• Journal of Korea Game Society
• /
• v.18 no.2
• /
• pp.89-98
• /
• 2018

The recent Neural Network technique has shown good performance in content generation such as image generation in addition to the conventional classification problem and clustering problem solving. In this study, we propose an image generation method using artificial neural network as a next generation content creation technique. The proposed artificial neural network model receives two images and combines them into a new image by taking color from one image and shape from the other image. This model is made up of Convolutional Neural Network, which has two encoders for extracting color and shape from images, and a decoder for taking all the values of each encoder and generating a combination image. The result of this work can be applied to various 2D image generation and modification works in game development process at low cost.

• Journal of the Korean Society of Radiology
• /
• v.10 no.8
• /
• pp.637-643
• /
• 2016

Due to the popularity of artificial intelligent, medical image processing using artificial neural network is increasingly attracting the attention of academic and industry researches. Deep learning with a convolutional neural network has been proved to very effective representation of images. However, the training process requires high performance H/W platform. Thus, the realtime learning of a large number of high dimensional samples within low-power devices is a challenging problem. In this paper, we attempt to establish this possibility by presenting a realtime neural network method on Raspberry pi using online sequential extreme learning machine. Our experiments on high-dimensional dataset show that the proposed method records an almost real-time execution.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.23 no.2
• /
• pp.115-124
• /
• 2020

Due to the increasing threats of submarines from North Korea and other countries, ROK Navy should improve the detection capability of submarines. There are two ways to detect submarines : acoustic detection and non-acoustic detection. Since the acoustic-detection way has limitations in spite of its usefulness, it should have the complementary way. The non-acoustic detection is the way to detect submarines which are operating mast sets such as periscopes and snorkels by non-acoustic sensors. So, this paper proposes a new submarine non-acoustic detection model using an ensemble of Convolutional Neural Network models in order to automate the non-acoustic detection. The proposed model is trained to classify targets as 4 classes which are submarines, flag buoys, lighted buoys, small boats. Based on the numerical study with 10,287 images, we confirm the proposed model can achieve 91.5 % test accuracy for the non-acoustic detection of submarines.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.669-672
• /
• 2018

캡술내시경은 식도부터 항문까지 소화기관 전체를 한번에 촬영할 수 있는 의료기기로, 한번의 검사에 평균 8~12 시간 정도의 길이와 5만장 이상의 프레임으로 구성된 영상을 생성한다. 그러나 생성된 영상에 대한 분석은 수작업으로 진행되고 있어, 캡술내시경 영상 분석 자동화에 대한 기술적인 수요가 높아지고 있는 추세이다. 이를 위해, 캡슐내시경 영상 분석에 대한 많은 연구가 진행되고 있는데, 본 연구에서는 그 중에서도 폴립 영상에 대한 검출 자동화 연구에 주목하였다. 폴립이란 위장관 내에서 발견될 수 있는 융기성 병변으로, 많은 연구에서 기계학습 혹은 딥러닝 방식을 적용하여 이를 검출하기 위한 연구를 수행하였다. 그러나 캡슐내시경 영상의 특성상, 병번이 있는 영상이 굉장히 적기 때문에 일반적인 딥러닝 방식의 적용으로 좋은 성능을 내기 어렵다. 따라서 본 논문에서는 폴립 검출 컨볼루션 신경망 설계를 위한 멀티 스케일에 대한 원형 검출기법을 결합하여 폴립이 의심되는 영역을 추출해주는 특징 추출 기법으로, 수집한 데이터 150장에 대한 실험한 결과 약 82%의 성능을 보였다.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.3
• /
• pp.1-9
• /
• 2021

In this study, we evaluated the accuracy of deep learning-based tree species classification model trained by using high-resolution images. We selected five species classed, i.e., pine, birch, larch, korean pine, mongolian oak for classification. We created 5,000 datasets using high-resolution orthophoto and forest type map. CNN deep learning model is used to tree species classification. We divided training data, verification data, and test data by a 5:3:2 ratio of the datasets and used it for the learning and evaluation of the model. The overall accuracy of the model was 89%. The accuracy of each species were pine 95%, birch 89%, larch 80%, korean pine 86% and mongolian oak 98%.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.15-17
• /
• 2021

Handwriting recognition research is mainly focused on deep learning techniques and has achieved a great performance in the last few years. Especially, handwritten Thai digit recognition has been an important research area including generic digital numerical information, such as Thai official government documents and receipts. However, it becomes also a challenging task for a long time. For resolving the unavailability of a large Thai digit dataset, this paper constructs our dataset and learns them with some variants of the CNN model; Decision tree, K-nearest neighbors, Alexnet, LaNet-5, and VGG (11,13,16,19). The experimental results using the accuracy metric show the maximum accuracy of 98.29% when using VGG 13 with batch normalization.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.200-203
• /
• 2021

This paper introduces a smart mirror technology that recognizes a person's facial expressions through image classification among several artificial intelligence technologies and presents them in a mirror. 5 types of facial expression images are trained through artificial intelligence. When someone looks at the smart mirror, the mirror recognizes my expression and shows the recognized result in the mirror. The dataset fer2013 provided by kaggle used the faces of several people to be separated by facial expressions. For image classification, the network structure is trained using convolution neural network (CNN). The face is recognized and presented on the screen in the smart mirror with the embedded board such as Raspberry Pi4.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.630-633
• /
• 2020

무의식적인 손-얼굴의 접촉으로 인한 감염의 문제점을 해결하기 위해, 얼굴 만지기 행동을 인식할 필요가 있다. 본 연구는 최근 각광을 받는 딥러닝 기술을 이용하여 비디오 영상에서 얼굴 만지기 행동 인식에 대한 연구이다. 우선, 비디오 영상에서 얼굴 만지기와 관련된 11 가지 행동에 대한 시, 공간적 특징을 컨볼루션 신경망을 통해 추출한다. 추출된 정보는 각 행동 레이블로 인코딩되어 비디오 영상에서 얼굴 만지기 행동을 분류한다. 또한, 3D, 2D 컨볼루션 신경망의 대표 네트워크인 I3D, MobileNet v3에 대해 비교 실험을 진행한다. 제안하는 시스템을 적용하여 인간의 행동을 분류하는 실험을 진행했을 때, 얼굴을 만지는 행동을 99%의 확률로 구분했다. 이 시스템을 이용하여 일반인이 무의식적인 얼굴 만지기 행동에 대해서 정량적으로 또는 적시적으로 인식을 하여, 안전한 위생 습관을 확립하여 감염의 확산방지에 도움을 줄수 있기를 바란다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.524-526
• /
• 2021

As the video wall controller market is growing rapidly, issues that have not been addressed so far are raised. One of them is a phenomenon in which a black screen is displayed on a multi-screen. Black screen is displayed due to an error in the video being displayed in the video wall controller. Human intervention is inevitable to recognize and solve the black screen. However, it is impossible for the operator to monitor the multi-screen 24 hours a day. In this paper, we propose a model that detects the black screen being displayed on the video wall controller. We propose a CNN based architecture to detect a black screen.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.105-110
• /
• 2022

Traffic sign recognition plays an important role in solving traffic-related problems. Traffic sign recognition and classification systems are key components for traffic safety, traffic monitoring, autonomous driving services, and autonomous vehicles. A lightweight model, applicable to portable devices, is an essential aspect of the design agenda. We suggest a lightweight convolutional neural network model with residual blocks for traffic sign recognition systems. The proposed model shows very competitive results on publicly available benchmark data.