• Journal of Internet of Things and Convergence
• /
• v.9 no.1
• /
• pp.97-104
• /
• 2023

This paper is related to object segmentation using ESRGAN(Enhanced Super Resolution GAN) and SSS(Semantic Soft Segmentation). The segmentation performance of the object segmentation method using Mask R-CNN and SSS proposed by the research team in this paper is generally good, but the segmentation performance is poor when the size of the objects is relatively small. This paper is to solve these problems. The proposed method aims to improve segmentation performance of small objects by performing super-resolution through ESRGAN and then performing SSS when the size of an object detected through Mask R-CNN is below a certain threshold. According to the proposed method, it was confirmed that the segmentation characteristics of small-sized objects can be improved more effectively than the previous method.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.5
• /
• pp.17-23
• /
• 2018

The rapid development of mobile technology has increased the use of mobile devices, and the possibility of security incidents is also increasing. The leakage of information through photos is the most representative. Previous methods for preventing this are disadvantageous in that they can not take pictures for other purposes. In this paper, we design and implement a system to prevent information leakage through photos using object recognition and beacon. The system inspects pictures through object recognition based on deep learning and verifies whether security policies are violated. In addition, the location of the mobile device is identified through the beacon and the appropriate rules are applied. Web applications for administrator allow you to set rules for taking photos by location. As soon as a user takes a photo, they apply appropriate rules to the location to automatically detect photos that do not conform to security policies.

• Journal of Internet of Things and Convergence
• /
• v.6 no.2
• /
• pp.37-43
• /
• 2020

The paper proposed the method of calculating the latest approach angle that can reliably recognize multiple laser images even with the change in separation distance between screen and laser launch device. This method recognizes the angle of the laser pattern angle by using the distance of the laser pattern angle, and the angle extraction of the laser detects the laser image from the acquired image using the labeling algorithm, and performs the huff conversion to extract the angle of the straight line. The distance of the reference angle and angle of the laser image extracted using Euclidean distance among similarity scales is calculated, and the furnace is recognized using the calculated distance result value. Experiments with changing the separation distance to "200 cm to 400 cm" showed 100% recognition of individual strands at all separation distances. The experiment confirmed the reliability of the proposed method.

• Korean Journal of Veterinary Research
• /
• v.33 no.4
• /
• pp.605-609
• /
• 1993

Active metabolites in rat bile after an intravenous injection of $[^3H]$ pteroylglutamic acid(PteGlu)were studies using high-performance liquid chromatography(HPLC). Predominant four radioactive metabolites and parent compound PteGlu were detected on the chromatogram of HPLC with liquid scintillation counting system. These metabolites were identified as tetrahydrofolate, 10-formyltetrahydrofolate, 5-methyltetrahydrofolate and para-aminobenzoyl glutamate. The identification of active folate metabolites was based on the consistency of retention time profiles and hydrodynamic voltammograms which were obtained by HPLC with the electrochemical detection system, and characteristics of UV absorbance spectra obtained by HPLC with photodiode array detection system.

• Journal of Internet Computing and Services
• /
• v.3 no.6
• /
• pp.13-24
• /
• 2002

This paper presents an automatic approach to detect face and facial feature from face images based on the color information and deformable model. Skin color information has been widely used for face and facial feature diction since it is effective for object recognition and has less computational burden, In this paper, we propose how to compensates varying light condition and utilize the transformed YCbCr color model to detect candidates region of face and facial feature from color images, Moreover, the detected face facial feature areas are subsequently assigned to a initial condition of active contour model to extract optimal boundaries of face and facial feature by resolving initial boundary problem when the active contour is used, The experimental results show the efficiency of the proposed method, The face and facial feature information will be used for face recognition and facial feature descriptor.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2015.08a
• /
• pp.199.2-199.2
• /
• 2015

전이금속 칼코겐화합물(TMD)은 2차원 박막 물질로, 그래핀과 함께 차세대 사물인터넷에 적용할 수 있는 전자소자의 소재로 활용될 것으로 기대되고 있다. 특히 TMD는 그래핀과 다르게 1.2 eV 이상의 넓은 밴드갭을 지녀, 기존 실리콘 기반 반도체 소자를 대체할 차세대 물질로 각광받고 있다. TMD는 또한 실리콘 등의 3차원 반도체보다 광전효율이 뛰어나며, 이를 활용한 광전소자의 개발 및 연구가 활발히 진행되고 있다. 그러나 TMD는 그 두께가 나노미터 단위로 매우 얇아 광흡수율이 매우 떨어지는 단점이 있다. 우리는 이러한 TMD 기반 광전소자의 광흡수율을 향상시키기 위해 광전효율이 매우 뛰어난 페로브스카이트(Perovskite)를 TMD 채널 위에 덮음으로써, 이종접합 광전소자를 구현하였다. TMD 물질은 이황화 몰리브데넘($MoS_2$)을 선택하였으며, 광흡수층으로 선택한 페로브스카이트는 $MAPbI_3$을 스핀 코팅을 통해 TMD 채널 층에 접합하였다. 우리는 Photoluminescence 및 UV-Vis 측정을 통해 페로브스카이트 및 페로브스카이트/$MoS_2$ 층의 광특성을 측정하여 페로브스카이트에서 생성된 광캐리어가 확산되어 $MoS_2$에 전달되는 것을 확인하였다. 우리는 추가로 4가지 서로 다른 파장대의 레이저(520, 655, 785, 850 nm)를 이용하여 페로브스카이트 광흡수층이 있을 때와 없을 때의 $MoS_2$ 광검출기의 성능 변화를 관찰하였다.

• Journal of Broadcast Engineering
• /
• v.22 no.2
• /
• pp.234-239
• /
• 2017

A real-time violence detection algorithm based on a new descriptor using the magnitude and direction changes of movement in images is proposed. The descriptor was developed from the observation that the changes of violent actions are much larger than those of normal movements. Descriptor feature vectors consisting of descriptor values during several frames are obtained and these are inputs to SVM(Support Vector Machine) classifier for discriminating violence actions from and non-violence actions. Comparison experiments between the ViF(Violent Flow) and the proposed algorithm were conducted with three different types of datasets. The experimental results show that the proposed algorithm outperforms the ViF in every case.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.86-88
• /
• 2013

Theft is secretly steal things of others. And theft tell the person who secretly stealing, bandits, stealing one's things. In modern society, theft is one of the crimes that occur frequently in the elevator. In this paper, theft crime is extracted using a ${\chi}^2$ histogram of scene change detection method. Extracted images are submitted as evidence for the action on the merits the court.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.05a
• /
• pp.137-140
• /
• 2003

캐리커처의 일반적인 의미는 어떤 사람이나 사물의 특징을 추출하여 익살스럽게 풍자한 그림이나 글이다. 다시 말해, 캐리커처는 사람의 얼굴에서 특징을 잡아 과장하거나 왜곡하여 그린 데생이라고 한다. 컴퓨터를 이용한 기존의 캐리커처 제작방법으로는, 입력 이미지 좌표의 통계적인 차이값을 이용하는 PICASSO System 방법[1], 제작자의 애매한 느낌을 퍼지 논리를 이용하여 표현하는 방법, 이미지를 와핑하는 방법, 여러 단계의 벡터 필드 변환을 이용하는 방법등이 연구되어 왔다. 본 논문에서는 실시간 또는 준비된 영상을 입력으로 받아 저장한 후, 네 단계의 과정으로 처리한 후 최종적으로 캐리커처된 이미지를 생성하게 된다. 각 단계별 처리 내용으로는 첫번째 단계에서는 영상에서 얼굴을 검출하고 두번째 단계에서는 특정 얼굴부위의 기하학적 정보를 좌표값으로 추출한다. 세번째 단계에서는 전 단계에서 얻은 좌표값으로 로컬 와핑 기법을 이용하여 영상을 변환한다. 네 번째 단계에서는 변형된 영상으로 퍼지 논리를 이용하여 보다 개선된 윤곽선 이미지로 변환하여 캐리커처 이미지를 얻는다. 본 논문에서는 영상 인식, 변환 및 윤곽선 검출 및 둥의 여러 가지 영상 처리 기법을 이용하여 기존의 캐리커처 제작 방식보다 간단하고, 복잡한 연산 과정이 없는 캐리커처 제작 시스템을 구현하였다.

• Journal of Convergence for Information Technology
• /
• v.8 no.3
• /
• pp.193-198
• /
• 2018

Recently, the casualties of automobile traffic accidents are rapidly increasing, and serious accidents involving serious injury and death are increasing more than those of ordinary people. More than 70% of major accidents occur in drowsy driving. Therefore, in this paper, we studied the drowsiness prevention system to prevent large-scale disasters of traffic accidents. In this paper, we propose a real-time flicker recognition method for drowsy driving detection system and drowsy recognition according to the increase of carbon dioxide. The drowsy driving detection system applied the existing image detection and the deep running, and the carbon dioxide detection was developed based on the IoT. The drowsy prevention system using both of these techniques improved the accuracy compared to the existing products.