• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.35-39
• /
• 2009

In the hydraulic room of a forging press machine, a system which can detect and prevent risks at its early stage is needed because there may be a leakage due to the damage of the connection parts of the piping which can endanger human life and mechanical damage. In this paper, the system to automatically recognize a leakage of hydraulic fluid by the pan/tilt camera from a remote place is implemented. It finds the Minimum Boundary Rectangles(MBR) which are recognized with candidate leakage regions in the process of labeling and detects the proper leakage regions of hydraulic fluid with the width and height of MBRs and the area ratios of the MBRs and the candidate leakage regions. The experimental results show that the proposed system has been verified to detect the leakage regions accurately in various light conditions.

• Bulletin of the Korean Chemical Society
• /
• v.35 no.8
• /
• pp.2367-2370
• /
• 2014

"Cat's eye"-shaped $[^{57}Co]CoO@SiO_2$ core-shell nanostructure was prepared by the reverse microemulsion method combined with radioisotope technique to investigate a potential imaging agent for a single photon emission computed tomography (SPECT) in nuclear medicine. The core cobalt oxide nanorods were obtained by thermal decomposition of $Co-(oleate)_2$ precursor from radio isotope Co-57 containing cobalt chloride and sodium oleate. The $SiO_2$ coating on the surface of the core cobalt oxide nanorods was produced by hydrolysis and a condensation reaction of tetraethylorthosilicate (TEOS) in the water phase of the reverse microemulsion system. In vivo test, micro SPECT image was acquired with nude mice after 30 min of intravenous injection of $[^{57}Co]CoO@SiO_2$ core-shell nanostructure.

• Journal of Korea Multimedia Society
• /
• v.7 no.1
• /
• pp.27-34
• /
• 2004

This thesis proposes a face detection algorithm using the color and edge informations in color image. The proposed algorithm segments skin color by Cb and Cr in YCbCr coordinates. Then face candidate regions are made after morphological filtering and labeling. For the regions, the Sobel vortical operation and horizontal projection are performed in the Y luminance components. The peak value indicates the eye location. Similarly, the chin location is detected by the Sobel horizontal operation and horizontal projection. The computer simulation shows that the proposed method gains similar detection rates of previous method and prevent facial region from including neck by detection of chin.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.24 no.6
• /
• pp.1027-1033
• /
• 2010

This study aimed to evaluate the effects of Astragali radix on brain edema of intracerebral hemorrhage(ICH)-induced rats. Brain edema following ICH was induced via the stereotaxic intrastriatal injection of bacterial collagenase type VII in Sprague-Dawley rats. Ethanol extract of Astragli radix was treated once a day for 3 days. Then brain hematoma volume and edema were examined. Immunohistochemistry was processed for iNOS, c-Fos, Bax, and HSP72 expressions in the brain sections and each immuno-labeling were calculated with image analysis. Ethanol extract of Astragli radix reduced hematoma volume(not significantly) and brain edema(significantly) ICH induced rats. Ethanol extract of Astragli radix reduced iNOS expressions, c-Fos, Bax and HSP72 positive cells significantly and reduced apoptotic bodies and swollen neurons in ICH induced rat brain. These results suggest that Astragli radix plays an inhibitory role in the hemorrhagic, inflammatory and apoptotic events induced by ICH. And it is supposed that neuroprotective effect of Astragli radix reveals by anti-apoptosis mechanism.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.3
• /
• pp.477-486
• /
• 2016

This paper presents the area classification, identification, and tracking for multiple moving objects with the similar colors. To do this, first, we use the GMM(Gaussian Mixture Model)-based background modeling method to detect the moving objects. Second, we propose the use of the binary and morphology of image in order to eliminate the shadow and noise in case of detection of the moving object. Third, we recognize ROI(region of interest) of the moving object through labeling method. And, we propose the area classification method to remove the background from the detected moving objects and the novel method for identifying the classified moving area. Also, we propose the method for tracking the identified moving object using Kalman filter. To the end, we propose the effective tracking method when detecting the multiple objects with the similar colors. Finally, we demonstrate the feasibility and applicability of the proposed algorithms through some experiments.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.613-618
• /
• 2021

Facial expression recognition has long been established as a subject of continuous research in various fields. In this paper, the relationship between each landmark is analyzed using the features obtained by calculating the distance between the facial landmarks in the image, and five facial expressions are classified. We increased data and label reliability based on our labeling work with multiple observers. In addition, faces were recognized from the original data and landmark coordinates were extracted and used as features. A genetic algorithm was used to select features that are relatively more helpful for classification. We performed facial recognition classification and analysis with the method proposed in this paper, which shows the validity and effectiveness of the proposed method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.8
• /
• pp.2787-2800
• /
• 2022

The aging society increases emergency situations of the elderly living alone and a variety of social crimes. In order to prevent them, techniques to detect emergency situations through voice are actively researched. This study proposes CutPaste-based anomaly detection model using multi-scale feature extraction in time series streaming data. In the proposed method, an audio file is converted into a spectrogram. In this way, it is possible to use an algorithm for image data, such as CNN. After that, mutli-scale feature extraction is applied. Three images drawn from Adaptive Pooling layer that has different-sized kernels are merged. In consideration of various types of anomaly, including point anomaly, contextual anomaly, and collective anomaly, the limitations of a conventional anomaly model are improved. Finally, CutPaste-based anomaly detection is conducted. Since the model is trained through self-supervised learning, it is possible to detect a diversity of emergency situations as anomaly without labeling. Therefore, the proposed model overcomes the limitations of a conventional model that classifies only labelled emergency situations. Also, the proposed model is evaluated to have better performance than a conventional anomaly detection model.

• Journal of Radiopharmaceuticals and Molecular Probes
• /
• v.6 no.2
• /
• pp.69-74
• /
• 2020

PIB is the first amyloid plaque PET image tracer reported for the first time in 2003, and is considered to be the best and is still being utilized due to its very high uptake and kinetic properties. Initially, it was synthesized by radioisotope labeling using a precursor containing a methoxy methyl protection group, but now it is synthesized using a 6-OH precursor that can be easily synthesized in one step using [¹¹C]methyl triflate. Carbon-11 has several limitations in clinical studies using PET because its half-life is as short as 20 minutes. In this study, in order to overcome the difficulty of this half-life, a rapid method using Sep-Pak was adopted instead of HPLC purification to significantly reduce the burden of the purification process and attempted synthesis. As a result, the synthesis time was shortened by more than 50%, and the yield of the final compound was higher than the previous result and showed relatively high specific radioactivity, confirming that it is a strategic method with high applicability for various precursors having primary amines.

• Journal of Korea Multimedia Society
• /
• v.25 no.4
• /
• pp.600-609
• /
• 2022

In supervised learning, labeling of all data is essential, and in particular, in the case of object detection, all objects belonging to the image and to be learned have to be labeled. Due to this problem, continual learning has recently attracted attention, which is a way to accumulate previous learned knowledge and minimize catastrophic forgetting. In this study, a continaul learning model is proposed that accumulates previously learned knowledge and enables learning about new objects. The proposed method is applied to CenterNet, which is a object detection model of anchor-free manner. In our study, the model is applied the knowledge distillation algorithm to be enabled continual learning. In particular, it is assumed that all output layers of the model have to be distilled in order to be most effective. Compared to LWF, the proposed method is increased by 23.3%p mAP in 19+1 scenarios, and also rised by 28.8%p in 15+5 scenarios.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.602-605
• /
• 2021

최근 인공지능 연구가 활발히 진행되고 있는 가운데 국내외에서 오픈 데이터셋을 제공하고 있어 기술개발이 가속화되고 있다. 데이터셋은 지도학습을 위한 학습데이터로 라벨링 데이터를 포함하고 있어 다양한 라벨링 기능이 적용된 도구 개발이 필요하다. 본 논문에서는 의료영상의 라벨링 데이터를 정교하고 빠르게 생성하기 위한 라벨링 웹 애플리케이션에 대해서 기술한다. 이를 구현하기 위해서 Back Projection, Grabcut 기법을 이용한 반자동 방식과 기계학습 모델을 통해서 예측한 자동 방식의 라벨링 기능을 구현하였다. 이와 관련하여 라벨링 기능별 수행 결과를 근감소증 진단을 위한 영상 라벨링 수행결과와 정량분석 결과를 보였다.