• Annals of Clinical Neurophysiology
• /
• v.25 no.1
• /
• pp.10-18
• /
• 2023

The ultimate purpose of eye movement is to maintain clear vision by ensuring that images of observed objects are focused on the fovea in the retina. Accurate evaluation of ocular movements, including nystagmus and saccadic intrusions, provides very useful information for determining the overall function and abnormality of the complex oculomotor system, from the peripheral vestibular system to the cerebrum. Eye movement tests are therefore essential for the accurate diagnosis of patients who complain of dizziness and imbalance. They help to predict lesion locations from the peripheral vestibular system to the central cerebral cortex and play an important role in differentiation from other diseases. The methodology of recording and interpreting ocular movements using video-oculography are described in this review article.

• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.663-672
• /
• 2023

Most vehicle detection methods have poor vehicle feature extraction performance at night, and their robustness is reduced; hence, this study proposes a night vehicle detection method based on style transfer image enhancement. First, a style transfer model is constructed using cycle generative adversarial networks (cycleGANs). The daytime data in the BDD100K dataset were converted into nighttime data to form a style dataset. The dataset was then divided using its labels. Finally, based on a YOLOv5s network, a nighttime vehicle image is detected for the reliable recognition of vehicle information in a complex environment. The experimental results of the proposed method based on the BDD100K dataset show that the transferred night vehicle images are clear and meet the requirements. The precision, recall, mAP@.5, and mAP@.5:.95 reached 0.696, 0.292, 0.761, and 0.454, respectively.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.794-797
• /
• 2024

Despite advancements in deep learning, existing semantic segmentation models exhibit suboptimal performance under adverse weather conditions, such as fog or rain, whereas they perform well in clear weather conditions. To address this issue, much of the research has focused on making image or feature-level representations weather-independent. However, disentangling the style and content of images remains a challenge. In this work, we propose a novel fine-tuning method, 'freeze-n-update.' We identify a subset of model parameters that are weather-independent and demonstrate that by freezing these parameters and fine-tuning others, segmentation performance can be significantly improved. Experiments on a test dataset confirm both the effectiveness and practicality of our approach.

• Journal of Science of Art and Design
• /
• v.6
• /
• pp.119-139
• /
• 2004

The intention of the research is to look into the form reflecting the spiritual image due to Oriental aesthetic from a realistic point of view. In this regard, I will pay attention to examining the process from figurative perspectives, in which painting image by subject acquires the beauty of form. Of the main subjection this paper, figure is an image itself appearing in painting. At this point, I will attempt to show how the meaning and value of image have been interpreted and judged on the aesthetic standard in Oriental painting in particular. For this process, I generalize the conception of the image as 'figure' and through this I will reconsider the standard of understanding and the value of perception regarding painting images on the method which are more applicable to the expressions of Oriental painting. The reason why I try to find out the true nature of images in Oriental painting from a figurative viewpoint is to convert a conventional sense of value which recognizes the images of Oriental painting only as results of idealism, into more practical field. If the true nature of Oriental painting is fixed and restricted to natures of idealism, any productive development and any changes in form for future couldn't be expected at all. In fact, what the ideological and aesthetic values of art suggest is clearly a proof of real art form. However, it is not a hard thing to prospect that only a superficial idealism will be ceaselessly produced, while the practical study about aesthetic values, meaningful results of painting expressions, is totally ignored, if ideology itself is used as criteria to judge the identity of it or if only the idealistic aesthetic values are emphasized while any clue to show a real existence of oriental paintings is not certain. Actually, nobody can deny the fact that interests about real natures regarding art expressions have been relatively ignored while armed with mental ideology for esthetic view of oriental painting in traditionalism Therefore, it is clear that 'spiritual status' itself can generate any form. Traditionally, in the Orient, the standard of judging a real value of things, which put a focus on a spiritual view of value rather than on a materialistic view of it, has been vaguely positioned the identity of images in painting As a result, the aesthetic convention has finally committed to an error that for images of oriental painting, ideological criteria like so called spiritualism are applied as a judging way, and esthetic meanings and values of real painting are considered as strategic results and spiritual intentions.

• Journal of Internet Computing and Services
• /
• v.19 no.5
• /
• pp.43-54
• /
• 2018

Images taken in haze weather are characteristic of low contrast and poor visibility. The process of reconstructing clear-weather image from a hazy image is called dehazing. The main challenge of image dehazing is to estimate the transmission map or depth map for an input hazy image. In this paper, we propose a single image dehazing method by utilizing the Generative Adversarial Network(GAN) for accurate depth map estimation. The proposed GAN model is trained to learn a nonlinear mapping between the input hazy image and corresponding depth map. With the trained model, first the depth map of the input hazy image is estimated and used to compute the transmission map. Then a guided filter is utilized to preserve the important edge information of the hazy image, thus obtaining a refined transmission map. Finally, the haze-free image is recovered via atmospheric scattering model. Although the proposed GAN model is trained on synthetic indoor images, it can be applied to real hazy images. The experimental results demonstrate that the proposed method achieves superior dehazing results against the state-of-the-art algorithms on both the real hazy images and the synthetic hazy images, in terms of quantitative performance and visual performance.

• Science of Emotion and Sensibility
• /
• v.10 no.3
• /
• pp.491-502
• /
• 2007

Categorization is very important for product design. Consumer's emotion become different according to a type of categorization, so design concept and design elements must be combined differently with difference of the emotion. Specially, categorization process is necessary if nowadays product line is enlarged, and a product differentiation is not clear. That is, designers decide on correct categories and a design concept based on similarity of emotion and have to provide to consumer-oriented design. The purpose of this study is to provide a design direction for Korean traditional sauce products after extracting consumers' sensitivity from the whole image of Korean traditional sauce and each images of the sauces-korean hot pepper paste, soybean paste, fermented soybeans paste, SsamJang, and soy sauce- and deciding categories of the each sauces based on the extracted sensitivities' similarity. In the result of this study, we knew that Korean traditional sauces didn't differentiate from consumers' preference images. In our empirical research, the research - emotional image survey on sauces - have conclusion that emotional image of "well-being", "tasty" have positive influence, but emotional image of "messy and dirty", "smelly" have negative influence. Therefore, we suggest that positive emotional images like "tasty" should be emphasized, but negative emotional images like "messy" should be eliminated for design and marketing strategy of Korean traditional sauces. This research will suggest the guideline for product design with respect to academic aspects and working-level aspects.

• Korean Journal of Optics and Photonics
• /
• v.20 no.6
• /
• pp.354-360
• /
• 2009

We have constructed and analyzed the performance of a simple fiber bundle multi-focal microscope. The microscope had a fiber bundle substituted for micro-lens array that is the core part of MMM(multi-focal multi-photon microscope). The MMM is a type of confocal microscope. To analyze the performance and characteristics of the fiber bundle multi-focal microscope, three types of samples were used: a standard grating, USAF 1951(7, 3), and 1951(7, 6). Using two polarizers and a polarizing beam splitter, we eliminated noise and got clear images. We obtained the FWHM of fiber spot images with the standard grating using two different magnifier lenses which were 63X and 20X, and found an image of the sample as a distribution of fiber spot images. For this case we used the low magnification lens, which gives denser distribution, so that we could get clearer images. In order to test the resolution of the fiber bundle multi-focal microscopic system, we used the USAF 1951 sample which has a smaller line interval than that of the standard grating. The FWHM of the line width of the image coincides well with the real line width of the USAF 1951 sample. We confirmed the performance of a fiber bundle multi-focal microscopic system which is relatively simple but has submicron resolution and is able to get 1600 images at the same time.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.4
• /
• pp.283-294
• /
• 2021

Solar radiation is an important meteorological factor in the agricultural sector. The ground exposed to sunlight is highly influenced by the surrounding terrains especially in South Korea where the topology is complex. The solar radiation on an inclined surface is estimated using a solar irradiance correction factor for the slope of the terrain along with the solar radiation on a horizontal surface. However, such an estimation method assumes that there is no barrier in surroundings, which blocks sunlight from the sky. This would result in errors in estimation of solar radiation because the effect of shading caused by the surrounding terrain has not been taken into account sufficiently. In this study, the shading effect was simulated to obtain the brightness value (BV), which was used as a correction factor. The shaded relief images, which were generated using a 30m-resolution digital elevation model (DEM), were used to derive the BVs. These images were also prepared using the position of the sun and the relief of the terrain as inputs. The gridded data where the variation of direct solar radiation was quantified as brightness were obtained. The value of cells in the gridded data ranged from 0 (the darkest value) to 255 (the brightest value). The BV analysis was performed using meteorological observation data at 22 stations installed in study area. The observed insolation was compared with the BV of each point under clear and cloudless condition. It was found that brightness values were significantly correlated with the solar radiation, which confirmed that shading due to terrain could explain the variation in direct solar radiation. Further studies are needed to accurately estimate detailed solar radiation using shaded relief images and brightness values.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.6
• /
• pp.154-161
• /
• 2008

In this paper, a novel method is proposed using color and pattern information for recognizing some emotions included in a fertile. Here we use 10 Kobayashi emotion to represent emotions. - { romantic, clear, natural, casual, elegant chic, dynamic, classic, dandy, modem } The proposed system is composed of feature extraction and classification. To transform the subjective emotions as physical visual features, we extract representative colors and Patterns from textile. Here, the representative color prototypes are extracted by color quantization method, and patterns exacted by wavelet transform followed by statistical analysis. These exacted features are given as input to the neural network (NN)-based classifiers, which decides whether or not a textile had the corresponding emotion. When assessing the effectiveness of the proposed system with 389 textiles collected from various application domains such as interior, fashion, and artificial ones. The results showed that the proposed method has the precision of 100% and the recall of 99%, thereby it can be used in various textile industries.

• Food Science of Animal Resources
• /
• v.37 no.4
• /
• pp.502-510
• /
• 2017

This study investigated bacterial growth-inhibitory effect of 69 therapeutic herbal plants extracts on 9 bacterial strains using a disc diffusion assay. Especially, the antimicrobial activity of Psoraleae semen, which showed different activity on pathogenic Gram-positive and Gram-negative bacteria, was evaluated by MIC (minimal inhibition concentration) and biofilm formation assay. The effect of Psoraleae semen extract on bacterial cell membranes was examined by measurement of protein leakage (optical density at 280 nm) and scanning electron microscope (SEM). No clear zone was formed on discs containing Gram-negative bacteria, but Gram-positive bacteria exhibited clear zones. The MICs of Psoraleae semen extract were $8{\mu}g/mL$ for Streptococcus mutans, and $16{\mu}g/mL$ for Enterococci and Staphylococcus aureus. In addition, biofilm formation was inhibited at concentration $8-16{\mu}g/mL$. Protein leakage values and SEM images revealed that cell membranes of Gram-positive bacteria were impaired following exposure to the extract. Further, the extract inhibited the growth of Listeria monocytogenes in sausages. These results indicate that Psoraleae semen extract could be utilized as a natural antimicrobial agent against Gram-positive bacteria.