• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권6호
• /
• pp.2302-2316
• /
• 2015

We propose an efficient method of extracting targets within a region of interest in non-homogeneous infrared images by using a principal component analysis (PCA) plane and adaptive Gaussian kernel. Existing approaches for extracting targets have been limited to using only the intensity values of the pixels in a target region. However, it is difficult to extract the target regions effectively because the intensity values of the target region are mixed with the background intensity values. To overcome this problem, we propose a novel PCA based approach consisting of three steps. In the first step, we apply a PCA technique minimizing the total least-square errors of an IR image. In the second step, we generate a binary image that consists of pixels with higher values than the plane, and then calculate the second derivative of the sum of the square errors (SDSSE). In the final step, an iteration is performed until the convergence criteria is met, including the SDSSE, angle and labeling value. Therefore, a Gaussian kernel is weighted in addition to the PCA plane with the non-removed data from the previous step. Experimental results show that the proposed method achieves better segmentation performance than the existing method.

• 대한원격탐사학회지
• /
• 제19권2호
• /
• pp.149-157
• /
• 2003

본 연구에서는 향후 지속적으로 제공되어질 고해상도 위성영상의 효율적인 대체 센서모델링을 위하여 SPOT-3호의 위성영상으로부터 대상영역에 영상분할을 실시하고 분할된 영상으로부터 분모항이 없는 RFM 즉, 3차 다항식 모델의 적용성을 고찰하였다. 대상영역 전체에 적용한 분모항이 있는 기존 RFM의 적합도와 비교한 결과, 평면오차는 3차 다항식 모델링 방법이 0.8m 정도 낮게 산출된 반면 표고오차는 기존의 RFM이 1.0m 정도 낮게 산출되었다.

• 한국가시화정보학회지
• /
• 제19권1호
• /
• pp.28-35
• /
• 2021

In this study, an image processing method for the measurement of two-phase bubbly flow is developed. Shadowgraphy images obtained by high-speed camera are used for analysis. Some bubbles are generated as single unit and others are overlapped or clustered. Single bubbles can be easily analyzed using parameters such as bubble shape, centroid, and area. But overlapped bubbles are difficult to transform clustered bubbles into segmented bubbles. Several approaches were proposed for the bubble segmentation such as Hough transform, connection point method and watershed. These methods are not enough for bubble segmentation. In order to obtain the size distribution of bubbles, we present a method of splitting overlapping bubbles using watershed and approximating them to ellipse. There is only 5% error difference between manual and automatic analysis. Furthermore, the error can be reduced down to 1.2% when a correction factor is used. The ellipse fitting algorithm developed in this study can be used to measure bubble parameters accurately by reflecting the shape of the bubbles.

• 말소리와 음성과학
• /
• 제10권3호
• /
• pp.19-29
• /
• 2018

We propose to use independent component analysis (ICA) and deep neural network (DNN) to detect music sections in broadcast drama contents. Drama contents mainly comprise silence, noise, speech, music, and mixed (speech+music) sections. The silence section is detected by signal activity detection. To detect the music section, we train noise, speech, music, and mixed models with DNN. In computer experiments, we used the MUSAN corpus for training the acoustic model, and conducted an experiment using 3 hours' worth of Korean drama contents. As the mixed section includes music signals, it was regarded as a music section. The segmentation error rate (SER) of music section detection was observed to be 19.0%. In addition, when stereo mixed signals were separated into music signals using ICA, the SER was reduced to 11.8%.

• 대한전자공학회논문지
• /
• 제24권3호
• /
• pp.504-509
• /
• 1987

In this paper a characteristics of image which can be segmented based on the thresholding technique using a histogram was investigated employing 3 parameters: the variance of pixel value, the average mean difference between target and background and the target size. The threshold value for the histogram segmentation was determined by applying the hypothesis testing theory. The performance of the selected threshold was evaluated by computing a probability of error. Since a priori probability can be easily obtained from the histogram, it was found that the Bayes decision rule which theoretically guarantees the minimum probability of error works better than the minimax criterion rule.

• 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.

• 한국멀티미디어학회논문지
• /
• 제17권3호
• /
• pp.342-352
• /
• 2014

본 논문에서는 마이크로 CT 영상에서 치밀뼈와 해면뼈의 자동 분할 방법을 제안하고 분할된 해면뼈의 형태학적 분석 방법의 구현에 대해 기술한다. 제안된 분할 방법에서는 임계값을 이용하여 뼈 영역을 추출한다. 그 다음에는, 뼈의 바깥 경계선부터 안쪽 방향으로 인접한 경계선을 찾아 치밀뼈 후보 영역을 설정한다. 치밀뼈 후보 영역들 중에서 평균 픽셀값이 최대가 되는 지점을 후보 영역을 탐색하여 치밀뼈를 제거한다. 분할된 해면뼈에 BV/TV, Tb.Th, Tb.Sp, Tb.N의 네 가지 형태학적 지표자들을 계산하는 방법을 VTK(Visualization ToolKit)와 구 정합 알고리즘을 이용하여 구현하였다. 구현된 방법을 쥐의 20개 대퇴골 근위부 영상에 적용하였으며 사람이 수작업으로 분할하는 방법과 비교 실험을 수행하였다. 실험 결과 네 가지 형태학적 지표자 모두 수작업으로 분할한 경우와 자동으로 분할한 경우 3% 이내의 평균 오차율을 보여 제안된 방법은 번거로운 수작업 분할 대신 사용될 수 있음을 알 수 있었다.

• 한국음향학회지
• /
• 제21권3호
• /
• pp.274-284
• /
• 2002

한국어 대어휘 연속음성인식을 위한 텍스트 전처리에서 띄어쓰기 오류는 잘못된 단어를 인식 어휘에 포함시켜 언어모델의 성능을 저하시킨다. 본 논문에서는 텍스트 코퍼스의 띄어쓰기 교정을 위하여 한국어 음절 N-그램을 이용한 자동 띄어쓰기 알고리듬을 제시한다. 제시된 알고리듬에서는 주어진 입력음절열은 좌에서 우로의 천이만을 갖는 마코프 체인으로 표시되고 어떤 상태에서 같은 상태로의 천이에서 공백음절이 발생하며 다른 상태로의 천이에서는 주어진 음절이 발생한다고 가정한다. 마코프 체인에서 음절 단위 N-그램 언어모델에 의한 문장 확률이 가장 높은 경로를 찾음으로써 띄어쓰기 결과를 얻는다. 모든 공백을 삭제한 254문장으로 이루어진 신문 칼럼 말뭉치에 대하여 띄어쓰기 알고리듬을 적용한 결과 91.58%의 어절단위 정확도 및 96.69%의 음절 정확도를 나타내었다. 띄어쓰기 알고리듬을 응용한 줄바꿈에서의 공백 오류 처리에서 이 알고리듬은 91.00%에서 96.27%로 어절 정확도를 향상시켰으며, 복합명사 분리에서는 96.22%의 분리 정확도를 보였다.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 1998년도 Language, Information and Computation = Selected Papers from the 12th Pacific Asia Conference on Language, Information and Computation, Singapore
• /
• pp.218-229
• /
• 1998