http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Adaptive MCMC-Based Particle Filter for Real-Time Multi-Face Tracking on Mobile Platforms
Na, In Seop,Le, Ha,Kim, Soo Hyung The Korea Contents Association 2014 International Journal of Contents Vol.10 No.3
In this paper, we describe an adaptive Markov chain Monte Carlo-based particle filter that effectively addresses real-time multi-face tracking on mobile platforms. Because traditional approaches based on a particle filter require an enormous number of particles, the processing time is high. This is a serious issue, especially on low performance devices such as mobile phones. To resolve this problem, we developed a tracker that includes a more sophisticated likelihood model to reduce the number of particles and maintain the identity of the tracked faces. In our proposed tracker, the number of particles is adjusted during the sampling process using an adaptive sampling scheme. The adaptive sampling scheme is designed based on the average acceptance ratio of sampled particles of each face. Moreover, a likelihood model based on color information is combined with corner features to improve the accuracy of the sample measurement. The proposed tracker applied on various videos confirmed a significant decrease in processing time compared to traditional approaches.
Automatic Segmentation of Product Bottle Label Based on GrabCut Algorithm
Na, In Seop,Chen, Yan Juan,Kim, Soo Hyung The Korea Contents Association 2014 International Journal of Contents Vol.10 No.4
In this paper, we propose a method to build an accurate initial trimap for the GrabCut algorithm without the need for human interaction. First, we identify a rough candidate for the label region of a bottle by applying a saliency map to find a salient area from the image. Then, the Hough Transformation method is used to detect the left and right borders of the label region, and the k-means algorithm is used to localize the upper and lower borders of the label of the bottle. These four borders are used to build an initial trimap for the GrabCut method. Finally, GrabCut segments accurate regions for the label. The experimental results for 130 wine bottle images demonstrated that the saliency map extracted a rough label region with an accuracy of 97.69% while also removing the complex background. The Hough transform and projection method accurately drew the outline of the label from the saliency area, and then the outline was used to build an initial trimap for GrabCut. Finally, the GrabCut algorithm successfully segmented the bottle label with an average accuracy of 92.31%. Therefore, we believe that our method is suitable for product label recognition systems that automatically segment product labels. Although our method achieved encouraging results, it has some limitations in that unreliable results are produced under conditions with varying illumination and reflections. Therefore, we are in the process of developing preprocessing algorithms to improve the proposed method to take into account variations in illumination and reflections.
Unconstrained Object Segmentation Using GrabCut Based on Automatic Generation of Initial Boundary
Na, In-Seop,Oh, Kang-Han,Kim, Soo-Hyung The Korea Contents Association 2013 International Journal of Contents Vol.9 No.1
Foreground estimation in object segmentation has been an important issue for last few decades. In this paper we propose a GrabCut based automatic foreground estimation method using block clustering. GrabCut is one of popular algorithms for image segmentation in 2D image. However GrabCut is semi-automatic algorithm. So it requires the user input a rough boundary for foreground and background. Typically, the user draws a rectangle around the object of interest manually. The goal of proposed method is to generate an initial rectangle automatically. In order to create initial rectangle, we use Gabor filter and Saliency map and then we use 4 features (amount of area, variance, amount of class with boundary area, amount of class with saliency map) to categorize foreground and background. From the experimental results, our proposed algorithm can achieve satisfactory accuracy in object segmentation without any prior information by the user.
Magnetic Resonance Imaging of Ferumoxytol-Labeled Human Mesenchymal Stem Cells in the Mouse Brain
Lee, Na Kyung,Kim, Hyeong Seop,Yoo, Dongkyeom,Hwang, Jung Won,Choi, Soo Jin,Oh, Wonil,Chang, Jong Wook,Na, Duk L. Springer US 2017 Stem cell reviews and reports Vol.13 No.1
<P>The success of stem cell therapy is highly dependent on accurate delivery of stem cells to the target site of interest. Possible ways to track the distribution of MSCs in vivo include the use of reporter genes or nanoparticles. The U.S. Food and Drug Administration (FDA) has approved ferumoxytol (Feraheme® [USA], Rienso® [UK]) as a treatment for iron deficiency anemia. Ferumoxytol is an ultrasmall superparamagnetic iron oxide nanoparticle (USPIO) that has recently been used to track the fate of transplanted cells using magnetic resonance imaging (MRI). The major objectives of this study were to demonstrate the feasibility of labeling hUCB-MSCs with ferumoxytol and to observe, through MRI, the engraftment of ferumoxytol-labeled human umbilical cord blood-derived mesenchymal stem cells (hUCB-MSCs) delivered via stereotactic injection into the hippocampi of a transgenic mouse model of familial Alzheimer’s disease (5XFAD). Ferumoxytol had no toxic effects on the viability or stemness of hUCB-MSCs when assessed <I>in vitro</I>. Through MRI, hypointense signals were discernible at the site where ferumoxytol-labeled human MSCs were injected. Iron-positive areas were also observed in the engrafted hippocampi. The results from this study support the use of nanoparticle labeling to monitor transplanted MSCs in real time as a follow-up for AD stem cell therapy in the clinical field.</P><P><B>Electronic supplementary material</B></P><P>The online version of this article (doi:10.1007/s12015-016-9694-0) contains supplementary material, which is available to authorized users.</P>
나인섭(Na, In-seop),장우권(Chang, Woo-kwon),이명규(Lee, Myong-gyu) 호남대학교 인문사회과학연구소 2011 인문사회과학연구 Vol.31 No.-
유비쿼터스 인터넷 시대에 모든 정보자원은 디지털화되고 빠르게 확산되고 있다. 또한 민주적 시민의식의 함양은 정확한 정보를 공유함으로써 확산될 수 있다. 정보의 왜곡을 막고 시민들의 정확한 정보교류를 위한 도서관의 역할은 매우 중요하다고 할 수 있다. 이 논문에서는 시민 정보교류 향상을 위한 지역단위도서관통합정보시스템 구축모형 제시를 위해 전국 941개 도서관을 대상으로 설문조사(우편, 전자우편)를 실시하였다. 국내외 도서관의 통합정보시스템 구축 관리 현황 및 인식을 중심으로 조사는 이루어졌으며, 이들 조사결과를 토대로 지역단위도서관통합정보시스템 구축모형을 제시하였다. This study carried out a survey in 941 libraries via e-mail and post mail in order to model an integrated local library information system. The survey was conducted focusing on the status and awareness of the establishment and operation of various integrated library information systems both domestically and internationally. Based on the results of the survey, we proposed a model of a local integrated library information system.
Automatic Segmentation of Product Bottle Label Based on GrabCut Algorithm
In Seop Na,Yan Juan Chen,Soo Hyung Kim 한국콘텐츠학회(IJOC) 2014 International Journal of Contents Vol.10 No.4
In this paper, we propose a method to build an accurate initial trimap for the GrabCut algorithm without the need for human interaction. First, we identify a rough candidate for the label region of a bottle by applying a saliency map to find a salient area from the image. Then, the Hough Transformation method is used to detect the left and right borders of the label region, and the k-means algorithm is used to localize the upper and lower borders of the label of the bottle. These four borders are used to build an initial trimap for the GrabCut method. Finally, GrabCut segments accurate regions for the label. The experimental results for 130 wine bottle images demonstrated that the saliency map extracted a rough label region with an accuracy of 97.69% while also removing the complex background. The Hough transform and projection method accurately drew the outline of the label from the saliency area, and then the outline was used to build an initial trimap for GrabCut. Finally, the GrabCut algorithm successfully segmented the bottle label with an average accuracy of 92.31%. Therefore, we believe that our method is suitable for product label recognition systems that automatically segment product labels. Although our method achieved encouraging results, it has some limitations in that unreliable results are produced under conditions with varying illumination and reflections. Therefore, we are in the process of developing preprocessing algorithms to improve the proposed method to take into account variations in illumination and reflections.