• Journal of Convergence for Information Technology
• /
• v.11 no.11
• /
• pp.44-50
• /
• 2021

Recently, enterprise storage systems that require large-capacity storage devices to accommodate big data have used large-capacity flash memory-based storage devices with high density compared to cost and size. This paper proposes a high-efficiency life prediction method with slope descent to maximize the life of flash memory media that directly affects the reliability and usability of large enterprise storage devices. To this end, this paper proposes the structure of a matrix for storing metadata for learning the frequency of defects and proposes a cost model using metadata. It also proposes a life expectancy prediction policy in exceptional situations when defects outside the learned range occur. Lastly, it was verified through simulation that a method proposed by this paper can maximize its life compared to a life prediction method based on the fixed number of times and the life prediction method based on the remaining ratio of spare blocks, which has been used to predict the life of flash memory.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.419-428
• /
• 2021

Shadow removal plays a key role for the pre-processing of image processing techniques such as object tracking and detection. With the advances of image recognition based on deep convolution neural networks, researches for shadow removal have been actively conducted. In this paper, we propose a novel method for shadow removal, which utilizes self attention distillation to extract semantic features. The proposed method gradually refines results of shadow detection, which are extracted from each layer of the proposed network, via top-down distillation. Specifically, the training procedure can be efficiently performed by learning the contextual information for shadow removal without shadow masks. Experimental results on various datasets show the effectiveness of the proposed method for shadow removal under real world environments.

• Journal of Broadcast Engineering
• /
• v.26 no.2
• /
• pp.184-196
• /
• 2021

This paper proposes statistics adaptive linear regression-based object size prediction method for object detection. YOLOv2 and YOLOv3, which are typical deep learning-based object detection algorithms, designed the last layer of a network using statistics adaptive exponential regression model to predict the size of objects. However, an exponential regression model can propagate a high derivative of a loss function into all parameters in a network because of the property of an exponential function. We propose statistics adaptive linear regression layer to ease the gradient exploding problem of the exponential regression model. The proposed statistics adaptive linear regression model is used in the last layer of the network to predict the size of objects with statistics estimated from training dataset. We newly designed the network based on the YOLOv3tiny and it shows the higher performance compared to YOLOv3 tiny on the UFPR-ALPR dataset.

• Journal of Broadcast Engineering
• /
• v.24 no.4
• /
• pp.580-591
• /
• 2019

This paper focuses on to improving object detection performance using the camera and LiDAR on autonomous vehicle platforms by fusing detected objects from individual sensors through a late fusion approach. In the case of object detection using camera sensor, YOLOv3 model was employed as a one-stage detection process. Furthermore, the distance estimation of the detected objects is based on the formulations of Perspective matrix. On the other hand, the object detection using LiDAR is based on K-means clustering method. The camera and LiDAR calibration was carried out by PnP-Ransac in order to calculate the rotation and translation matrix between two sensors. For Sensor fusion, intersection over union(IoU) on the image plane with respective to the distance and angle on world coordinate were estimated. Additionally, all the three attributes i.e; IoU, distance and angle were fused using logistic regression. The performance evaluation in the sensor fusion scenario has shown an effective 5% improvement in object detection performance compared to the usage of single sensor.

• Journal of Korean language education
• /
• v.29 no.3
• /
• pp.227-253
• /
• 2018

The purpose of this study is to propose a plan for future developments of the Korean language textbooks for overseas by conducting the Importance-Performance Analysis (IPA) of the Korean language textbooks for overseas. For this purpose, this study analyse and evaluate the Korean language textbooks for overseas and the researches for developing Korean language textbooks for overseas. In this study, we have the IPA of the Korean language textbooks from the total of 158 surveys that were collected from teachers who teach Korean at King Sejong Institute and overseas university. The survey conducted about the Korean textbooks regarding the following questionnaires: 1) integrated and separated textbooks, 2) textbooks by learners' variables, 3) teaching materials by media type, 4) supplementary teaching materials, 5) diffusion and support of textbooks. The result of this survey found that supporting for the separated textbooks is needed, and there is a high demand for localized textbooks considering local characteristics. Furthermore, it is noteworthy that King Sejong Institute has a high demand for textbooks that can be downloaded from the web despite most of institutes are highly satisfied with paper textbooks. For the supplementary textbooks, it was found that vocabulary learning materials were needed for the King Sejong school students and additional reading materials for overseas college learners needed to be developed. We also found that it is necessary to support not only the development of textbooks but also smooth and efficient diffusion.

• Journal of Broadcast Engineering
• /
• v.24 no.2
• /
• pp.217-226
• /
• 2019

In this paper, we propose a filtering method that can improve the results of inverse tone-mapping using guided image filter. Inverse tone-mapping techniques have been proposed that convert LDR images to HDR. Recently, many algorithms have been studied to convert single LDR images into HDR images using CNN. Among them, there exists an algorithm for restoring pixel information using CNN which learned to restore saturated region. The algorithm does not suppress the noise in the non-saturation region and cannot restore the detail in the saturated region. The proposed algorithm suppresses the noise in the non-saturated region and restores the detail of the saturated region using a WGIF in the input image, and then applies it to the CNN to improve the quality of the final image. The proposed algorithm shows a higher quantitative image quality index than the existing algorithms when the HDR quantitative image quality index was measured.

• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.886-895
• /
• 2018

In this paper, we introduce a technique to detect the video forgery by using the regularity that occurs in the video compression process. The proposed method uses the hierarchical regularity lost by the video double compression and the frame deletion. In order to extract such irregularities, the depth information of CU and TU, which are basic units of HEVC, is used. For improving performance, we make a depth map of CU and TU using local information, and then create input data by grouping them in GoP units. We made a decision whether or not the video is double-compressed and forged by using a general three-dimensional convolutional neural network. Experimental results show that it is more effective to detect whether or not the video is forged compared with the results using the existing machine learning algorithm.

• Journal of Korea Multimedia Society
• /
• v.22 no.5
• /
• pp.535-546
• /
• 2019

Recently, there have been a lot of researches on the whole face replacement system, but it is not easy to obtain stable results due to various attitudes, angles and facial diversity. To produce a natural synthesis result when replacing the face shown in the video image, technologies such as face area detection, feature extraction, face alignment, face area segmentation, 3D attitude adjustment and facial transposition should all operate at a precise level. And each technology must be able to be interdependently combined. The results of our analysis show that the difficulty of implementing the technology and contribution to the system in facial replacement technology has increased in facial feature point extraction and facial alignment technology. On the other hand, the difficulty of the facial transposition technique and the three-dimensional posture adjustment technique were low, but showed the need for development. In this paper, we propose four facial replacement models such as 2-D Faceswap, OpenPose, Deekfake, and Cycle GAN, which are suitable for the Cox platform. These models have the following features; i.e. these models include a suitable model for front face pose image conversion, face pose image with active body movement, and face movement with right and left side by 15 degrees, Generative Adversarial Network.

• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.67-76
• /
• 2019

In this paper, we propose an efficient object classification method based on semantic segmentation for multi-labeled image data. In addition to various pixel unit information and processing techniques such as color information, contour, contrast, and saturation included in image data, a detailed region in which each object is located is extracted as a meaningful unit and the experiment is conducted to reflect the result in the inference. We use a neural network that has been proven to perform well in image classification to understand which object is located where image data containing various class objects are located. Based on these researches, we aim to provide artificial intelligence services that can classify real-time detailed areas of complex images containing various objects in the future.

• International Journal of Advanced Culture Technology
• /
• v.8 no.4
• /
• pp.82-88
• /
• 2020

With the development of medical care in the 21st century and the rapid development of the 4th industry, electronic devices and household goods taking into account the physical and mental aging of the silver generation have been developed, and apps related to health and health are generally developed and operated. The apps currently used by the silver generation are a form that provides information on diseases by focusing on prevention rather than treatment, such as safety management apps for the elderly living alone and methods for preventing diseases. There are not many apps that provide information on foods that have a direct effect and nutrients in that food, and research on apps that can obtain information about individual foods is insufficient. In this paper, we propose an app that analyzes food factors and provides self-medication for health promotion of the silver generation. This app allows the silver generation to conveniently and easily obtain information such as nutrients, calories, and efficacy of food they need. In addition, this app collects/categorizes healthy food information through a textom solution-based crawling agent, and stores highly relevant words in a data resource. In addition, wide deep learning was applied to enable self-medication recommendations for food. When this technique is applied, the most appropriate healthy food is suggested to people with similar eating patterns and tastes in the same age group, and users can receive recommendations on customized healthy foods that they need before eating. This made it possible to obtain convenient healthy food information through a customized interface for the elderly through a smartphone.