• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.432-435
• /
• 2019

Convolutional Neural Networks (CNNs) have recently been gaining popularity in the medical image analysis field because of their image segmentation capabilities. In this paper, we present a CNN that performs automated brain tumor segmentations of sparsely annotated 3D Magnetic Resonance Imaging (MRI) scans. Our CNN is based on 3D U-net architecture, and it includes separate Dilated and Depth-wise Convolutions. It is fully-trained on the BraTS 2018 data set, and it produces more accurate results even when compared to the winners of the BraTS 2017 competition despite having a significantly smaller amount of parameters.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.44 no.6
• /
• pp.1189-1204
• /
• 2020

Population aging and longevity have compelled major worldwide consumer markets to focus on senior citizens who exhibit a desire to nurture their appearance and obtain related products such as cosmetics. This trend signals an increasing need for in-depth research on elderly consumers in the color cosmetics market. This study identified the characteristics of seniors in the pre-elderly stage ("new seniors") based on their lifestyle and market segments. It employed online surveys with participants consisting of pre-elderly Korean women born between 1955 and 1963 who reside in the greater Seoul and Gyeonggi area. The study used SPSS 23.0 for factor analysis, reliability verification, cluster analysis, ANOVA, Duncan's test, and cross-analysis. The results show that new seniors could be classified into four groups based on lifestyle: Prime Seniors, Potential Seniors, Rational Seniors, and Slump Seniors. Each group has distinct characteristics. The findings suggest that the senior market requires further segmentation and is no longer a single uniform market. This study also confirms that the lifestyles of the elderly is an instrumental variable for their segmentation.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.4
• /
• pp.147-153
• /
• 2018

In this paper, we propose an efficient WBC 14-Diff classification which performs using the WBC-ResNet-152, a type of CNN model. The main point of view is to use Super-pixel for the segmentation of the image of WBC, and to use ResNet for the classification of WBC. A total of 136,164 blood image samples (224x224) were grouped for image segmentation, training, training verification, and final test performance analysis. Image segmentation using super-pixels have different number of images for each classes, so weighted average was applied and therefore image segmentation error was low at 7.23%. Using the training data-set for training 50 times, and using soft-max classifier, TPR average of 80.3% for the training set of 8,827 images was achieved. Based on this, using verification data-set of 21,437 images, 14-Diff classification TPR average of normal WBCs were at 93.4% and TPR average of abnormal WBCs were at 83.3%. The result and methodology of this research demonstrates the usefulness of artificial intelligence technology in the blood cell image classification field. WBC-ResNet-152 based morphology approach is shown to be meaningful and worthwhile method. And based on stored medical data, in-depth diagnosis and early detection of curable diseases is expected to improve the quality of treatment.

• Journal of Sensor Science and Technology
• /
• v.6 no.2
• /
• pp.123-130
• /
• 1997

In this paper, we present an original stereo vision system which comprises two process: 1. An image segmentation algorithm based on new concept called declivity and using automatic thresholds. 2. A new stereo matching algorithm based on an optimal path search. This path is obtained by dynamic programming method which uses the threshold values calculated during the segmentation process. At present, a complete depth map of indoor scene only needs about 3 s on a Sun workstation IPX, and this time will be reduced to a few tenth of second on a specialised architecture based on several DSPs which is currently under consideration.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.1
• /
• pp.120-129
• /
• 1990

In this paper, 3-dimensional object segmentation and classification are proposed. Planar object is segmented surface using jump boundary and internal boundary. Curved object is segmented surfaces by maximin clustering method. Segmented surfaces are classified by depth trends and angle measurement of normal vectors. Classified surfaces are merged according to adjacent surfaces and compared to Guassian curvature and mean curvature method. The proposed methods have been successfully applied to the synthetic range images and shows good classification.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.209-210
• /
• 2007

Obtained disparity map from the stereo camera by using the several stereo matching algorithms carries lots of noise because of various causes. In our approach, mode filtering and noise elimination technique using the histogram and projection-based region merging methods are adopted for improving the quality of disparity map and image segmentation. The proposed algorithms are implemented in VHDL and the real-time experimentation shows the accurately divided objects.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.1129-1132
• /
• 2005

In this paper, we proposed real-time stereoscopic image conversion algorithm using object segmentation and motion parallax. The proposed algorithm separates objects using luminance of image, extracts moving object among objects of the image using motion parallax and generates depth map. Parallax process is done based on the depth map. The proposed method has been evaluated using visual test and APD(Absolute Parallx Difference) for comparing the stereoscopic image of the proposed method with that of MTD. The proposed method offers realistic stereoscopic conversion effect regardless of the direction and velocity of the 2-D image.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.01a
• /
• pp.197-198
• /
• 2012

본 논문에서는 입력되는 스테레오 영상에서 3차원 깊이 정보를 이용하여 객체를 보다 정확하게 분리하는 알고리즘을 제안한다. 제안된 알고리즘은 먼저 촬영된 장면의 왼쪽과 오른쪽 영상으로부터 스테레오 정합 기법을 이용하여 영상의 각 화소에 대한 3차원의 깊이 정보를 추출한다. 그런 다음, 추출된 깊이 정보를 강인하게 이진화하여 배경 영역을 제외하고 전경에 해당하는 객체만을 분리한다. 성능평가를 위한 실험에서는 본 논문에서 제안된 방법을 여러 가지 영상에 적용하여 테스트를 해 보았으며, 제안된 방법이 기존의 2차원 기반의 객체 분리 방법에 비해 보다 강건하고 정확하게 객체를 분리함을 확인하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.07a
• /
• pp.315-317
• /
• 2012

본 논문에서는 인체의 골격 위치와 깊이 정보를 사용하여 주위 환경에 강건한 특성을 지니는 움직이는 사람 영역 검출 방법을 제안한다. 먼저 영상 내에서 인체의 골격 위치를 검출한 다음 인체 골격의 중심이 될 수 있는 지점에 대해 인체의 평균적 깊이 범위 내에서 깊이 세분화를 수행한다. 그리고 깊이 세분화를 통하여 검출된 사람 영역의 후보군에 대해 윤곽선 기반의 움직임 검출기법을 사용하여 후보군 내에서 움직이는 사람에 해당하는 특징점을 검출한다. 마지막으로 잡음 제거 및 움직이는 사람에 해당하는 영역 검출을 위하여 개선된 깊이 세분화 과정을 수행한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.727-730
• /
• 2024

최근 딥러닝 기술이 급속히 발전하며 현대 사회의 다양한 응용분야에서 빠르게 적용되고 있다. 특히 영상 기반의 딥러닝 기술은 자연어 처리와 함께 인공지능 기술의 핵심 연구 분야로 많은 연구가 진행되고 있다. 논문에서는 최근 많은 연구가 진행되고 있는 영상의 의미적 분할 (Semantic Segmentation) 성능을 향상하기 위한 연구를 진행한다. 특히 모델에서 고정밀의 의미적 분할을 수행할 수 있도록 추가적인 정보로써 의사 깊이맵 (Pseudo Depth-Map)을 활용하는 방법을 제안하였다. 더불어, 의사 깊이맵을 모델 상에서 효과적으로 학습시키기 위하여 다중 디코더 모델과 학습 효율을 높이는 학습 스케줄링 전략을 제안한다. 의사 깊이맵과 다중 디코더 모델 기반의 제안 모델은 기존 의미적 분할 모델과 비교하여 iIoU 기준 2%의 성능 향상을 보였다.