• Journal of the Korea Computer Graphics Society
• /
• v.24 no.4
• /
• pp.29-38
• /
• 2018

In this paper, we propose an automatic segmentation method of meniscus in knee MR images by automatic meniscus localization, multi-atlas-based locally-weighted voting, and patch-based edge feature classification. First, after segmenting the bone and knee articular cartilage, the volume of interest of the meniscus is automatically localized. Second, the meniscus is segmented by multi-atlas-based locally-weighted voting taking into account the weights of shape and intensity distribution in the volume of interest of the meniscus. Finally, to remove leakage to the collateral ligaments with similar intensity, meniscus is refined using patch-based edge feature classification considering shape and distance weights. Dice similarity coefficient between proposed method and manual segmentation were 80.13% of medial meniscus and 80.81 % for lateral meniscus, and showed better results of 7.25% for medial meniscus and 1.31% for lateral meniscus compared to the multi-atlas-based locally-weighted voting.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.12
• /
• pp.546-554
• /
• 2019

Typically, closed-circuit television (CCTV) monitoring is mainly used for post-processes (i.e. to provide evidence after an incident has occurred), but by using a streaming video feed, machine-based learning, and advanced image recognition techniques, current technology can be extended to respond to crimes or reports of missing persons in real time. The multi-CCTV cooperation technique developed in this study is a program model that delivers similarity information about a suspect (or moving object) extracted via CCTV at one location and sent to a monitoring agent to track the selected suspect or object when he, she, or it moves out of range to another CCTV camera. To improve the operating efficiency of local government CCTV control centers, we describe here the partial automation of a CCTV control system that currently relies upon monitoring by human agents. We envisage an integrated crime prevention service, which incorporates the cooperative CCTV network suggested in this study and that can easily be experienced by citizens in ways such as determining a precise individual location in real time and providing a crime prevention service linked to smartphones and/or crime prevention/safety information.

• Archives of design research
• /
• v.14 no.3
• /
• pp.37-48
• /
• 2001

This paper is a study on how women consumers purchase are affected by models who appear in advertisements for cosmetics, focusing especially on studies concerning the impact that models have on advertisement strategies of the cosmetic industry in korea. In surveys conducted, consumers responded that cosmetic advertisement models should examplify a expertness and trustworthiness attitude more than just display their own physical attractiveness. The consumers who bought cosmetic products based on its endorsement from particular models responded that they had a positive reaction to the models physical attractiveness and likability while experiencing a negative reaction to the model's expertness and trustworthiness attitude. Women consumers are interested in cosmetic advertisement models, but do not necessarily trust them. Hence, the use of a Particular model does not directly affect the consumers Purchasing decision. Famous stars often appear in cosmetic advertisements in korea, and targeted consumers have a very positive response to their physical attractiveness, familiarity and perceived likability. However, the consumers have a completely negative response to the models in regards to their expertness, trustworthiness, and their sense of similarity with the model. The models, then, should be used in these advertisements to try and uphold the fellowing qualities. expertness in regards to having some knowledge of, experience with, and expertness in using the cosmetic produces, trustworthiness when expressing their own opinion of the product, matching image of products and targeted consumers.

• Journal of KIISE:Computing Practices and Letters
• /
• v.10 no.2
• /
• pp.174-188
• /
• 2004

In the life environment changed with not only the quality and the price of the products but also the material abundance, it is the most crucial factor for the strategy of product sales to investigate consumer's sensibility and preference degree. In this perspective, it is necessary to design and merchandise the products in cope with each consumer's sensibility and needs as well as its functional aspects. In this paper, we propose the Fashion Design Recommender Agent System (FDRAS-pro) for textile design applying collaborative filtering personalization technique as one of the methods of material development centered on consumer's sensibility and preference. For a collaborative filtering system based on textile, Representative-Attribute Neighborhood is adopted to determine the number or neighbors that will be used for preferences estimation. Pearson's Correlation Coefficient is used to calculate similarity weights among users. We build a database founded on the sensibility adjectives to develop textile designs by extracting the representative sensibility adjectives from users' sensibility and preferences about textile designs. FDRAS-pro recommends textile designs to a customer who has a similar propensity about textile. To investigate the sensibility and emotion according to the effect of design factors, fertile designs were analyzed in terms of 9 design factors, such as, motif source, motif-background ratio, motif variation, motif interpretation, motif arrangement, motif articulation, hue contrast, value contrast, chroma contrast. Finally, we plan to conduct empirical applications to verify the adequacy and the validity of our system.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.2
• /
• pp.15-23
• /
• 2017

The person Re-identification is the most challenging part of computer vision due to the significant changes in human pose and background clutter with occlusions. The picture from non-overlapping cameras enhance the difficulty to distinguish some person from the other. To reach a better performance match, most methods use feature selection and distance metrics separately to get discriminative representations and proper distance to describe the similarity between person and kind of ignoring some significant features. This situation has encouraged us to consider a novel method to deal with this problem. In this paper, we proposed an enhanced recurrent neural network with three-tier hierarchical network for person re-identification. Specifically, the proposed recurrent neural network (RNN) model contain an iterative expectation maximum (EM) algorithm and three-tier Hierarchical network to jointly learn both the discriminative features and metrics distance. The iterative EM algorithm can fully use of the feature extraction ability of convolutional neural network (CNN) which is in series before the RNN. By unsupervised learning, the EM framework can change the labels of the patches and train larger datasets. Through the three-tier hierarchical network, the convolutional neural network, recurrent network and pooling layer can jointly be a feature extractor to better train the network. The experimental result shows that comparing with other researchers' approaches in this field, this method also can get a competitive accuracy. The influence of different component of this method will be analyzed and evaluated in the future research.

• Journal of The Korean Association For Science Education
• /
• v.34 no.6
• /
• pp.601-611
• /
• 2014

The purpose of this study is to analyze the Korean science magazine, Science Donga providing scientific facts, phenomenons, and issues with infographic for the readers by time series analysis and to search for the application of infographic on the science education. The criteria for the infographic analysis of Science Donga consisted of three categories such as storytelling type, visual perception, and framework level because infographic presents complex information quickly and clearly by integrating various images, words, and graphics. We found that the articles emphasized by including image about science issue have been published from 1986 to 2014. Particularly, after 2008, the articles including infographic sharply rose. So we set up 2008 as $T_c$(Critical time point). The articles including infographic after 2008 have been more variously distributed and frequently used in storytelling types category such as location, time, number, connection, function, and process based infographic, in visual perception of Gestalt Theory such as proximity, similarity, continuation, and closure than before 2008. Lastly, in framework level category, location, time, number, and process based infographic mainly had total range level but function and connection based infographic changed in the framework level. The three features about storytelling type, visual perception, framework level are important changes to influence $T_c$ in the infographic analysis about Science Donga. Through the results of this study, we analyzed the feature of change on infographic from 1986 to 2014. Thus, we hope that the results suggest a basic criteria for making materials including infographic in science education.

• Korean Journal of Remote Sensing
• /
• v.16 no.3
• /
• pp.221-233
• /
• 2000

An intertidal topography is continuously changed due to morphodynamics processes. Detection and measurement of topographic change for a tidal flat is important to make an integrated coastal area management plan as well as to carry out sedimentologic study. The objective of this study is to generate intertidal DEM using leveling data and waterlines extracted from optical and microwave remotely sensed data in a relatively short period. Waterline is defined as the border line between exposed tidal flat and water body. The contour of the terrain height in tidal flat is equivalent to the waterline. One can utilize satellite images to generate intertidal DEM over large areas. Extraction of the waterline in a SAR image is a difficult task to perform partly because of the presence of speckle and partly because of similarity between the signal returned from the sea surface and that from the exposed tidal flat surface or land. Waterlines in SAR intensity and coherence map can effectively be extracted with MSP-RoA edge detector. From multiple images obtained over a range of tide elevation, it is possible to build up a set of heighted waterline within intertidal zone, and then a gridded DEM can be interpolated. We have tested the proposed method over the Gomso Bay, and succeeded in generating intertidal DEM with relatively high accuracy.

• Investigative Magnetic Resonance Imaging
• /
• v.23 no.3
• /
• pp.210-219
• /
• 2019

Purpose: The purpose of this study was to investigate if double inversion recovery (DIR) imaging can have a role in the evaluation of brain ischemia, compared with diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) imaging. Materials and Methods: Sixty-seven patients within 48 hours of onset, underwent MRI scans with FLAIR, DWI with b-value of 0 (B0) and $1000s/mm^2$, and DIR sequences. Patients were categorized into four groups: within three hours, three to six hours, six to 24 hours, and 24 to 48 hours after onset. Lesion-to-normal ratio (LNR) value was calculated and compared among all sequences within each group, by the Friedman test and conducted among all groups, for each sequence by the Kruskal-Wallis test. In qualitative assessment, signal intensity changes of DIR, B0, and FLAIR based on similarity with DWI and image quality of each sequence, were graded on a 3-point scale, respectively. Scores for detectability of lesions were compared by the McNemar's test. Results: LNR values from DWI were higher than DIR, but not statistically significant in all groups (P > 0.05). LNR values of DIR were significantly higher than FLAIR within 24 hours of onset (P < 0.05). LNR values were significantly different between, before, and after six hours onset time for DIR (P = 0.016), B0 (P = 0.008), and FLAIR (P = 0.018) but not for DWI (P = 0.051). Qualitative analysis demonstrated that detectability of DIR was higher, compared to that of FLAIR within 4.5 hours and six hours of onset (P < 0.05). Also, the DWI quality score was lower than that of DIR, particularly relative to infratentorial lesions. Conclusion: DIR provides higher detectability of hyperacute brain ischemia than B0 and FLAIR, and does not suffer from susceptibility artifact, unlike DWI. So, DIR can be used to replace evaluation of the FLAIR-DWI mismatch.

• Korean Journal of Heritage: History & Science
• /
• v.33
• /
• pp.162-181
• /
• 2000

This paper investigates sixteen rock-cut arhat images of the Koryo period at Sungbul-sa (成佛寺) in Chunan (天安), South Chungchung Province. These images, together with a Buddha triad in the center, are carved in thin relief on the large granite wall ($375cm{\times}248cm$), and below them is engraved a huge lotus petal which looks to be supporting all the images above. According to extant textual sources, arhats were popularly worshipped in the Koryo period. The Painting of Five Hundred Arhat Images was brought to Koryo from Later Liang (後梁) of the Five Dynasties (五代) in 923. From that time on, the cult of arhat had become gradually known in Koryo. More than thirty ceremonies worshipping arhats (羅漢齊) were officially held in Koryo court. The Sixteen Arhat images (十六羅漢像) were enshrined in many temples. In Boje-sa (普濟寺), which kings and aristocrats often visited for ritual ceremonies, had its main hall dominated by the Five Hundred Arhats, called Nahan-pocheon (羅漢寶殿). However, a limited number of arhat images of the Koryo period, originally made as sets of sixteen or five hundred arhats, are now extant. The Sixteen Arhat images at Sungbul-sa are unique examples that show all sixteen images in situ. The Sixteen Arhat images, though some of them are abraded, show various postures and gesture. One of them sits with his knee bent, and one arhat is sitting on a chair with his hand held upward. Each image is carved in a niche, just as the arhat images of Northern Song China are normally represented in niches of a cave, and are quite similar in style to the arhat images of the Northern Song period at Qinglindong (靑林洞) cave, Feilaifeng (飛來峰), Zejiang province (浙江省). This similarity between the arhat images of Sungbul-sa and those of Qinglindong certifies the strong impact of Song Buddhist art on Koryo frequently mentioned in texts. The Sixteen Arhat images surround the central Buddha raising his hand up to his chest. This Buddha triad could be ascribed to be either the Maitreya Buddha triad or the Sakyamuni Buddha triad based on the Lotus Sutra (妙法蓮華經). Still, the Sakyamuni Buddha triad was more often represented with sixteen or five hundred arhats in the Koryo period, as was seen in the record of Boje-sa where the Sakyamuni triad was enshrined with five hundred arhat images. The Sixteen Arhat images of Sungbul-sa arc most likely to be a rare example of Koryo Arhat images showing the Sakyamuni Buddha triad and the Sixteen Arhats who were predicted to be Buddhas by Sakyamuni in the Lotus Sutra.

• Journal of Broadcast Engineering
• /
• v.26 no.1
• /
• pp.39-60
• /
• 2021

In the field of deep learning, there are many algorithms mainly after GAN in research related to generation, but in terms of generation, there are similarities and differences with art. If the generation in the engineering aspect is mainly to judge the presence or absence of a quantitative indicator or the correct answer and the incorrect answer, the creation in the artistic aspect creates a creation that interprets the world and human life by cross-validating and doubting the correct answer and incorrect answer from various perspectives. In this paper, the video generation ability of deep learning was interpreted from the perspective of collage and compared with the results made by the artist. The characteristic of the experiment is to compare and analyze how much GAN reproduces the result of the creator made with the collage technique and the difference between the creative part, and investigate the satisfaction level by making performance evaluation items for the reproducibility of GAN. In order to experiment on how much the creator's statement and purpose of expression were reproduced, a deep learning algorithm corresponding to the statement keyword was found and its similarity was compared. As a result of the experiment, GAN did not meet much expectations to express the collage technique. Nevertheless, the image association showed higher satisfaction than human ability, which is a positive discovery that GAN can show comparable ability to humans in terms of abstract creation.