliminary clustered dataset plays a role of preventing coincident or close clusters and the un-clustered dataset is lastly clustered by PCM. From the experiment, the proposed method obtains a better performance than other PCM algorithms on a simulated magnetic resonance(MR) brain image dataset which is corrupted by various noises and bias-fields.

• International Journal of Advanced Culture Technology
• /
• v.9 no.4
• /
• pp.385-391
• /
• 2021

3D modeling of the human body is an integral part of computer graphics. Among them, several studies have been conducted on hair modeling, but there are generally few studies that effectively implement hair and face modeling simultaneously. This study has the originality of providing users with customized face modeling and hair modeling that is different from previous studies. For realistic hair styling, We design and realize hair segmentation using FCN, and we select the most appropriate model through comparing PSPNet, DeepLab V3+, and MobileNet. In this study, we use the open dataset named Figaro1k. Through the analysis of iteration and epoch parameters, we reach the optimized values of them. In addition, we experiment external parameters about the location of the camera, the color of the lighting, and the presence or absence of accessories. And the environmental analysis factors of the avatar maker were set and solutions to problems derived during the analysis process were presented.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.4_2
• /
• pp.573-586
• /
• 2022

Corrosion can cause dangerous and expensive damage and failures of ship hulls and equipment. Therefore, it is necessary to maintain the vessel by periodic corrosion inspections. During visual inspection, many corrosion locations are inaccessible for many reasons, especially safety's point of view. Including subjective decisions of inspectors is one of the issues of visual inspection. Automation of visual inspection is tried by many pieces of research. In this study, we propose image preprocessing methods by image patch segmentation and thresholding. YOLOv5 was used as an object detection model after the image preprocessing. Finally, it was evaluated that corrosion detection performance using the proposed method was improved in terms of mean average precision.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.11-13
• /
• 2023

의미론적 분할(Semantic Segmentation)은 이미지 내의 객체 및 배경을 픽셀 단위로 분류하는 작업으로 정밀한 탐지가 요구되는 분야에서 활발히 연구되고 있다. 기존 어텐션 기법은 의미론적 분할의 다운샘플링(Downsampling) 과정에서 발생하는 정보손실을 완화하기 위해 널리 사용됐지만 고정된 Convolution 필터의 형태 때문에 객체의 형태에 따라 유동적으로 대응하지 못했다. 본 논문에서는 이를 보완하고자 Deformable Convolution과 셀프어텐션(Self-attention) 구조기반 어텐션 모듈을 사용한 의미론적 분할 모델을 제안한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.481-484
• /
• 2024

본 논문에서는 레고(LEGO®) 조립 설명서를 생성하기 위해 딥러닝을 이용한 조립 및 설명서 생성 시스템을 제안한다. 이 시스템은 사용자가 제공한 단일 이미지를 기반으로 레고 조립 설명서를 자동 생성한다. 해당 시스템은 딥러닝 기반 이미지 분할 기술을 활용하여 물체를 배경으로부터 분리하고 이를 통해 조립 설명서를 생성하는 과정을 포함하며, 조립을 위한 알고리즘을 새로 설계하였다. 이 시스템은 기존 레고 제품의 한계를 극복하고, 사용자에게 주어진 부품으로 다양한 모델을 자유롭게 조립할 수 있게 한다. 또한, 복잡한 레고 조립 과정을 간소화하고, 조립의 장벽을 낮추는 데 도움을 준다.

• ETRI Journal
• /
• v.46 no.3
• /
• pp.526-537
• /
• 2024

Monitoring fetal growth in utero is crucial to anomaly diagnosis. However, current computer-vision models struggle to accurately assess the key metrics (i.e., head circumference and occipitofrontal and biparietal diameters) from ultrasound images, largely owing to a lack of training data. Mitigation usually entails image augmentation (e.g., flipping, rotating, scaling, and translating). Nevertheless, the accuracy of our task remains insufficient. Hence, we offer a U-Net fetal head measurement tool that leverages a hybrid Dice and binary cross-entropy loss to compute the similarity between actual and predicted segmented regions. Ellipse-fitted two-dimensional ultrasound images acquired from the HC18 dataset are input, and their lower feature layers are reused for efficiency. During regression, a novel region of interest pooling layer extracts elliptical feature maps, and during segmentation, feature pyramids fuse field-layer data with a new scale attention method to reduce noise. Performance is measured by Dice similarity, mean pixel accuracy, and mean intersection-over-union, giving 97.90%, 99.18%, and 97.81% scores, respectively, which match or outperform the best U-Net models.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.51 no.1
• /
• pp.1-10
• /
• 2024

Deep learning algorithms are becoming more prevalent in dental research because they are utilized in everyday activities. However, dental researchers and clinicians find it challenging to interpret deep learning studies. This review aimed to provide an overview of the general concept of deep learning and current deep learning research in dental radiographic image analysis. In addition, the process of implementing deep learning research is described. Deep-learning-based algorithmic models perform well in classification, object detection, and segmentation tasks, making it possible to automatically diagnose oral lesions and anatomical structures. The deep learning model can enhance the decision-making process for researchers and clinicians. This review may be useful to dental researchers who are currently evaluating and assessing deep learning studies in the field of dentistry.

• International journal of advanced smart convergence
• /
• v.13 no.2
• /
• pp.187-194
• /
• 2024

For precise cardiac diagnostics and treatment, we introduce a novel method for patient-specific mapping between myocardial and coronary anatomy, leveraging local variations in myocardial thickness. This complex system integrates and automates multiple sophisticated components, including left ventricle segmentation, myocardium segmentation, long-axis estimation, coronary artery tracking, and advanced geodesic Voronoi distance mapping. It meticulously accounts for variations in myocardial thickness and precisely delineates the boundaries between coronary territories according to the conventional 17-segment myocardial model. Each phase of the system provides a step-by-step approach to automate coronary artery mapping onto the myocardium. This innovative method promises to transform cardiac imaging by offering highly precise, automated, and patient-specific analyses, potentially enhancing the accuracy of diagnoses and the effectiveness of therapeutic interventions for various cardiac conditions.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.794-797
• /
• 2024

Despite advancements in deep learning, existing semantic segmentation models exhibit suboptimal performance under adverse weather conditions, such as fog or rain, whereas they perform well in clear weather conditions. To address this issue, much of the research has focused on making image or feature-level representations weather-independent. However, disentangling the style and content of images remains a challenge. In this work, we propose a novel fine-tuning method, 'freeze-n-update.' We identify a subset of model parameters that are weather-independent and demonstrate that by freezing these parameters and fine-tuning others, segmentation performance can be significantly improved. Experiments on a test dataset confirm both the effectiveness and practicality of our approach.