• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.6
• /
• pp.469-481
• /
• 2018

DL (Deep Learning) is getting popular in various fields to implement artificial intelligence that resembles human learning and cognition. DL based on complicate structure of the ANN (Artificial Neural Network) requires computing power and computation cost. Variety of DL models with improved performance have been developed with powerful computer specification. The main purpose of this paper is to detect buildings from aerial images and evaluate performance of Mask R-CNN (Region-based Convolutional Neural Network) developed by FAIR (Facebook AI Research) team recently. Mask R-CNN is a R-CNN that is evaluated to be one of the best ANN models in terms of performance for semantic segmentation with pixel-level accuracy. The performance of the DL models is determined by training ability as well as architecture of the ANN. In this paper, we characteristics of the Mask R-CNN with various types of the images and evaluate possibility of the generalization which is the ultimate goal of the DL. As for future study, it is expected that reliability and generalization of DL will be improved by using a variety of spatial information data for training of the DL models.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.5
• /
• pp.57-66
• /
• 2022

The Road Management Administration is cracking down on overloaded vehicles by installing low-speed or high-speed WIMs at toll gates and main lines on expressways. However, in recent years, the act of intelligently evading the overloaded-vehicle control system of the Road Management Administration by illegally manipulating the variable axle of an overloaded truck is increasing. In this manipulation, when entering the overloaded-vehicle checkpoint, all axles of the vehicle are lowered to pass normally, and when driving on the main road, the variable axle of the vehicle is illegally lifted with the axle load exceeding 10 tons alarmingly. Therefore, this study developed a technology to detect the state of the variable axle of a truck driving on the road using roadside camera images. In particular, this technology formed the basis for cracking down on overloaded vehicles by lifting the variable axle after entering the checkpoint and linking the vehicle with the account information of the checkpoint. Fundamentally, in this study, the tires of the vehicle were recognized using the Mask RCNN algorithm, the recognized tires were virtually arranged before and after the checkpoint, and the height difference of the vehicle was measured from the arrangement to determine whether the variable axle was lifted after the vehicle left the checkpoint.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.1-9
• /
• 2020

In this paper, we propose a model that performs more natural facial attribute editing by utilizing mask information in the hair and hat region. STGAN, one of state-of-the-art research of facial attribute editing, has shown results of naturally editing multiple facial attributes. However, editing hair-related attributes can produce unnatural results. The key idea of the proposed method is to additionally utilize information on the face regions that was lacking in the existing model. To do this, we apply three ideas. First, hair information is supplemented by adding hair ratio attributes through masks. Second, unnecessary changes in the image are suppressed by adding cycle consistency loss. Third, a hat segmentation network is added to prevent hat region distortion. Through qualitative evaluation, the effectiveness of the proposed method is evaluated and analyzed. The method proposed in the experimental results generated hair and face regions more naturally and successfully prevented the distortion of the hat region.

• Journal of the Korean Society of Safety
• /
• v.34 no.6
• /
• pp.50-57
• /
• 2019

In this study, various types of deep learning models that have been proposed recently are classified according to data input / output types and analyzed to find the deep learning model suitable for constructing a crack detection model. First the deep learning models are classified into image classification model, object segmentation model, object detection model, and instance segmentation model. ResNet-101, DeepLab V2, Faster R-CNN, and Mask R-CNN were selected as representative deep learning model of each type. For the comparison, ResNet-101 was implemented for all the types of deep learning model as a backbone network which serves as a main feature extractor. The four types of deep learning models were trained with 500 crack images taken from real concrete structures and collected from the Internet. The four types of deep learning models showed high accuracy above 94% during the training. Comparative evaluation was conducted using 40 images taken from real concrete structures. The performance of each type of deep learning model was measured using precision and recall. In the experimental result, Mask R-CNN, an instance segmentation deep learning model showed the highest precision and recall on crack detection. Qualitative analysis also shows that Mask R-CNN could detect crack shapes most similarly to the real crack shapes.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.271-286
• /
• 2023

The global COVID-19 pandemic has transformed face masks from situational accessories to indispensable items in daily life, prompting a shift in public perception and behavior. While the relaxation of mandatory mask-wearing regulations is underway, a significant number of individuals continue to embrace face masks, turning them into a form of personal expression and identity. This phenomenon has given rise to the Fashion Mask industry, characterized by unique designs and colors, experiencing rapid growth in the market. However, existing research on masks is predominantly focused on their efficacy in preventing infection or exploring attitudes during the pandemic, leaving a gap in understanding consumer preferences for mask design. We address this gap by investigating consumer perceptions and preferences for two prevalent mask designs-horizontal fold flat masks and vertical fold flat masks. Through a comprehensive approach involving surveys and eye-tracking experiments, we aim to unravel the subtle differences in how consumers perceive these designs. Our research questions focus on determining which design is more appealing and exploring the reasons behind any observed differences. The study's findings reveal a clear preference for vertical fold flat masks, which are not only preferred but also perceived as unique, sophisticated, three-dimensional, and lively. The eye-tracking analysis provides insights into the visual attention patterns associated with mask designs, highlighting the pivotal role of the fold line in influencing these patterns. This research contributes to the evolving understanding of masks as a fashion statement and provides valuable insights for manufacturers and marketers in the Fashion Mask industry. The results have implications beyond the pandemic, emphasizing the importance of design elements in sustaining consumer interest in face masks.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.6A
• /
• pp.568-574
• /
• 2002

The main issue of noise reduction of image is how to preserve edge and reduce noise. Usually, The Wiener falter is used for this purpose. But the conventional Wiener filter cannot remove noise well in both edge and smooth region due to the single size estimation window. In addition, it ignores the correlation between pixels. In this paper, we propose a new noise reduction algorithm, in which adaptive estimation window is used according to property of smooth region and edge region. In order to make edge more clear, directional Gaussian mask and directional estimation window combines to the Wiener filter according to direction of edge. From the simulation results, it can be seen that the proposed algorithm showed improves performance in both PSNR arid subjective evaluation

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.13 no.2
• /
• pp.33-39
• /
• 2004

Sandblasting has recently been developed into a powder blasting technique for brittle materials. In this study, the machinability of $Si_3N_4$-hBN based machinable ceramics are evaluated for micro - pattern making processes using powder blasting. Material properties of the developed machinable ceramics according to the variation of h-BN contents give a good machinability to the ceramics. The effect of scanning times, the size of patterns and variation of BN contents on the erosion depth of samples without mask and samples with different mask patterns in powder blasting of $Si_3N_4$-hBN ceramics are investigated. The Parameters are the impact angle of $90^{\circ}$, the scanning times of nozzle up to 40, and the stand-off distances of 100mm The widths of masked pattern are 0.1mm 0.5mm and 1mm. The powder used is Alumina particles, WA#600. and the blasting pressure of powder is 0.2MPa. Through required experiments, the results are investigated and analyzed. As the results, the machinability of the developed ceramics increases as the BN contents in the ceramics.

• Journal of Fashion Business
• /
• v.25 no.2
• /
• pp.51-62
• /
• 2021

This study evaluated the cosmetic effects of a far-infrared hot and cool mask (BBSkinplus) on face skin moisturization, whitening, and wrinkles using a randomized clinical trial. Forty female participants (mean age 47.7 ± 4.6 years) were allocated into the treatment group (BBSkinplus treatment and lotion application twice a day) or the control group (only lotion application twice a day), and moisture, brightness, and wrinkles were measured at 0, 1 and 2 weeks. The average values of each measurement were changed significantly by BBSkinplus treatment compared to the control group. At the 2-week treatment time point, the statistical differences in improvement rates between the two groups were significant at 8.7% vs. 3.9% for moisture (p < 0.01), 0.7% vs. 0.4% for brightness (p < 0.01), and -3.1% vs. 0.0% as Ra and -6.3% vs. 1.5% as R3z for wrinkles (p < 0.05), respectively. No notable complaint was reported regarding any kind of adverse effects such as erythema, itching, or burning. This clinical data support the potential of BBSkinplus as a home beauty device providing moisturizing, whitening, and anti-wrinkle effects on the face.

• Journal of Digital Convergence
• /
• v.15 no.6
• /
• pp.545-550
• /
• 2017

This study conducted an experiment to develop new raw ingredients for natural cosmetics by evaluating the efficacy of cosmetic products containing the extracts of Pleurotus eringii mushrooms grown without agricultural chemicals. To this end, purchased were Pleurotus eringii mushrooms grown without agricultural chemicals in South Gyeongsang province, South Korea in 2016; extraction was conductedwith 80% EeOH at room temperature after dry ing them. The study identified the excellent efficacy of the extracts after evaluating the antioxidant activity using the DPPH assay and ROS assay. According to the evaluation of he categories of moisture, oil, pH and pigment after the application of a cream-type facial mask pack containing 5% of the extracts, there were significant differences in the categories of moisture and oil on the T-zone area, and no statistically significant differences in the categories of oil change on the U-zone, pH and pigment. However as the extracts of Pleurotus eringii mushrooms had excellent efficacy in all categories compared to the control group, the efficacy of the extracts as a cosmetic raw ingredient could be identified. It is expected that this study may further contribute to developing more advanced raw ingredients, given the extract and cultivation conditions by concentration.

• Journal of Advanced Marine Engineering and Technology
• /
• v.31 no.5
• /
• pp.575-582
• /
• 2007

In this paper, a 100 Watt high power amplifier has been implemented and performed evaluation, which is operating at UHF band ($470\;{\sim}\;806\;MHz$) for Digital TV repeater. To achieve increase of bandwidth and high power capability, 3-way power combiner and divider of Wilkinson type was adopted. In order to measure the fabricated 100 Watt power amplifier, the estimation technique function which makes equivalent mask was used. As a result of the measurement, the existence of pilot signal is confirmed and the signal transmitted at the rated output power 100 Watt is brought out the flat feature through 6 MHz bandwidth. and it resulted that its value was less than -47 dB at the edge of radiation channel and less than -110 dB at more than 6 MHz position from channel edge.