• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.335-336
• /
• 2006

In this paper, we propose an active shape image segmentation method for three-dimensional(3-D) medical images using a generation method of the 3-D shape model. The proposed method generates the shape model using a distance transform and a tetrahedron method for landmarking. After generating the 3-D model, we extend the training and segmentation processes of 2-D active shape model(ASM) and improve the searching process. The proposed method provides comparative results to 2-D ASM, region-based or contour-based methods. Experimental results demonstrate that this algorithm is effective for a semi-automatic segmentation method of 3-D medical images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권3호
• /
• pp.861-880
• /
• 2023

Semantic segmentation of road scene is the key technology of autonomous driving, and the improvement of convolutional neural network architecture promotes the improvement of model segmentation performance. The existing convolutional neural network has the simplification of learning knowledge and the complexity of the model. To address this issue, we proposed a road scene semantic segmentation algorithm based on multi-task collaborative learning. Firstly, a depthwise separable convolution atrous spatial pyramid pooling is proposed to reduce model complexity. Secondly, a collaborative learning framework is proposed involved with saliency detection, and the joint loss function is defined using homoscedastic uncertainty to meet the new learning model. Experiments are conducted on the road and nature scenes datasets. The proposed method achieves 70.94% and 64.90% mIoU on Cityscapes and PASCAL VOC 2012 datasets, respectively. Qualitatively, Compared to methods with excellent performance, the method proposed in this paper has significant advantages in the segmentation of fine targets and boundaries.

• 한국멀티미디어학회논문지
• /
• 제17권12호
• /
• pp.1412-1417
• /
• 2014

The corpus callosum is the largest part of the brain, which is related to many neurological diseases. Snake model or active contour model is widely used in medical image processing field, especially image segmentation they look into the nearby edge, localizing them accurately. In this paper, corpus callosum segmentation using the snake model, is proposed. We tested a snake model on brain MRI. Then we compared the result with an active shape approach and found that snake model had better segmentation accuracy also faster than active shape approach.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제18권2호
• /
• pp.129-142
• /
• 2014

We propose a variational segmentation model based on statistical information of intensities in an image. The model consists of both a local region-based energy and a global region-based energy in order to handle misclassification which happens in a typical statistical variational model with an assumption that an image is a mixture of two Gaussian distributions. We find local ambiguous regions where misclassification might happen due to a small difference between two Gaussian distributions. Based on statistical information restricted to the local ambiguous regions, we design a local region-based energy in order to reduce the misclassification. We suggest an algorithm to avoid the difficulty of the Euler-Lagrange equations of the proposed variational model.

• 한국정보전자통신기술학회논문지
• /
• 제5권1호
• /
• pp.1-6
• /
• 2012

본 논문에서는 HMM(Hidden Markov Model)방법에 기초하여 전경과 배경영역 뿐만 아니라 그림자 까지도 분할 할 수 있는 교통모니터링 방법을 제안하였다. 움직이는 물체의 그림자는 시각적 추적을 방해하기 때문에 이러한 문제점을 해결하기 위한 방법으로 각 화소나 영역을 3개의 카테고리 즉, 그림자, 전경, 배경물체로 분할하였다. 교통 모니터링 영상의 경우, 실험결과를 통해 제안된 방법의 효율성을 입증 할 수 있었다.

• 대한음성학회지:말소리
• /
• 제47호
• /
• pp.131-140
• /
• 2003

We propose a new method of generating client models for HMM based text-dependent speaker verification system with only a small amount of training data. To make a client model, statistical methods such as segmental K-means algorithm are widely used, but they do not guarantee the quality or reliability of a model when only limited data are avaliable. In this paper, we propose a blind speech segmentation based on level building DTW algorithm as an alternative method to make a client model with limited data. In addition, considering the fact that voiced sounds have much more speaker-specific information than unvoiced sounds and energy of the former is higher than that of the latter, we also propose a new score evaluation method using the observation probability raised to the power of weighting factor estimated from the normalized log energy. Our experiment shows that the proposed methods are superior to conventional HMM based speaker verification system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권12호
• /
• pp.4763-4775
• /
• 2020

This research aims to develop a deep learning-based method that automatically detects and segments the defects on railroad surfaces to reduce the cost of visual inspection of the railroad. We developed our segmentation model by modifying a fully convolutional network model [1], a well-known segmentation model used for machine learning, to detect and segment railroad surface defects. The data used in this research are images of the railroad surface with one or more defect regions. Railroad images were cropped to a suitable size, considering the long height and relatively narrow width of the images. They were also normalized based on the variance and mean of the data images. Using these images, the suggested model was trained to segment the defect regions. The proposed method showed promising results in the segmentation of defects. We consider that the proposed method can facilitate decision-making about railroad maintenance, and potentially be applied for other analyses.

• Korean Circulation Journal
• /
• 제54권1호
• /
• pp.30-39
• /
• 2024

Background and Objectives: Intravascular ultrasound (IVUS) evaluation of coronary artery morphology is based on the lumen and vessel segmentation. This study aimed to develop an automatic segmentation algorithm and validate the performances for measuring quantitative IVUS parameters. Methods: A total of 1,063 patients were randomly assigned, with a ratio of 4:1 to the training and test sets. The independent data set of 111 IVUS pullbacks was obtained to assess the vessel-level performance. The lumen and external elastic membrane (EEM) boundaries were labeled manually in every IVUS frame with a 0.2-mm interval. The Efficient-UNet was utilized for the automatic segmentation of IVUS images. Results: At the frame-level, Efficient-UNet showed a high dice similarity coefficient (DSC, 0.93±0.05) and Jaccard index (JI, 0.87±0.08) for lumen segmentation, and demonstrated a high DSC (0.97±0.03) and JI (0.94±0.04) for EEM segmentation. At the vessel-level, there were close correlations between model-derived vs. experts-measured IVUS parameters; minimal lumen image area (r=0.92), EEM area (r=0.88), lumen volume (r=0.99) and plaque volume (r=0.95). The agreement between model-derived vs. expert-measured minimal lumen area was similarly excellent compared to the experts' agreement. The model-based lumen and EEM segmentation for a 20-mm lesion segment required 13.2 seconds, whereas manual segmentation with a 0.2-mm interval by an expert took 187.5 minutes on average. Conclusions: The deep learning models can accurately and quickly delineate vascular geometry. The artificial intelligence-based methodology may support clinicians' decision-making by real-time application in the catheterization laboratory.

• 대한음성학회지:말소리
• /
• 제43호
• /
• pp.137-150
• /
• 2002

Speech segmentation at phoneme level is important for corpus-based text-to-speech synthesis. In this paper, we examine acoustic modeling methods to improve the performance of automatic speech segmentation system based on Hidden Markov Model (HMM). We compare monophone and triphone models, and evaluate several model training approaches. In addition, we employ an energy-based postprocessing scheme to make correction of frequent boundary location errors between silence and speech sounds. Experimental results show that our system provides 71.3% and 84.2% correct boundary locations given tolerance of 10 ms and 20 ms, respectively.

• 한국측량학회지
• /
• 제25권6_1호
• /
• pp.575-583
• /
• 2007

Surface segmentation aims to represent the terrain as a set of bounded and analytically defined surface patches. Many previous segmentation methods have been developed to extract planar patches from LIDAR data for building extraction. However, most of them were not fully satisfactory for more general applications in terms of the degree of automation and the quality of the segmentation results. This is mainly caused from the limited information derived from LIDAR data. The purpose of this study is thus to develop an automatic method to perform surface segmentation by combining not only LIDAR data but also images. A region-based method is proposed to generate a set of planar patches by grouping LIDAR points. The grouping criteria are based on both the coordinates of the points and the corresponding intensity values computed from the images. This method has been applied to urban data and the segmentation results are compared with the reference data acquired by manual segmentation. 76% of the test area is correctly segmented. Under-segmentation is rarely founded but over-segmentation still exists. If the over-segmentation is mitigated by merging adjacent patches with similar properties as a post-process, the proposed segmentation method can be effectively utilized for a reliable intermediate process toward automatic extraction of 3D model of the real world.