• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.7
• /
• pp.225-232
• /
• 2022

Recent development in information and communication technology has been beneficial to many, but at the same time, malicious attack attempts are also increasing through vulnerabilities in new programs. Among malicious attacks, malware operate in various ways and is distributed to people in new ways every time, and to solve this malware, it is necessary to quickly analyze and provide defense techniques. If new malware can be classified into the same type of malware, malware has similar behavioral characteristics, so they can provide defense techniques for new malware using analyzed malware. Therefore, there is a need for a solution to this because the method of accurately and quickly classifying malware and the number of data may not be uniform for each family of analyzed malware. This paper proposes a system that combines image preprocessing and ensemble techniques to increase accuracy in imbalanced data.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.50-53
• /
• 2022

In order to detect an object in yolv5, a process of annotating location information on an existing image is required when learning an image. The most representative method is to draw a bounding box on an image to store location information as meta information. However, if the boundary of the object is ambiguous, it will be difficult to make a bounding box. A representative example would be to classify parts that are not fire and parts that are fire. Therefore, in this paper, images of 100 samples judged to have caught fire were learned by varying the number of boxes. The results showed better fire detection performance in the model where the bounding box was trained by annotating it with three boxes by segmenting it slightly more than annotating it with one box by holding the edge as large as possible during annotating it with one box.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.1
• /
• pp.80-91
• /
• 2010

As the volume of image data increases dramatically, its good organization of image data is crucial for efficient image retrieval. Clustering is a typical way of organizing image data. However, traditional clustering methods have a difficulty of requiring a user to provide the number of clusters as a parameter before clustering. In this paper, we discuss an approach for clustering image data that does not require the parameter. Basically, the proposed approach is based on Cross-Association that finds a structure or patterns hidden in data using the relationship between individual objects. In order to apply Cross-Association to clustering of image data, we convert the image data into a graph first. Then, we perform Cross-Association on the graph thus obtained and interpret the results in the clustering perspective. We also propose the method of hierarchical clustering and the method of outlier detection based on Cross-Association. By performing a series of experiments, we verify the effectiveness of the proposed approach. Finally, we discuss the finding of a good value of k used in k-nearest neighbor search and also compare the clustering results with symmetric and asymmetric ways used in building a graph.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.5
• /
• pp.527-534
• /
• 2014

Poroelastic analyses of fiber-reinforced composites were performed using image-based computational models. The section image of a porous matrix was analyzed in order to investigate the porosity, number of pores, and distribution of pores. The resolution, location, and size of the section image were considered to quantify the effective elastic modulus, poroelastic parameter, and strain energy density using the image-based computational models. The poroelastic parameter was calculated from the effective elastic modulus and pore pressure-induced strain. In addition, the results of the poroelastic analyses were verified through representative volume elements by simplifying various pore configurations and arrangements.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.73-75
• /
• 2019

360°VR 영상은 카메라에서 촬영된 여러 영상들을 이어 붙이는 작업인 스티칭(Stitching)을 통하여 만들 수 있다. 스티칭은 영상들을 이어 붙이기 위해 각 영상의 특징점을 추출하는 특징점 추출, 특징점간 유사도를 비교하여 유사한 특징점끼리 매칭시키는 특징점 매칭, 특징점 매칭 과정에서 획득한 호모그래피 매트릭스를 이용한 이미지 와핑, 각 영상 간의 부자연스러운 경계선을 제거하는 블렌딩 과정을 거친다. 고품질의 360°VR 영상을 획득하기 위해서는 영상의 개수를 증가시킬 필요가 있고, 이로 인해 스티칭 과정에서 소요되는 시간이 증가한다. 본 논문에서는 카메라 센서 정보를 이용해 유사한 영상끼리 클러스터링하여, 한번에 스티칭이 진행되는 영상의 수를 감소시키고, 멀티 스레드를 이용하여 각 그룹의 스티칭을 병렬적으로 진행한 뒤, 최종적으로 스티칭하여 최종 360°VR 영상을 획득하는 과정을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.999-1000
• /
• 2017

본 논문에서는 이전의 의미 기반 이미지 어노테이션 및 검색 시스템 Moment(Mobile Semantic Image Annotation and Retrieval System)에 RDF(Resource Description Framework) 추론 기능을 사용한 어노테이션 방법을 제안한다. 이를 위하여 제안된 시스템은 Apache Jena Inference API를 통해 구현되였으며 각 이미지들이 가진 어노테이션의 개수가 증가되었다. 자동으로 추론된 결과 또한 SPARQL 질의를 통해 검색이 가능하며, 기존 어노테이션 결과에 대한 의미 검색을 더욱 효과적으로 할 수 있게 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.737-739
• /
• 2016

파노라마 이미지 생성 기법의 중요한 부분은 입력 영상들로부터 특징을 추출하고, 영상간의 대응점을 찾는 작업이다. 특징 추출할 때 영상의 회전, 스케일, 밝기 변화에 강건하고 수행속도가 비교적 빠른 검출 알고리즘을 사용한다. 파노라마 이미지 생성 과정에 있어서 실제 대응하는 점들을 크게 다루기 때문에 불필요한 영역의 특징들은 오히려 연산속도의 방해 요소가 된다. 본 논문에서는 특징 추출 영역을 제한함으로써 특징 매칭 횟수 감소 및 속도 향상 방법을 제안한다. 특징의 개수가 감소되면 매칭 횟수 감소되고, 이후 이루어질 여러 계산량도 줄어 속도가 향상된다. 본 연구에 SURF(Speeded-Up Robust Feature) 알고리즘을 사용하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.45-48
• /
• 2020

최근 마이크로서비스 아키텍처(Microservice Architecture)를 도입하는 프로젝트가 많아짐에 따라 컨테이너 오케스트레이션 도구인 쿠버네티스의 필요성이 증대되고 있다. 쿠버네티스 환경을 구성하고 서비스를 테스트 및 배포하기 위해서는 클러스터링을 하고 yaml파일을 작성하고 적용하여 자원을 생성하는 등의 작업이 필요하다. 이렇게 반복되는 작업을 자동화하기 위해 기존에는 쉘스크립트를 사용하는데, 이를 사용하기 위해서는 쿠버네티스 및 인프라에 관한 기초지식이 있어야 하는 문제점이 있다. 본 논문에서는 마이크로서비스를 위한 웹 기반의 배포 시스템을 제안한다. 웹을 통해 배포하고 테스트할 수 있어 기초지식이 없어도 사용할 수 있다. 웹에서 프로젝트 개발자로부터 도커 이미지와 사용할 포트번호 및 레플리카 개수를 입력받아 배포를 요청하면 쿠버네티스 환경에 배포하고, 필요한 자원들이 배포가 완료되면 엔드포인트를 제공한다. 그리고 배포된 서버의 엔드포인트에 요청을 전송하고 응답이 오는 것을 확인할 수 있어 활용성이 높다. 이 시스템은 쿠버네티스를 이용하여 복수 개의 파드(Pod)를 유지하여 가용성을 보장하고 빠르게 배포가 가능하게 한다. 또한 이미지가 업데이트되면 웹에서 요청하여 클러스터에 새 버전의 이미지로 배포한다.

• 한국정보교육학회:학술대회논문집
• /
• 2021.08a
• /
• pp.385-391
• /
• 2021

In this paper, a case of deep learning artificial neural network education was studied for artificial intelligence literacy education for preservice teachers and incumbent teachers. In addition, through the proposed educational case, we tried to explore the contents of artificial neural network principle education that elementary, middle and high school students can experience. To this end, first, an example of training on the principle of operation of an artificial neural network that recognizes two types of images is presented. And as an artificial neural network extension application education case, an artificial neural network education case for recognizing three types of images was presented. The number of output layers was changed according to the number of images to be recognized by the artificial neural network, and the cases implemented in a spreadsheet were divided and explained. In addition, in order to experience the operation results of the artificial neural network, we presented the educational contents to directly write the learning data necessary for the artificial neural network of the supervised learning method. In this paper, the implementation of the artificial neural network and the recognition test results are visually presented using a spreadsheet.

• Journal of Broadcast Engineering
• /
• v.21 no.4
• /
• pp.569-577
• /
• 2016

Place recognition for LBS (Location Based Service) has been one of the important techniques for user-oriented service. FLANN (Fast Library for performing Approximate Nearest Neighbor) of place recognition with image features is fast, but it is affected much by environmental condition such as occlusions. This paper presents a place recognition method using quad vocabulary tree with SURF (Speeded Up Robust Features). In learning stage, an image is represented with spatial pyramid of three levels and vocabulary trees of their sub-regions are constructed. Query image is matched with the learned vocabulary trees in each level. The proposed method measures homography error of the matched features. By considering the number of inliers in sub-region, we can improve place recognition performance.