• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.207-220
• /
• 2022

Structural health monitoring (SHM) plays a vital role in the maintenance and operation of constructions. In recent years, autonomous inspection has received considerable attention because conventional monitoring methods are inefficient and expensive to some extent. To develop autonomous inspection, a potential approach of crack identification is needed to locate defects. Therefore, this study exploits two deep learning-based segmentation models, DeepLabv3+ and Mask R-CNN, for crack segmentation because these two segmentation models can outperform other similar models on public datasets. Additionally, impacts of label quality on model performance are explored to obtain an empirical guideline on the preparation of image datasets. The influence of image cropping and label refining are also investigated, and different strategies are applied to the dataset, resulting in six alternated datasets. By conducting experiments with these datasets, the highest mean Intersection-over-Union (mIoU), 75%, is achieved by Mask R-CNN. The rise in the percentage of annotations by image cropping improves model performance while the label refining has opposite effects on the two models. As the label refining results in fewer error annotations of cracks, this modification enhances the performance of DeepLabv3+. Instead, the performance of Mask R-CNN decreases because fragmented annotations may mistake an instance as multiple instances. To sum up, both DeepLabv3+ and Mask R-CNN are capable of crack identification, and an empirical guideline on the data preparation is presented to strengthen identification successfulness via image cropping and label refining.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권1호
• /
• pp.105-125
• /
• 2024

Gliomas are the most common malignant brain tumor and cause the most deaths. Manual brain tumor segmentation is expensive, time-consuming, error-prone, and dependent on the radiologist's expertise and experience. Manual brain tumor segmentation outcomes by different radiologists for the same patient may differ. Thus, more robust, and dependable methods are needed. Medical imaging researchers produced numerous semi-automatic and fully automatic brain tumor segmentation algorithms using ML pipelines and accurate (handcrafted feature-based, etc.) or data-driven strategies. Current methods use CNN or handmade features such symmetry analysis, alignment-based features analysis, or textural qualities. CNN approaches provide unsupervised features, while manual features model domain knowledge. Cascaded algorithms may outperform feature-based or data-driven like CNN methods. A revolutionary cascaded strategy is presented that intelligently supplies CNN with past information from handmade feature-based ML algorithms. Each patient receives manual ground truth and four MRI modalities (T1, T1c, T2, and FLAIR). Handcrafted characteristics and deep learning are used to segment brain tumors in a Global Convolutional Neural Network (GCNN). The proposed GCNN architecture with two parallel CNNs, CSPathways CNN (CSPCNN) and MRI Pathways CNN (MRIPCNN), segmented BraTS brain tumors with high accuracy. The proposed model achieved a Dice score of 87% higher than the state of the art. This research could improve brain tumor segmentation, helping clinicians diagnose and treat patients.

• 방송공학회논문지
• /
• 제21권5호
• /
• pp.782-791
• /
• 2016

영상에서 배경으로부터 객체를 추출하는 영상 segmentation 알고리즘은 물체 인식 및 추적 등 다양한 응용분야에서 활용될 수 있다. 본 논문에서는 고정된 카메라에서 다수의 초기 프레임을 참조하여 실시간 객체 segmentation 방법을 제안한다. 먼저 객체와 배경을 분류하는 확률모델을 제안하였으며 초기 프레임 동안에 카메라의 color consistency와 focus 특성을 분석하여 안정적인 segmentation 성능을 증가시켰다. 또한 분류된 객체에서 human의 skeleton 특성을 이용하여 추출 결과를 보정하는 방법을 제안한다. 마지막으로 제안된 알고리즘은 객체 segmentation 실시간 처리를 위하여 복잡도를 최소화하므로 다양한 mobile 단말에 확대 적용 가능하다.

• 한국전자파학회논문지
• /
• 제11권4호
• /
• pp.582-591
• /
• 2000

본 논문에서는 휴대전화기에 의한 인체 영향을 FDTD (시간영역 유한차분법) 해석할 수 있도록 한국인 표준 에 알맞는 인체 두부의 FDTD 모텔 제작 방법을 소개하였다. 한국인 표준에 알맞은 사람의 두부를 MRI 촬영한 다음.2차원 MRI 영상 데이터를 이용하여 2차원 segmentation을 하였다. segmentation은 반자동법을 적용하였 으며 제작된 2차원 se밍nentation 데이터를 토대로 $1mm\times1mm\times1mm$크기의 3차원 고해상도 segmentation 데이터를 제작하였다. 3차원 고해상도 segmentation 데이터를 이용하여 휴대전화기의 사용 상황에 어올리도록 다양한 각도로 기울인 인체 두부의 FDTD 모델을 제작하였다.

• 한국의류학회지
• /
• 제26권11호
• /
• pp.1605-1614
• /
• 2002

The purpose of this study was to identify the consumers who use the level of price as the indicator of the product quality. In order to implement the purpose of this study, Jeans market had been segmented by the mixture regression model, and price response function was calibrated for each segment. Based on the types of price response function, segments were allocated into one of two groups; the group using the level of price as the quality indicator or the group not using the level of price as that. Then, characteristics of both groups were compared in terms of product attributes and demographic variables. Data were co]looted from the sample of the 23o undergraduate and graduate students in Seoul. For the data analysis, mixture regression model, conjoint analysis, and t-test were used. As a result, jeans market was divided into 5 segments. Segment 1,2,3 were allocated into the group not using the level of price as the quality indicator while segment 4,5 were done into the other group. Significant differences existed between two groups in product attributes, not in demographic variables. Mixture model and conjoint analysis were proved to be an effective set of tools in market segmentation.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2011년도 하계학술대회
• /
• pp.437-438
• /
• 2011

Spectral segmentation is a major trend in image segmentation. Specially, constrained spectral segmentation, inspired by the user-given inputs, remains its challenging task. Since it makes use of the spectrum of the affinity matrix of a given image, its overall quality depends mainly on how to design the graphical model. In this work, we propose a sparse, multi-layer graphical model, where the pixels and the over-segmented regions are the graph nodes. Here, the graph affinities are computed by using the must-link and cannot-link constraints as well as the likelihoods that each node has a specific label. They are then used to simultaneously cluster all pixels and regions into visually coherent groups across all layers in a single multi-layer framework of Normalized Cuts. Although we incorporate only the adjacent connections in the multi-layer graph, the foreground object can be efficiently extracted in the spectral framework. The experimental results demonstrate the relevance of our algorithm as compared to existing popular algorithms.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2001년도 춘계학술대회 논문집
• /
• pp.435-438
• /
• 2001

Reverse engineering technology refers to the process that creates a CAD model of an existing part using measuring devices. Recently, non-contact scanning devices have become more accurate and the speed of data acquisition has increased drastically. However, they generate thousands of points per second and various types of point data. Therefore, it becomes a major issue to handle the huge amount and various types of point data. To generate a CAD model from scanned point data efficiently, these point data should be well arranged through point data handling processes such as data reduction and segmentation. This paper proposes a new point data handling method using 3D grids. The geometric information of a part is extracted from point cloud data by estimating normal values of the points. The non-uniform 3D grids for data reduction and segmentation are generated based on the geometric information. Through these data reduction and segmentation processes, it is possible to create CAD models autmatically and efficiently. The proposed method is applied to two quardric medels and the results are discussed.

• 한국인터넷방송통신학회논문지
• /
• 제13권2호
• /
• pp.233-237
• /
• 2013

이미지 인식은 패턴인식의 중요한 한 연구 분야이다. 본 논문은 이미지 세그멘테이션 알고리즘을 소개하고, 이의 응용으로 도로 Sign 인식시스템에 적용하여 그 결과를 고찰하였다. 본 논문에서, 우리는 이미지 프로세싱 기술의 도움으로 도로 Sign 의 체계적인 연구를 하였고, 이에 해당하는 알고리즘을 만들었다. 도로 Sign을 인식하기 위하여, 본 논문은 이미지 세그멘테이션 알고리즘 파트와 이미지 인식파트의 두 부분으로 나누어서 기술하였다. 인식실험은 도로 Sign 인식 알고리즘 모델이 스마트 폰에 유용하게 사용될 것과, 그 외 여러분야에 사용될 수 있음을 보여 준다.

• 보건행정학회지
• /
• 제13권4호
• /
• pp.84-98
• /
• 2003

This research objective is to determine the optimal price break points for n­block tariff, because comparing non­linear pricing with uniform pricing on the basis of profit, n­block tariff outperforms two­part tariff, all unit discount price schedule, and uniform pricing. Although the merits of non­linear pricing are well documented, the attempt to practice the non-linear pricing in medical service sector has been relatively rare. The determination of the parameters under n­block tariff is the interesting decision making agenda for marketers. Under n­block tariff, the marketers should decide the optimal price break points and the optimal marginal price for each price zone. The results can be summarized as follows: The researchers found that mixture model can be the feasible methodology for determining the optimal number of n­block tariff and identifying the optimal segmentation criteria. We demonstrate the feasibility and the superiority of the mixture model by applying it to the database of medical examination. The results appear that the number of patients per month can be the optimal segmentation variable. And 6­block tariff is the optimal price break for this medical service.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2003년도 춘계학술발표회 논문집
• /
• pp.229-236
• /
• 2003

In this study, for efficient replacemen of sensor modelling of high-resolution satellite imagery, image segmentation method is applied to the test area of the SPOT-3 satellite imagery. After that, a third-order polynomial model in the sectioned area is compared with the RFM which is to the entire in the test area. As results, plane error of the third-order polynomial model is lower(approximately 0.8m) than that of RFM. On the other hand, height error of RFM is lower(approximately 1.0m).