• 한국콘텐츠학회논문지
• /
• 제6권9호
• /
• pp.19-27
• /
• 2006

Mean shift 방법은 중심 모드를 찾기 위한 비모수적 통계 방법으로 컬러 영상을 분할하는데 효율적이다. 그러나 입력되는 윈도우 크기에 따라 분할된 결과가 달라지며 윈도우의 크기 값이 작을 경우 많은 영역으로 분할되는 단점이 있다. 본 논문은 이러한 단점을 개선하여 mean shift 알고리즘에 의한 분할 영상이 과도하게 분할되었을 경우 영역 병합 방법을 이용하여 유사 영역을 병합하는 방법을 제안한다. 제안 방법은 과분할된 영상을 HSI 컬러 공간으로 변환하여 색상 정보를 이용하여 유사 영역으로 병합하며 이때 경계 영역을 보존하기 위해 영역 병합 제한자를 이용하여 병합 유무를 결정한다. 그 후 RGB 컬러 공간을 이용하여 HSI 컬러 공간에서 병합되지 않은 영역들을 병합하였다. 실험 결과는 다양한 영상에 대해 주요 영역들의 분할 결과에서 우수한 성능을 보여준다.

• 정보처리학회 논문지
• /
• 제13권3호
• /
• pp.130-139
• /
• 2024

제조 분야 설비 예지보전을 위해서 진동, 전류, 온도 등 물리 데이터를 기반으로 설비 이상을 탐지하는 인공지능 학습 모델이 활용되고 있다. 설비 결함, 고장 등 설비 이상 유형은 매우 다양하므로, 주로 오토인코더 기반 비지도 학습 모델을 이용한 이상 탐지 방법이 적용되고 있다. 설비 상태의 정상, 비정상 여부는 오토인코더의 재구성 오차를 이용해 효과적으로 분류할 수 있지만, 설비 이상의 구체적인 상태를 식별하는 데 한계가 있다. 설비 불균형, 정렬 불량, 고정 불량 등 설비 이상 상황 발생 시, 설비 진동 주파수는 특정 영역에서 정상 상태와 다른 패턴을 나타낸다. 본 논문에서는 전체 진동 주파수 범위를 N개 영역으로 나누어 이상 탐지를 수행하는 N 분할 이상 탐지 방법을 제시하였다. 압축기의 진동 데이터를 이용해 주파수와 강도를 달리한 9종의 이상 데이터를 대상으로 실험한 결과, N 분할을 적용하였을 때 더 높은 이상 탐지 성능을 나타냈다. 제안 방법은 설비 이상 탐지 이후, 설비 이상 구체화에 활용될 수 있다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1989년도 추계학술대회 논문집 학회본부
• /
• pp.415-420
• /
• 1989

This thesis deals with range finding using one camera and laser pointer. Range finding will be used further recognition of the image, that is, range image which allows further segmentation of the scene. In the first step, camera modeling is performed by camera calibration which executes least square fit. Least square fit uses the method of sigular value decomposition. And perspective transform of camera is obtained. Lastly range finding is performed by triangulation principle. The result of this algorithm are displayed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권3호
• /
• pp.1121-1139
• /
• 2015

In texture-plus-depth format, depth map compression is an important task. Different from normal texture images, depth maps have less texture information, while contain many homogeneous regions separated by sharp edges. This feature will be employed to form an efficient depth map coding scheme in this paper. Firstly, the histogram of the depth map will be analyzed to find an appropriate threshold that segments the depth map into the foreground and background regions, allowing the edge between these two kinds of regions to be obtained. Secondly, the two regions will be encoded through rate distortion optimization with a shape adaptive wavelet transform, while the edges are lossless encoded with JBIG2. Finally, a depth-updating algorithm based on the threshold and the depth range is applied to enhance the quality of the decoded depth maps. Experimental results demonstrate the effective performance on both the depth map quality and the synthesized view quality.

• 한국정보통신학회논문지
• /
• 제14권4호
• /
• pp.967-975
• /
• 2010

영상 세그먼테이션은 배경으로부터 객체들을 구별하는 것으로서, 영상 분석과 해석을 하는데 있어서 첫 번째 단계에 해당한다. 그러나 활성 외곽선 모델은 위상이 2개밖에 없으므로 정확하게 원하는 객체들을 추출할 수가 없다. 본 논문에서 원하는 특정한 범위의 명암도를 갖는 객체들을 추출하기 위해서 초기 곡선을 객체들 근처에 구성함으로써 바라는 윤곽을 찾는 방법을 제안한다. 초기 곡선은 히스토그램 평활화, 가우시안 평활화, 임계치를 이용하여 구한다. 제안한 방법은 초기 곡선을 관심영역에 최대 근접시키므로 계산 속도를 줄이고 원하는 영역을 정확하게 추출할 수 있다. CT 영상과 MR 영상에 적용한 결과 제안한 방법이 활성 외곽선 모델보다 더 효과적임을 보였다.

• 한국컴퓨터정보학회논문지
• /
• 제21권11호
• /
• pp.103-111
• /
• 2016

Traditionally, in the hospital the doctors saw the TRUS images by their eyes and manually segmented the boundary between the prostate and nonprostate. But the manually segmenting process not only needed too much time but also had different boundaries according to the doctor. To cope the problems, some automatic segmentations of the prostate have been studied to generate the constant segmentation results and get the belief from patients. Besides, on detecting the boundary, the ones in the middle of all images are easy to find the boundary but the base and apex of the images are hard to do it since there are lots of uncertain boundary. Accurate detection of prostate boundaries is a challenging and difficult task due to weak prostate boundaries, speckle noises and the short range of gray levels. In this paper, we propose the method that extracts a prostate boundary using features of its directions on prostate image. As a result of our experiments, it shows that the boundary never falls short of the existing methods or human expert's segmentation. And also, its searching speed is too fast because the method searches a smaller area that other methods.

• 한국의류학회지
• /
• 제27권6호
• /
• pp.601-611
• /
• 2003

The main objective of this study was to investigate the relationship between benefits segmentation and knitwear purchasing behavior of college female students. A questionnaire was developed to measure benefits segmentation, knit wear purchasing behavior. The questionnaire was administered to 505 college female students in Chonbuk and Chonnam. The data was analyzed using percentage, frequency, mean, factor analysis, cluster analysis and ANOVA, Duncan multiple range test. The results of the study were as follows: The college female students were classified into four subdivisions by the cluster analysis: recreation pursuit group, fashion pursuit group, individuality pursuit group, self-improvement pursuit group on the basis of pursuit benefit factors. The knitwear purchasing motives of consumers were significantly different according to pursuit benefit subdivision. The individuality pursuit group was the highest user of mass media fashion information sources. The fashion pursuit group used purchasing experience and advice of others less than other groups. Consumers' evaluation criteria of knitwear products were significantly different depending on pursuit benefit subdivision in design and coordination, goods traits, practicality, individual expression, and external criterion. The other groups used purchasing experience and advice of others more than the fashion pursuit group.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4395-4412
• /
• 2020

The multisource image fusion has become an active topic in the last few years owing to its higher segmentation rate. To enhance the accuracy of multimodal pig-body feature segmentation, a multisource image fusion method was employed. Nevertheless, the conventional multisource image fusion methods can not extract superior contrast and abundant details of fused image. To superior segment shape feature and detect temperature feature, a new multisource image fusion method was presented and entitled as NSST-GF-IPCNN. Firstly, the multisource images were resolved into a range of multiscale and multidirectional subbands by Nonsubsampled Shearlet Transform (NSST). Then, to superior describe fine-scale texture and edge information, even-symmetrical Gabor filter and Improved Pulse Coupled Neural Network (IPCNN) were used to fuse low and high-frequency subbands, respectively. Next, the fused coefficients were reconstructed into a fusion image using inverse NSST. Finally, the shape feature was extracted using automatic threshold algorithm and optimized using morphological operation. Nevertheless, the highest temperature of pig-body was gained in view of segmentation results. Experiments revealed that the presented fusion algorithm was able to realize 2.102-4.066% higher average accuracy rate than the traditional algorithms and also enhanced efficiency.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권10호
• /
• pp.2788-2808
• /
• 2023

Brain tumors are one of the most threatening malignancies for humans. Misdiagnosis of brain tumors can result in false medical intervention, which ultimately reduces a patient's chance of survival. Manual identification and segmentation of brain tumors from Magnetic Resonance Imaging (MRI) scans can be difficult and error-prone because of the great range of tumor tissues that exist in various individuals and the similarity of normal tissues. To overcome this limitation, the Amended Convolutional Neural Network (ACNN) model has been introduced, a unique combination of three techniques that have not been previously explored for brain tumor detection. The three techniques integrated into the ACNN model are image tissue preprocessing using the Kalman Bucy Smoothing Filter to remove noisy pixels from the input, image tissue segmentation using the Isotonic Regressive Image Tissue Segmentation Process, and feature extraction using the Marr Wavelet Transformation. The extracted features are compared with the testing features using a sigmoid activation function in the output layer. The experimental findings show that the suggested model outperforms existing techniques concerning accuracy, precision, sensitivity, dice score, Jaccard index, specificity, Positive Predictive Value, Hausdorff distance, recall, and F1 score. The proposed ACNN model achieved a maximum accuracy of 98.8%, which is higher than other existing models, according to the experimental results.

• 한국전자파학회:학술대회논문집
• /
• 한국전자파학회 2002년도 종합학술발표회 논문집 Vol.12 No.1
• /
• pp.324-327
• /
• 2002

For the characterization of arbitrary shaped printed circuit board, lossy transmission line grid model based on SPICE netlist and analytical plane model based on the segmentation method are proposed in this paper. Two methods are compared with an arbitrary shaped power/ground plane. Furthermore, design considerations for the complete power distribution network structure are discussed to ensure the maximum value of the PDN impedance is low enough across the desired frequency range and to guide decoupling capacitor selection.