• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.733-735
• /
• 2018

최근의 차량 주차관리 시설, 출입통제가 필요한 장소 그리고 도로 방범카메라를 통한 단속 등 다양한 곳에서 차량 번호판 자동 인식 기술들이 활용되고 있다. 하지만 현재 사용되고 있는 LPR(License Plate Recognition) 시스템에는 많은 장비와 비용이 들어간다는 큰 단점이 존재한다. 본 논문에서는 하나의 컴퓨터와 최소의 카메라를 가지고 할 수 있는 기계학습을 통한 영상처리를 제안하려 한다. 먼저 딥러닝 프레임워크 중 하나인 YOLO(You Only Look Once) [4]를 활용하여 자동차의 번호판 부분의 영역을 검출하고 Grayscale를 통해 햇빛 또는 조명 등의 영향을 감소시켜 번호판의 특징을 보존시킨다. 전처리 작업이 끝난 후 번호판에서 숫자를 인식 하는 부분에서는 k-NN(k-Nearest Neighbor) 알고리즘을 사용하였으며 한글 문자 인식부분은 Template Matching을 이용하였다. 제안한 알고리즘을 사용하여 기존 LPR 시스템에서 획득한 차량이미지를 대상으로 시뮬레이션 한 결과 좋은 결과를 얻을 수 있어 향후 연구 방향의 시스템 확장성의 가능성을 발견할 수 있었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.220-223
• /
• 2020

초해상화란, 저해상도의 영상으로부터 고해상도 영상을 복원하는 이미지 처리 기법이다. 최근 영상 출력 장치의 발전으로 고해상도의 영상을 출력할 장치는 많아지는 한편, 이에 맞는 고해상도 영상을 찍을 영상 기록 장치의 보급은 이에 비해 부족한 실정이다. 따라서 저해상도의 영상을 고해상도 영상으로 변환하는 초해상화 연구는 많은 분야에서 활용되고 있다. 문화재 영상에서의 초해상화는 특히 기존 문화재의 질감, 무늬 등을 보존해야하기 때문에 정교한 초해상화 과정이 요구된다. 본 논문에서는 문화재 영상의 초해상화 과정에 집중해, 기존 문화재의 질감, 무늬 등을 잘 보존하면서 영상 데이터의 양이 상대적으로 적은 경우에도 활용 가능한 기계학습 기범, GLM-SI를 이용한 문화재 영상 초해상화 방법을 제안한다. GLM-SI 를 사용한 초해상화 결과, 문화재 영상에서 선행 방법인 SI 에 비하여 4 배 초해상화에서 PSNR 0.12dB, SSIM 0.017, 8 배 초해상화에서 PSNR 0.23dB, 0.033 의 성능적 향상을 얻을 수 있었다.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1423-1429
• /
• 2019

Recently, a system that supports efficient interaction, a human machine interface (HMI), has become a hot topic. In this paper, we propose a new real time low-cost hand gesture control system as one of vehicle interaction methods. In order to reduce computation time, depth information was acquired using a time-of-flight (TOF) camera because it requires a large amount of computation when detecting hand regions using an RGB camera. In addition, fourier descriptor were used to reduce the learning model. Since the Fourier descriptor uses only a small number of points in the whole image, it is possible to miniaturize the learning model. In order to evaluate the performance of the proposed technique, we compared the speeds of desktop and raspberry pi2. Experimental results show that performance difference between small embedded and desktop is not significant. In the gesture recognition experiment, the recognition rate of 95.16% is confirmed.

• The Journal of the Korea Contents Association
• /
• v.21 no.3
• /
• pp.23-32
• /
• 2021

Semantic image segmentation technology in the field of computer vision is a technology that classifies an image by dividing it into pixels. This technique is also rapidly improving performance using a machine learning method, and a high possibility of utilizing information in units of pixels is drawing attention. However, this technology has been raised from the early days until recently for 'lack of detailed segmentation' problem. Since this problem was caused by increasing the size of the label map, it was expected that the label map could be improved by using the edge map of the original image with detailed edge information. Therefore, in this paper, we propose a post-processing algorithm that maintains semantic image segmentation based on learning, but modifies the resulting label map based on the edge map of the original image. After applying the algorithm to the existing method, when comparing similar applications before and after, approximately 1.74% pixels and 1.35% IoU (Intersection of Union) were applied, and when analyzing the results, the precise targeting fine segmentation function was improved.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.4
• /
• pp.157-163
• /
• 2022

Recently, with the development of automation in the industrial field, research on anomaly detection is being actively conducted. An application for anomaly detection used in factory automation is camera-based defect inspection. Vision camera inspection shows high performance and efficiency in factory automation, but it is difficult to overcome the instability of lighting and environmental conditions. Although camera inspection using deep learning can solve the problem of vision camera inspection with much higher performance, it is difficult to apply to actual industrial fields because it requires a huge amount of normal and abnormal data for learning. Therefore, in this study, we propose a network that overcomes the problem of collecting abnormal data with 72 geometric transformation deep learning methods using only normal data and adds an outlier exposure method for performance improvement. By applying and verifying this to the MVTec data set, which is a database for auto-mobile parts data and outlier detection, it is shown that it can be applied in actual industrial sites.

• Proceedings of the Korean Vacuum Society Conference
• /
• 1999.07a
• /
• pp.53-53
• /
• 1999

전계방출을 이용한 평판 표시장치는 CRT가 가진 장점을 모두 갖는 동시에 얇고 가벼우며 낮은 전력소모로 완벽한 색을 구현할 수 있는 차세대 표시장치로서 이에 대한 여국가 활발히 이루어지고 있다. 여기에 사용되는 음극물질로서 실리콘이나 몰리 등을 팁모양으로 제작하여 사용해 왔다. 하지만 잔류가스에 의한 역스퍼터링이나 화학적 반응에 의해서 전계방출 성능이 점차 저하되는 등의 해결해야할 많은 문제가 있다. 이러한 문제들을 해결하기 위하여 탄소계 재료로서 다이아몬드, 다이아몬드상 카본 등을 이용하려는 노력이 진행되어 왔다. 이중 유리화 비정형 탄소는 다량의 결함을 가지고 있는 유리질의 고상 탄소 재로로서, 전기전도도가 우수하면서 outgassing이 적고 기계적 강도가 뛰어나며 고온에서도 화학적으로 안정하여 전계방출 소자의 음극재료로서 알맞은 것으로 생각된다. 유리화 비정형 탄소가루를 전기영동법으로 기판에 코팅하여 전계방출 소자를 제작하였다. 전기영동 용액으로 이소프로필알코올에 질산마그네슘과 소량의 증류수, 유리화 비정형 탄소분말을 섞어주었고 기판으로는 몰리(Mo)가 증착된 유리를 사용하였다. 균일한 증착을 위해서 증착후 역전압을 걸어 주는 방법과 증착 후 플라즈마 처리를 하는 등의 여러 가지 방법을 사용했다. 전계방출 전류는 1$\times$10-7Torr이사에서 측정하였다. 1회 제작된 용액으로 반복해서 증착한 횟수에 따라 표면의 거치기, 입자의 분포, 전계방출 측정 결과 등의 차이가 관찰되었다. 발광이미지는 전압에 따라 변화하였고, 균일한 발광을 관찰하기 위해서 오랜 시간동안 aging 과정을 거쳐야 했다. 그리고 구 모양의 양극을 사용해서 위치를 변화시키며 시동 전기장을 관찰하여 위치에 따른 전계방출의 차이를 조사하여 발광의 균일성을 알 수 있었다.on microscopy로 분석하였으며 구조 분석은 X-선 회절분석, X-ray photoelectron spectroscopy 그리고Auger electron spectroscope로 하였다. 증착된 산화바나듐 박막의 전기화학적 특성을 분석하기 위하여 리튬 메탈을 anode로 하고 EC:DMC=1:1, 1M LiPF6 액체 전해질을 사용한 Half-Cell를 구성하여 200회 이상의 정전류 충 방전 시험을 행하였다. Half-Cell test 결과 박막의 결정성과 표면상태에 따라 매우 다른 전지 특성을 나타내었다.도상승율을 갖는 경우가 다른 베이킹 시나리오 모델에 비해 효과적이라 생각되며 초대 필요 공급열량은 200kW 정도로 산출되었다. 실질적인 수치를 얻기 위해 보다 고차원 모델로의 해석이 필요하리라 생각된다. 끝으로 장기적인 관점에서 KSTAR 장치의 베이킹 계획도 살펴본다.습파라미터와 더불어, 본 연구에서 새롭게 제시된 주기분할층의 파라미터들이 모형의 학습성과를 높이기 위해 함께 고려된다. 한편, 이러한 학습과정에서 추가적으로 고려해야 할 파라미터 갯수가 증가함에 따라서, 본 모델의 학습성과가 local minimum에 빠지는 문제점이 발생될 수 있다. 즉, 웨이블릿분석과 인공신경망모형을 모두 전역적으로 최적화시켜야 하는 문제가 발생한다. 본 연구에서는 이 문제를 해결하기 위해서, 최근 local minimum의 가능성을 최소화하여 전역적인 학습성과를 높여 주는 인공지능기법으로서 유전자알고리즘기법을 본 연구이 통합모델에 반영하였다. 이에 대한 실증사례 분석결과는 일일 환율예측문제를 적용하였을 경우, 기존의 방법론보다 더 나운 예측성과를 타나내었다.pective" to workflow architectural discussions. The vocabulary suggested

• Cartoon and Animation Studies
• /
• s.36
• /
• pp.237-257
• /
• 2014

This study is the process of performing the interdisciplinary fusion study between multiple fields by identifying the status on the previous artistic education considering the brain scientific mechanism of image creativity and brain-based learning principles. In recent years, producing the educational methods of each field as the fusion study activities are emerging as the trend and thanks to such, the results of brain-based educational fusion studies are being presented for each field. It includes artistic fields such as music, art and dance. In other words, the perspective is that by understanding the operating principles of the brain while creativity and learning is taking place, when applying various principles that can develop the corresponding functions as a teaching method, it can effectively increase the artistic performance ability and creativity. Since the animation drawing should be able to intuitively recognize the elements of movement and produce the communication with the target beyond the delineative perspective of simply drawing the objects to look the same, it requires the development of systematic educational method including the methods of communication, elements of higher cognitive senses as well as the cognitive perspective of form implementation. Therefore, this study proposes a literature study results on the artistic education applied with brain-based principles in order to design the educational model considering the professional characteristics of animation drawing. Therefore, the overseas and domestic trends of the cases of brain-based artistic education were extracted and analyzed. In addition, the cases of artistic education studies applied with brain-based principles and study results from cases of drawing related education were analyzed. According to the analyzed results, the brain-based learning related to the drawing has shown a common effect of promoting the creativity and changes of positive emotion related to the observation, concentration and image expression through the training of the right brain. In addition, there was a case of overseas educational application through the brain wave training where the timing ability and artistic expression have shown an enhancement effect through the HRV training, SMR, Beta 1 and neuro feedback training that strengthens the alpha/seta wave and it was proposing that slow brain wave neuro feedback training contributes significantly in overcoming the stress and enhancing the creative artistic performance ability. The meaning of this study result is significant in the fact that it was the case that have shown the successful application of neuro feedback training in the environment of artistic live education beyond the range of laboratory but the use of the machine was shown to have limitations for being applied to the teaching methods so its significance can be found in providing the analytical foundation for applying and designing the brain-based learning principles for future animation drawing teaching methods.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.7
• /
• pp.271-278
• /
• 2021

As the current cyber attacks become more intelligent, the existing Intrusion Detection System is difficult for detecting intelligent attacks that deviate from the existing stored patterns. In an attempt to solve this, a model of a deep learning-based intrusion detection system that analyzes the pattern of intelligent attacks through data learning has emerged. Intrusion detection systems are divided into host-based and network-based depending on the installation location. Unlike network-based intrusion detection systems, host-based intrusion detection systems have the disadvantage of having to observe the inside and outside of the system as a whole. However, it has the advantage of being able to detect intrusions that cannot be detected by a network-based intrusion detection system. Therefore, in this study, we conducted a study on a host-based intrusion detection system. In order to evaluate and improve the performance of the host-based intrusion detection system model, we used the host-based Leipzig Intrusion Detection-Data Set (LID-DS) published in 2018. In the performance evaluation of the model using that data set, in order to confirm the similarity of each data and reconstructed to identify whether it is normal data or abnormal data, 1D vector data is converted to 3D image data. Also, the deep learning model has the drawback of having to re-learn every time a new cyber attack method is seen. In other words, it is not efficient because it takes a long time to learn a large amount of data. To solve this problem, this paper proposes the Siamese Convolutional Neural Network (Siamese-CNN) to use the Few-Shot Learning method that shows excellent performance by learning the little amount of data. Siamese-CNN determines whether the attacks are of the same type by the similarity score of each sample of cyber attacks converted into images. The accuracy was calculated using Few-Shot Learning technique, and the performance of Vanilla Convolutional Neural Network (Vanilla-CNN) and Siamese-CNN was compared to confirm the performance of Siamese-CNN. As a result of measuring Accuracy, Precision, Recall and F1-Score index, it was confirmed that the recall of the Siamese-CNN model proposed in this study was increased by about 6% from the Vanilla-CNN model.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.3
• /
• pp.55-65
• /
• 2022

Recently, deep learning-based automated systems for identifying and detecting landmarks have been proposed. In order to train such a deep learning-based model without overfitting, a large amount of image and labeling data is required. Conventionally, an experienced reader manually identifies and labels landmarks in a patient's image. However, such measurement is not only expensive, but also has poor reproducibility, so the need for an automated labeling method has been raised. In addition, in the X-ray image, since various human tissues on the path through which the photons pass are displayed, it is difficult to identify the landmark compared to a general natural image or a 3D image modality image. In this study, we propose a geometric data augmentation technique that enables the generation of a large amount of labeling data in X-ray images. In addition, the optimal attention mechanism for landmark detection was presented through the implementation and application of various attention techniques to improve the detection performance of 16 major landmarks in the skull. Finally, among the major cranial landmarks, markers that ensure stable detection are derived, and these markers are expected to have high clinical application potential.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.1-23
• /
• 2018

From the 21st century, various high-quality services have come up with the growth of the internet or 'Information and Communication Technologies'. Especially, the scale of E-commerce industry in which Amazon and E-bay are standing out is exploding in a large way. As E-commerce grows, Customers could get what they want to buy easily while comparing various products because more products have been registered at online shopping malls. However, a problem has arisen with the growth of E-commerce. As too many products have been registered, it has become difficult for customers to search what they really need in the flood of products. When customers search for desired products with a generalized keyword, too many products have come out as a result. On the contrary, few products have been searched if customers type in details of products because concrete product-attributes have been registered rarely. In this situation, recognizing texts in images automatically with a machine can be a solution. Because bulk of product details are written in catalogs as image format, most of product information are not searched with text inputs in the current text-based searching system. It means if information in images can be converted to text format, customers can search products with product-details, which make them shop more conveniently. There are various existing OCR(Optical Character Recognition) programs which can recognize texts in images. But existing OCR programs are hard to be applied to catalog because they have problems in recognizing texts in certain circumstances, like texts are not big enough or fonts are not consistent. Therefore, this research suggests the way to recognize keywords in catalog with the Deep Learning algorithm which is state of the art in image-recognition area from 2010s. Single Shot Multibox Detector(SSD), which is a credited model for object-detection performance, can be used with structures re-designed to take into account the difference of text from object. But there is an issue that SSD model needs a lot of labeled-train data to be trained, because of the characteristic of deep learning algorithms, that it should be trained by supervised-learning. To collect data, we can try labelling location and classification information to texts in catalog manually. But if data are collected manually, many problems would come up. Some keywords would be missed because human can make mistakes while labelling train data. And it becomes too time-consuming to collect train data considering the scale of data needed or costly if a lot of workers are hired to shorten the time. Furthermore, if some specific keywords are needed to be trained, searching images that have the words would be difficult, as well. To solve the data issue, this research developed a program which create train data automatically. This program can make images which have various keywords and pictures like catalog and save location-information of keywords at the same time. With this program, not only data can be collected efficiently, but also the performance of SSD model becomes better. The SSD model recorded 81.99% of recognition rate with 20,000 data created by the program. Moreover, this research had an efficiency test of SSD model according to data differences to analyze what feature of data exert influence upon the performance of recognizing texts in images. As a result, it is figured out that the number of labeled keywords, the addition of overlapped keyword label, the existence of keywords that is not labeled, the spaces among keywords and the differences of background images are related to the performance of SSD model. This test can lead performance improvement of SSD model or other text-recognizing machine based on deep learning algorithm with high-quality data. SSD model which is re-designed to recognize texts in images and the program developed for creating train data are expected to contribute to improvement of searching system in E-commerce. Suppliers can put less time to register keywords for products and customers can search products with product-details which is written on the catalog.