• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.10
• /
• pp.1441-1446
• /
• 2022

Modern people can access various information about food recipes very easily on the Internet or social media. As the supply of food recipes increases, it is difficult to find a suitable recipe for each user in the overflowing information. As such, the need to provide information by reflecting users' requirements has increased, and research related to food recipes and cooking recommendations is becoming active. In addition, the Internet, video, and application markets using this are also rapidly activating. In this study, in order to classify recipes from the user's perspective of food recipe users, the user's review data was applied with the k-mean clustering technique, which is unsupervised learning, and a "food recipe classification model" was derived. As a result, it was classified into a total of 25 clusters including information needed by many users, such as specific purposes and cooking stages.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.738-747
• /
• 2021

Today, with the improvement of deep learning technology, computer vision areas such as image classification, object detection, object segmentation, and object tracking have shown remarkable improvements. Various applications such as intelligent surveillance, robots, Internet of Things, and autonomous vehicles in combination with deep learning technology are being applied to actual industries. Accordingly, the requirement of an efficient compression method for video data is necessary for machine consumption as well as for human consumption. In this paper, we propose an object-based compression of thermal infrared images for machine vision. The input image is divided into object and background parts based on the object detection results to achieve efficient image compression and high neural network performance. The separated images are encoded in different compression ratios. The experimental result shows that the proposed method has superior compression efficiency with a maximum BD-rate value of -19.83% to the whole image compression done with VVC.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.748-757
• /
• 2021

In this paper, we propose a gaze estimation network in which eye landmark position detection and gaze direction vector estimation are integrated into one deep learning network. The proposed network uses the Stacked Hourglass Network as a backbone structure and is largely composed of three parts: a landmark detector, a feature map extractor, and a gaze direction estimator. The landmark detector estimates the coordinates of 50 eye landmarks, and the feature map extractor generates a feature map of the eye image for estimating the gaze direction. And the gaze direction estimator estimates the final gaze direction vector by combining each output result. The proposed network was trained using virtual synthetic eye images and landmark coordinate data generated through the UnityEyes dataset, and the MPIIGaze dataset consisting of real human eye images was used for performance evaluation. Through the experiment, the gaze estimation error showed a performance of 3.9, and the estimation speed of the network was 42 FPS (Frames per second).

• Journal of Broadcast Engineering
• /
• v.27 no.4
• /
• pp.538-547
• /
• 2022

Recently introduced image classification methods using Transformers show remarkable performance improvements over conventional neural network-based methods. In order to effectively consider regional features, research has been actively conducted on how to apply transformers by dividing image areas into multiple window areas, but learning of inter-window relationships is still insufficient. In this paper, to overcome this problem, we propose a transformer structure that can reflect the relationship between windows in learning. The proposed method computes the importance of each window region through compression and a fully connected layer based on self-attention operations for each window region. The calculated importance is scaled to each window area as a learned weight of the relationship between the window areas to re-calibrate the feature value. Experimental results show that the proposed method can effectively improve the performance of existing transformer-based methods.

• Journal of Broadcast Engineering
• /
• v.28 no.2
• /
• pp.238-241
• /
• 2023

Recently deep learning models are widely used for various tasks such as facial recognition and face editing. Their training process often involves a dataset with imbalanced age distribution. It is because some age groups (teenagers and middle age) are more socially active and tends to have more data compared to the less socially active age groups (children and elderly). This imbalanced age distribution may negatively impact the deep learning training process or the model performance when tested against those age groups with less data. To this end, we propose an age-controllable face synthesis technique using a feature decomposition to classify age from facial images which can be utilized to synthesize novel data to balance out the age distribution. We perform extensive qualitative and quantitative evaluation on our proposed technique using the FFHQ dataset and we show that our method has better performance than existing method.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.333-336
• /
• 2023

Recently, the transformer model used in natural language processing is also applied to the image super resolution field, showing good performance. However, these transformer based models have a disadvantage that they are difficult to use in small mobile devices because they are complex and have many learning parameters and require high hardware resources. Therefore, in this paper, we propose a knowledge distillation technique that can effectively reduce the size of a transformer based super resolution model. As a result of the experiment, it was confirmed that by applying the proposed technique to the student model with reduced number of transformer blocks, performance similar to or higher than that of the teacher model could be obtained.

• Safety and Health at Work
• /
• v.14 no.1
• /
• pp.66-70
• /
• 2023

Background: Online teaching and learning extend the duration of using gadgets such as mobile phones and tablets. A prolonged usage of these gadgets in a static position can lead to musculoskeletal disorders (MSD). Therefore, this study aims to identify the risk factors related to musculoskeletal symptoms while using gadgets during work from home due to the COVID-19 pandemic. Method: A cross-sectional survey with online-based questionnaires was collected from the University of Indonesia, consisting of lecturers, students, and managerial staff. The minimum number of respondents was 1,080 and was defined by stratified random sampling. Furthermore, the dependent variable was musculoskeletal symptoms, while the independent were age, gender, job position, duration, activity when using gadgets, and how to hold them. Result: Most of the respondents had mobile phones but only 16% had tablets. Furthermore, about 56.7% have used a mobile phone for more than 10 years, while about 89.7% have used a tablet for less than 10 years. A multivariate analysis found factors that were significantly associated with MSD symptoms while using a mobile phone, such as age, gender, web browsing activity, work, or college activities. These activities include doing assignments and holding the phone with two hands with two thumbs actively operating. The factors that were significantly associated with MSD symptoms when using tablets were gender, academic position, social media activity, and placing the tablet on a table with two actively working index fingers. Conclusion: Therefore, from the results of this study it is necessary to have WFH and e-learning policies to reduce MSD symptoms and enhance productivity at work.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.20-30
• /
• 2022

Recently, as VR (Virtual Reality) technology has been in the spotlight, 360° panoramic images that can view lively VR contents are attracting a lot of attention. Image stitching technology is a major technology for producing 360° panorama images, and many studies are being actively conducted. Typical stitching algorithms are based on feature point-based image stitching. However, conventional feature point-based image stitching methods have a problem that stitching results are intensely affected by feature points. To solve this problem, deep learning-based image stitching technologies have recently been studied, but there are still many problems when there are few overlapping areas between images or large parallax. In addition, there is a limit to complete supervised learning because labeled ground-truth panorama images cannot be obtained in a real environment. Therefore, we produced three fisheye images with different camera centers and corresponding ground truth image through carla simulator that is widely used in the autonomous driving field. We propose image stitching model that creates a 360° panorama image with the produced fisheye image. The final experimental results are virtual datasets configured similar to the actual environment, verifying stitching results that are strong against various environments and large parallax.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.145-147
• /
• 2020

As deep learning technology advances, there have been many attempts to improve video codecs such as High-Efficiency-Video-Coding (HEVC) using deep learning technology. One of the most researched approaches is improving filters inside codecs through image restoration researches. In this paper, we propose a method 01 replacing the sample adaptive offset (SAO) filtering with a deep neural network. The proposed method uses the deep neural network to find the optimal offset value. The proposed network consists of two subnetworks to find the offset value and its type of the signal, which can restore nonlinear and complex type of error. Experimental results show that the performance is better than the conventional HEVC in low delay P and random access mode.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.377-379
• /
• 2022

POI refers to the point of Interest in Location-Based Social Networks (LBSNs). With the rapid development of mobile devices, GPS, and the Web (web2.0 and 3.0), LBSNs have attracted many users to share their information, physical location (real-time location), and interesting places. The tremendous demand of the user in LBSNs leads the recommendation systems (RSs) to become more widespread attention. Recommendation systems assist users in discovering interesting local attractions or facilities and help social network service (SNS) providers based on user locations. Therefore, it plays a vital role in LBSNs, namely POI recommendation system. In the machine learning model, most of the training data are stored in the centralized data storage, so information that belongs to the user will store in the centralized storage, and users may face privacy issues. Moreover, sharing the information may have safety concerns because of uploading or sharing their real-time location with others through social network media. According to the privacy concern issue, the paper proposes a recommendation model to prevent user privacy and eliminate traditional RS problems such as cold-start and data sparsity.