• 지능정보연구
• /
• 제24권1호
• /
• pp.183-203
• /
• 2018

전통적으로 신문 매체는 국내외에서 발생하는 사건들을 살피는 데에 가장 적합한 매체이다. 최근에는 정보통신 기술의 발달로 온라인 뉴스 매체가 다양하게 등장하면서 주변에서 일어나는 사건들에 대한 보도가 크게 증가하였고, 이것은 독자들에게 많은 양의 정보를 보다 빠르고 편리하게 접할 기회를 제공함과 동시에 감당할 수 없는 많은 양의 정보소비라는 문제점도 제공하고 있다. 본 연구에서는 방대한 양의 뉴스기사로부터 데이터를 추출하여 주요 사건을 감지하고, 사건들 간의 관련성을 판단하여 사건 네트워크를 구축함으로써 독자들에게 현시적이고 요약적인 사건정보를 제공하는 기법을 제안하는 것을 목적으로 한다. 이를 위해 2016년 3월에서 2017년 3월까지의 한국 정치 및 사회 기사를 수집하였고, 전처리과정에서 NPMI와 Word2Vec 기법을 활용하여 고유명사 및 합성명사와 이형동의어 추출의 정확성을 높였다. 그리고 LDA 토픽 모델링을 실시하여 날짜별로 주제 분포를 계산하고 주제 분포의 최고점을 찾아 사건을 탐지하는 데 사용하였다. 또한 사건 네트워크를 구축하기 위해 탐지된 사건들 간의 관련성을 측정을 위하여 두 사건이 같은 뉴스 기사에 동시에 등장할수록 서로 더 연관이 있을 것이라는 가정을 바탕으로 코사인 유사도를 확장하여 관련성 점수를 계산하는데 사용하였다. 최종적으로 각 사건은 각의 정점으로, 그리고 사건 간의 관련성 점수는 정점들을 잇는 간선으로 설정하여 사건 네트워크를 구축하였다. 본 연구에서 제시한 사건 네트워크는 1년간 한국에서 발생했던 정치 및 사회 분야의 주요 사건들이 시간 순으로 정렬되었고, 이와 동시에 특정 사건이 어떤 사건과 관련이 있는지 파악하는데 도움을 주었다. 또한 일련의 사건들의 시발점이 되는 사건이 무엇이었는가도 확인이 가능하였다. 본 연구는 텍스트 전처리 과정에서 다양한 텍스트 마이닝 기법과 새로이 주목받고 있는 Word2vec 기법을 적용하여 봄으로써 기존의 한글 텍스트 분석에서 어려움을 겪고 있었던 고유명사 및 합성명사 추출과 이형동의어의 정확도를 높였다는 것에서 학문적 의의를 찾을 수 있다. 그리고, LDA 토픽 모델링을 활용하기에 방대한 양의 데이터를 쉽게 분석 가능하다는 것과 기존의 사건 탐지에서는 파악하기 어려웠던 사건 간 관련성을 주제 동시출현을 통해 파악할 수 있다는 점에서 기존의 사건 탐지 방법과 차별화된다.

• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.235-238
• /
• 2019

In real world object detection is an active research topic for understanding different objects from images. There are different models presented in past and had significant results. In this paper we are presenting vehicle logo detection using previous object detection models such as You only look once (YOLO) and Faster Region-based CNN (F-RCNN). Both the front and rear view of the vehicles were used for training and testing the proposed method. Along with deep learning an image pre-processing algorithm called perspective transformation is proposed for all the test images. Using perspective transformation, the top view images were transformed into front view images. This algorithm has higher detection rate as compared to raw images. Furthermore, YOLO model has better result as compare to F-RCNN model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권11호
• /
• pp.5592-5609
• /
• 2017

JPEG steganography detection is an active research topic in the field of information hiding due to the wide use of JPEG image in social network, image-sharing websites, and Internet communication, etc. In this paper, a new steganalysis method for content-adaptive JPEG steganography is proposed by integrating the evolutionary feature selection and classifier ensemble selection. First, the whole framework of the proposed steganalysis method is presented and then the characteristic of the proposed method is analyzed. Second, the feature selection method based on genetic algorithm is given and the implement process is described in detail. Third, the method of classifier ensemble selection is proposed based on Pareto evolutionary optimization. The experimental results indicate the proposed steganalysis method can achieve a competitive detection performance by compared with the state-of-the-art steganalysis methods when used for the detection of the latest content-adaptive JPEG steganography algorithms.

• 스마트미디어저널
• /
• 제7권4호
• /
• pp.61-69
• /
• 2018

Multi-tracking of general objects and specific faces is an important topic in the field of computer vision applicable to many branches of industry such as biometrics, security, etc. The rapid development of deep neural networks has resulted in a dramatic improvement in face recognition and object detection problems, which helps improve the multiple-face tracking techniques exploiting the tracking-by-detection method. Our proposed method uses face detection trained with a head dataset to resolve the face deformation problem in the tracking process. Further, we use robust face features extracted from the deep face recognition network to match the tracklets with tracking faces using Hungarian matching method. We achieved promising results regarding the usage of deep face features and head detection in a face tracking benchmark.

• 한국산업융합학회 논문집
• /
• 제26권2_1호
• /
• pp.217-223
• /
• 2023

With the rapid advancement of technologies, need for different research fields where this technology can be used is also increasing. One of the most researched topic in computer vision is object detection, which has widely been implemented in various fields which include healthcare, video surveillance and education. The main goal of object detection is to identify and categorize all the objects in a target environment. Specifically, methods of object detection consist of a variety of significant techniq ues, such as image processing and patterns recognition. Anomaly detection is a part of object detection, anomalies can be found various scenarios for example crowded places such as subway stations. An abnormal event can be assumed as a variation from the conventional scene. Since the abnormal event does not occur frequently, the distribution of normal and abnormal events is thoroughly imbalanced. In terms of public safety, abnormal events should be avoided and therefore immediate action need to be taken. When abnormal events occur in certain places, real time detection is required to prevent and protect the safety of the people. To solve the above problems, we propose a modified YOLOv5 object detection algorithm by implementing dilated convolutional layers which achieved 97% mAP50 compared to other five different models of YOLOv5. In addition to this, we also created a simple mobile application to avail the abnormal event detection on mobile phones.

• 정보과학회지
• /
• 제22권4호
• /
• pp.28-34
• /
• 2004

사건 탐색 및 추적(TDT: Topic Detection and Tracking) 연구 [1]은 전세계 각 나라에서 매일 보도 되고 있는 신문이나 방송 뉴스 기사에서 "어떤 중요한 사건이 발생했는가\ulcorner"또는 "새로운 사건이 일어났는가\ulcorner"와 같이 그날 처음 발생한 사건을 탐색하거나, 같은 사건을 다루는 기사들을 탐색하거나, 예전에 발생한 사건과 관련된 사건인지를 추적해 나가는 것이다.된 사건인지를 추적해 나가는 것이다.

• Journal of Information Science Theory and Practice
• /
• 제2권4호
• /
• pp.31-48
• /
• 2014

The proliferation of many interactive Topic Detection and Tracking (iTDT) systems has motivated researchers to design systems that can track and detect news better. iTDT focuses on user interaction, user evaluation, and user interfaces. Recently, increasing effort has been devoted to user interfaces to improve TDT systems by investigating not just the user interaction aspect but also user and task oriented evaluation. This study investigates the combination of the bag of words and named entities approaches implemented in the iTDT interface, called Interactive Event Tracking (iEvent), including what TDT tasks these approaches facilitate. iEvent is composed of three components, which are Cluster View (CV), Document View (DV), and Term View (TV). User experiments have been carried out amongst journalists to compare three settings of iEvent: Setup 1 and Setup 2 (baseline setups), and Setup 3 (experimental setup). Setup 1 used bag of words and Setup 2 used named entities, while Setup 3 used a combination of bag of words and named entities. Journalists were asked to perform TDT tasks: Tracking and Detection. Findings revealed that the combination of bag of words and named entities approaches generally facilitated the journalists to perform well in the TDT tasks. This study has confirmed that the combination approach in iTDT is useful and enhanced the effectiveness of users' performance in performing the TDT tasks. It gives suggestions on the features with their approaches which facilitated the journalists in performing the TDT tasks.

• 대한임베디드공학회논문지
• /
• 제11권3호
• /
• pp.163-171
• /
• 2016

Lane detection is a widely researched topic. Although simple road detection is easily achieved by previous methods, lane detection becomes very difficult in several complex cases involving noisy edges. To address this, we use a Convolution neural network (CNN) for image enhancement. CNN is a deep learning method that has been very successfully applied in object detection and recognition. In this paper, we introduce a robust lane detection method based on a CNN combined with random sample consensus (RANSAC) algorithm. Initially, we calculate edges in an image using a hat shaped kernel, then we detect lanes using the CNN combined with the RANSAC. In the training process of the CNN, input data consists of edge images and target data is images that have real white color lanes on an otherwise black background. The CNN structure consists of 8 layers with 3 convolutional layers, 2 subsampling layers and multi-layer perceptron (MLP) of 3 fully-connected layers. Convolutional and subsampling layers are hierarchically arranged to form a deep structure. Our proposed lane detection algorithm successfully eliminates noise lines and was found to perform better than other formal line detection algorithms such as RANSAC

• 한국멀티미디어학회:학술대회논문집
• /
• 한국멀티미디어학회 2012년도 춘계학술발표대회논문집
• /
• pp.284-286
• /
• 2012

There has been increasing attention about the prevention and counter-measure of disasters. Particularly, for the case of fire disaster, early detection reduces the damage caused by fire significantly and effective detection method is important. Since most existing detectors need to be located at a close distance to fire, analyzing camera images to find fire becomes active research topic. In this paper, we analyze the color characteristics of fire images in various color spaces and report the experimental detection results. The best result is 77.8% success rate in YIQ space.

• International Journal of Computer Science & Network Security
• /
• 제21권12spc호
• /
• pp.415-426
• /
• 2021

The implementation of iris biometrics on smartphone devices has recently become an emerging research topic. As the use of iris biometrics on smartphone devices becomes more widely adopted, it is to be expected that there will be similar efforts in the research community to beat the biometric by exploring new spoofing methods and this will drive a corresponding requirement for new liveness detection methods. In this paper we addresses the problem of presentation attacks (Spoofing) against the Iris Recognition System on mobile devices and propose novel Presentation Attack Detection (PAD) method which suitable for mobile environment.