• Journal of the Korea Society of Computer and Information
• /
• v.26 no.5
• /
• pp.1-8
• /
• 2021

Coronavirus disease 2019 (COVID-19) has affected the world seriously. Every person is required for wearing a mask properly in a public area to prevent spreading the virus. However, many people are not wearing a mask properly. In this paper, we propose an efficient mask detection system. In our proposed system, we first detect the faces of input images using YOLOv5 and classify them as the one of three scene complexity classes (Simple, Moderate, and Complex) based on the number of detected faces. After that, the image is fed into the Faster-RCNN with the one of three ResNet (ResNet-18, 50, and 101) as backbone network depending on the scene complexity for detecting the face area and identifying whether the person is wearing the mask properly or not. We evaluated our proposed system using public mask detection datasets. The results show that our proposed system outperforms other models.

• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• v.3 no.2
• /
• pp.67-72
• /
• 2022

Ecological research relies on the interpretation of large amounts of visual data obtained from extensive wildlife surveys, but such large-scale image interpretation is costly and time-consuming. Using an artificial intelligence (AI) machine learning model, especially convolution neural networks (CNN), it is possible to streamline these manual tasks on image information and to protect wildlife and record and predict behavior. Ecological research using deep-learning-based object recognition technology includes various research purposes such as identifying, detecting, and identifying species of wild animals, and identification of the location of poachers in real-time. These advances in the application of AI technology can enable efficient management of endangered wildlife, animal detection in various environments, and real-time analysis of image information collected by unmanned aerial vehicles. Furthermore, the need for school education and social use on biodiversity and environmental issues using AI is raised. School education and citizen science related to ecological activities using AI technology can enhance environmental awareness, and strengthen more knowledge and problem-solving skills in science and research processes. Under these prospects, in this paper, we compare the results of our early 2013 study, which automatically identified African cichlid fish species using photographic data of them, with the results of reanalysis by CNN deep learning method. By using PyTorch and PyTorch Lightning frameworks, we achieve an accuracy of 82.54% and an F1-score of 0.77 with minimal programming and data preprocessing effort. This is a significant improvement over the previous our machine learning methods, which required heavy feature engineering costs and had 78% accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.365-380
• /
• 2022

The target detection algorithm based on supervised learning is the current mainstream algorithm for target detection. A high-quality dataset is the prerequisite for the target detection algorithm to obtain good detection performance. The larger the number and quality of the dataset, the stronger the generalization ability of the model, that is, the dataset determines the upper limit of the model learning. The convolutional neural network optimizes the network parameters in a strong supervision method. The error is calculated by comparing the predicted frame with the manually labeled real frame, and then the error is passed into the network for continuous optimization. Strongly supervised learning mainly relies on a large number of images as models for continuous learning, so the number and quality of images directly affect the results of learning. This paper proposes a dataset STAR-24K (meaning a dataset for Space TArget Recognition with more than 24,000 images) for detecting common targets in space. Since there is currently no publicly available dataset for space target detection, we extracted some pictures from a series of channels such as pictures and videos released by the official websites of NASA (National Aeronautics and Space Administration) and ESA (The European Space Agency) and expanded them to 24,451 pictures. We evaluate popular object detection algorithms to build a benchmark. Our STAR-24K dataset is publicly available at https://github.com/Zzz-zcy/STAR-24K.

• Journal of Broadcast Engineering
• /
• v.27 no.4
• /
• pp.499-510
• /
• 2022

This paper introduces a video editing system for senior creator who is not familiar to video editing. Based on video analysis techniques, it provide various information and delete unwanted shot. The system detects shot boundaries based on RNN(Recurrent Neural Network), and it determines the deletion of video shots. The shots can be deleted using shot-level significance, which is computed by detecting focused area. It is possible to delete unfocused shots or motion-blurred shots using the significance. The system detects object and face, and extract the information of emotion, age, and gender from face image. Users can create video contents using the information. Decorating tools are also prepared, and in the tools, the preferred design, which is determined from user history, places in the front of the design element list. With the video editing system, senior creators can make their own video contents easily and quickly.

• Journal of Biomedical Engineering Research
• /
• v.43 no.4
• /
• pp.290-297
• /
• 2022

During surgery, Surgical instruments are often left behind due to accidents. Most of these are surgical gauze, so radioactive non-permeable gauze (X-ray gauze) is used for preventing of accidents which gauze is left in the body. This gauze is divided into wire and pad type. If it is confirmed that the gauze remains in the body, gauze must be detected by radiologist's reading by imaging using a mobile X-ray device. But most of operating rooms are not equipped with a mobile X-ray device, but equipped C-Arm equipment, which is of poorer quality than mobile X-ray equipment and furthermore it takes time to read them. In this study, Use C-Arm equipment to acquire gauze image for detection and Build dataset using artificial intelligence and select a detection model to Assist with the relatively low image quality and the reading of radiology specialists. mAP@50 and detection time are used as indicators for performance evaluation. The result is that two-class gauze detection dataset is more accurate and YOLOv5 model mAP@50 is 93.4% and detection time is 11.7 ms.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.6
• /
• pp.43-52
• /
• 2022

We can sense somebody's feeling fatigue, which means that fatigue can be detected through sensing human biometric signals. Numerous researches for assessing fatigue are mostly focused on diagnosing the edge of disease-level fatigue. In this study, we adapt quantitative analysis approaches for estimating qualitative data, and propose video analysis models for measuring fatigue state. Proposed three deep-learning based classification models selectively include stages of video analysis: object detection, feature extraction and time-series frame analysis algorithms to evaluate each stage's effect toward dividing the state of fatigue. Using frontal face videos collected from various fatigue situations, our CNN model shows 0.67 accuracy, which means that we empirically show the video analysis models can meaningfully detect fatigue state. Also we suggest the way of model adaptation when training and validating video data for classifying fatigue.

• Journal of radiological science and technology
• /
• v.46 no.4
• /
• pp.277-285
• /
• 2023

In this study, pneumonia identification networks with the small number of layers were constructed by using chest X-ray images. The networks had similar trainable-parameters, and the performance of the trained models was quantitatively evaluated with the modification of the network architectures. A total of 6 networks were constructed: convolutional neural network (CNN), VGGNet, GoogleNet, residual network with identity blocks, ResNet with bottleneck blocks and ResNet with identity and bottleneck blocks. Trainable parameters for the 6 networks were set in a range of 273,921-294,817 by adjusting the output channels of convolution layers. The network training was implemented with binary cross entropy (BCE) loss function, sigmoid activation function, adaptive moment estimation (Adam) optimizer and 100 epochs. The performance of the trained models was evaluated in terms of training time, accuracy, precision, recall, specificity and F1-score. The results showed that the trained models with the small number of layers precisely detect pneumonia from chest X-ray images. In particular, the overall quantitative performance of the trained models based on the ResNets was above 0.9, and the performance levels were similar or superior to those based on the CNN, VGGNet and GoogleNet. Also, the residual blocks affected the performance of the trained models based on the ResNets. Therefore, in this study, we demonstrated that the object detection networks with the small number of layers are suitable for detecting pneumonia using chest X-ray images. And, the trained models based on the ResNets can be optimized by applying appropriate residual-blocks.

• Nuclear Engineering and Technology
• /
• v.55 no.9
• /
• pp.3260-3267
• /
• 2023

Zr-Nb alloy have been widely used as fuel rods in nuclear power plants. However, from the Fukushima nuclear accident, the weakness of the rod was revealed under harsh conditions, and research on the safety of these types of rods was conducted after the disaster. The method of depositing chromium onto the existing Zr-Nb alloy fuel rods is being considered as a means by which to compensate for the weakness of Zr-Nb alloy rods because chromium is strong against oxidation at high temperatures and has high strength. In order to secure these advantages, it is important to maintain the Cr thickness of the rods and properly inspect the rods before and during their use in power generation. Eddy current testing is a typical means of evaluating the thickness of thin metals and detecting surface defects. Depending on the size and shape of the inspected object, various eddy current sensors can be applied. In particular, because pancake sensors can be manufactured in very small sizes, they can be used for inspections even in narrow spaces, such as a nuclear fuel assembly. In this study, an eddy current technique was developed to confirm the feasibility of Cr coating thickness evaluations. After determining the design parameters of the pancake sensor by means of a FEM simulation, a FPCB pancake sensor was manufactured and the optimal frequency was selected by measuring minute changes in the Cr-coating thickness using the developed sensor.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.101-103
• /
• 2022

CCTV is mainly used as a real-time detection system for critical facilities. In the case of CCTV, although the accuracy is high, the viewing angle is narrow, so it is used in combination with a sensor such as a radar. LiDAR is a technology that acquires distance information by detecting the time it takes to reflect off an object using a high-power pulsed laser. In the case of lidar, there is a problem in that the utilization is not high in terms of cost and technology due to the limitation of the number of simultaneous processing sensors in the server due to the data throughput. The detection method by the optical mesh sensor is also vulnerable to strong winds and extreme cold, and there is a problem of maintenance due to damage to animals. In this paper, by using the 1550nm wavelength band instead of the 905nm wavelength band used in the existing lidar sensor, the effect on the weather environment is strong and we propose to develop a system that can integrate and control multiple sensors.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.463-465
• /
• 2021

Currently, the inspection method printed on food packages and boxes is to sample only a few products and inspect them with human eyes. Such a sampling inspection has the limitation that only a small number of products can be inspected. Therefore, accurate inspection using a camera is required. This paper proposes a deep learning object recognition technology model, which is an artificial intelligence technology, as a method for detecting the defects of expiration date printed on the product packaging. Using the Faster R-CNN (region convolution neural network) model, the color images, converted gray images, and converted binary images of the printed expiration date are trained and then tested, and each detection rates are compared. The detection performance of expiration date printed on the package by the proposed method showed the same detection performance as that of conventional vision-based inspection system.