• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.166-173
• /
• 2024

This study explores lip-sync detection, focusing on the synchronization between lip movements and voices in videos. Typically, lip-sync detection techniques involve cropping the facial area of a given video, utilizing the lower half of the cropped box as input for the visual encoder to extract visual features. To enhance the emphasis on the articulatory region of lips for more accurate lip-sync detection, we propose utilizing a pre-trained visual attention-based encoder. The Visual Transformer Pooling (VTP) module is employed as the visual encoder, originally designed for the lip-reading task, predicting the script based solely on visual information without audio. Our experimental results demonstrate that, despite having fewer learning parameters, our proposed method outperforms the latest model, VocaList, on the LRS2 dataset, achieving a lip-sync detection accuracy of 94.5% based on five context frames. Moreover, our approach exhibits an approximately 8% superiority over VocaList in lip-sync detection accuracy, even on an untrained dataset, Acappella.

• Journal of Biomedical Engineering Research
• /
• v.24 no.4
• /
• pp.259-266
• /
• 2003

Non-rigid registration between different modality images with shape deformation can be used to diagnosis and study for inter-patient image registration, longitudinal intra-patient registration, and registration between a patient image and an atlas image. This paper proposes a hierarchical registration method using bodily tissue based segmentation for registration between color images and CT images of the Visible Human leg areas. The cross-sectional color images and the axial CT images are segmented into three distinctive bodily tissue regions, respectively: fat, muscle, and bone. Each region is separately registered hierarchically. Bounding boxes containing bodily tissue regions in different modalities are initially registered. Then, boundaries of the regions are globally registered within range of searching space. Local boundary segments of the regions are further registered for non-rigid registration of the sampled boundary points. Non-rigid registration parameters for the un-sampled points are interpolated linearly. Such hierarchical approach enables the method to register images efficiently. Moreover, registration of visibly distinct bodily tissue regions provides accurate and robust result in region boundaries and inside the regions.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.3
• /
• pp.227-237
• /
• 2022

The most critical factors for detecting changes in very high-resolution satellite images are building positional inconsistencies and relief displacements caused by satellite side-view. To resolve the above problems, additional processing using a digital elevation model and deep learning approach have been proposed. Unfortunately, these approaches are not sufficiently effective in solving these problems. This study proposed a change detection method that considers both positional and topology information of buildings. Mask R-CNN (Region-based Convolutional Neural Network) was trained on a SpaceNet building detection v2 dataset, and the central points of each building were extracted as building nodes. Then, triangulated irregular network graphs were created on building nodes from temporal images. To extract the area, where there is a structural difference between two graphs, a change index reflecting the similarity of the graphs and differences in the location of building nodes was proposed. Finally, newly changed or deleted buildings were detected by comparing the two graphs. Three pairs of test sites were selected to evaluate the proposed method's effectiveness, and the results showed that changed buildings were detected in the case of side-view satellite images with building positional inconsistencies.

• Journal of Korea Water Resources Association
• /
• v.55 no.6
• /
• pp.393-404
• /
• 2022

Reliable terrestrial rainfall observations from satellites at finer spatial resolution are essential for urban hydrological and microscale agricultural demands. Although various traditional "top-down" approach-based satellite rainfall products were widely used, they are limited in spatial resolution. This study aims to assess the potential of a novel "bottom-up" approach for rainfall estimation, the parameterized SM2RAIN model, applied to the C-band SAR Sentinel-1 satellite data (SM2RAIN-S1), to generate high-spatial-resolution terrestrial rainfall estimates (0.01° grid/6-day) over Central South Korea. Its performance was evaluated for both spatial and temporal variability using the respective rainfall data from a conventional reanalysis product and rain gauge network for a 1-year period over two different sub-regions in Central South Korea-the mixed forest-dominated, middle sub-region and cropland-dominated, west coast sub-region. Evaluation results indicated that the SM2RAIN-S1 product can capture general rainfall patterns in Central South Korea, and hold potential for high-spatial-resolution rainfall measurement over the local scale with different land covers, while less biased rainfall estimates against rain gauge observations were provided. Moreover, the SM2RAIN-S1 rainfall product was better in mixed forests considering the Pearson's correlation coefficient (R = 0.69), implying the suitability of 6-day SM2RAIN-S1 data in capturing the temporal dynamics of soil moisture and rainfall in mixed forests. However, in terms of RMSE and Bias, better performance was obtained with the SM2RAIN-S1 rainfall product over croplands rather than mixed forests, indicating that larger errors induced by high evapotranspiration losses (especially in mixed forests) need to be included in further improvement of the SM2RAIN.

• Korean Journal of Cognitive Science
• /
• v.26 no.4
• /
• pp.393-433
• /
• 2015

Creativity refers to the ability to generate novel and useful ideas. Understanding the mechanism of creativity and its enhancement is important in order to solve major problems of the modern society and to improve the wellness of mankind. Creativity is a highly heterogeneous and complex ability which should not be conceptualized as a single entity. Thus, the current literature on creativity is based on a component process approach to creativity. The present study introduces cognitive neuroscience research studying the mechanism of divergent thinking, insight, relational thinking and artistic creativity which are the major components of creativity. Based on an expansive review, the early hypothesis of hemispheric asymmetry emphasizing the importance of the right as opposed to the left hemisphere is not supported by scientific evidence. In addition, there is no consensus or consistency on which specific brain region is related to a certain component of creativity. In fact, there is a mixture of studies reporting involvement of various brain regions across all four lobes of the brain. This inconsistency in the literature most likely reflects heterogeneity of the component processes of creativity and sensitivity of the neural response to differences across tasks and cognitive strategy. The present study introduces examples of representative studies reporting seminal findings on the neural basis and the enhancement of creativity based on innovative methodology. In addition, we discuss limitations of the current cognitive neuroscience approach to creativity and present directions for future research.

• Journal of the Economic Geographical Society of Korea
• /
• v.20 no.3
• /
• pp.287-306
• /
• 2017

Since the 1990s, political geographers have focused on the study of the process of border construction. They have shifted from the old morphological and functional approaches to boundary that have focused on the types and functions of boundaries. Recent scholarship on border studies understand boundaries and the border regions as entities with overlapping and competing relationships not as manifestation of territoriality. There has been the emphasis on the multidimensional actors and the historical and cultural legacies inherent in the border region as well. Based on these recent discussions, this study examines how the border region has been constructed by various actors and strategies in Dandong China, the border city between North Korea and China. Several sanctions including UN Security Council have been resolved and implemented in accordance with North Korea's nuclear and missile development, which is a relevant example to examine the "border as relationships" in which strategies of various actors are competing. In addition, this paper has a significance as a case study on the construction process of border and the characteristics of its materiality, which is a way to overcome the limitation of discourse-oriented critical geopolitical research.

• Journal of the Korean Society of Groundwater Environment
• /
• v.4 no.1
• /
• pp.27-40
• /
• 1997

The hydrogeochemical study on the 15 natural waters was carried out in the vicinity of tunnel excavation site of Donghae largely composed of granite and limestone. The water samples can be classified based on their chemical characteristics into two groups; waters draining in the granitic region(group 1) and the limestone region(group 2). This classification was also confirmed by statistical examination through cluster analysis, and the tunnel seepage waters collected at the same site appear to be included in group 1 and 2 by their sampling period, respectively. According to factor analysis, the waters of group 1 art mainly represented by the weathering of plagioclase to kaolinite and those of group 2 are characterized by the dissolution of calcite. Different properties of the tunnel seepage waters are thought to be resulted from the effective waterproofing processes conducted during the sampling interval to the surface and subsurface leakage zones at the granitic region, which contributed to the change of groundwater flow system. However both the tunnel seepage waters seem to have thermodynamically interacted with rock-forming minerals in their wallrocks. The mixing ratio of the waters from two groups and water-rock interactions are evaluated quantitatively for the tunnel seepage waters through the mass balance approach, and the results are identical with the previous conclusions in this study.

• Journal of Korea Multimedia Society
• /
• v.8 no.4
• /
• pp.473-481
• /
• 2005

In this paper, we propose an image segmentation method preserving object's boundaries by using the number of quantized colors and merging regions using adaptive threshold values. First of all, the proposed method quantizes an original image by a vector quantization and the number of quantized colors is determined differently using PSNR each image. We obtain initial regions from the quantized image, merge initial regions in CIE Lab color space and RGB color space step by step and segment the image into semantic regions. In each merging step, we use color distance between adjacent regions as similarity-measure. Threshold values for region-merging are determined adaptively according to the global mean of the color difference between the original image and its split-regions and the mean of those variations. Also, if the segmented image of RGB color space doesn't split into semantic objects, we merge the image again in the CIE Lab color space as post-processing. Whether the post-processing is done is determined by using the color distance between initial regions of the image and the segmented image of RGB color space. Experiment results show that the proposed method splits an original image into main objects and boundaries of the segmented image are preserved. Also, the proposed method provides better results for objective measure than the conventional method.

• Journal of Korea Multimedia Society
• /
• v.15 no.6
• /
• pp.737-747
• /
• 2012

Recently, in order to support automatic meter reading for conventional metering devices, an image processing-based approach of recognizing the number meter data in the captured meter images has attracted many researchers' interests. Numerical character segmentation is a very critical process for successful recognition. In this paper, we propose an efficient numeric character segmentation method which can segment numeric characters well for any metering device types under diverse illumination environments. The proposed method consists of two consecutive stages; detection of number area containing all numbers as a tight ROI(Region of Interest) and segmentation of numerical characters in the ROI. Detection of tight ROI is achieved in two steps: extraction of rough ROI by utilizing horizontal line segments after illumination enhancement preprocessing, and making the rough ROI more tight through clipping utilizing vertical and horizontal projection about binarized ROI. Numerical character segmentation in the detected ROI is stably achieved in two processes of 'vertical segmentation of each number region' and 'number segmentation in the each vertical segmented number region'. Through the experiments about a homegrown meter image database containing various meter type images of low contrast, low intensity, shadow, and saturation, it is shown that the proposed numeric character segmentation method performs effectively well for any metering device types under diverse illumination environments.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.8
• /
• pp.3435-3442
• /
• 2015

Objective : To provide background information for strengthening cervical cancer prevention in the Pacific by mapping current human papillomavirus (HPV) vaccination and cervical cancer screening practices, as well as intent and barriers to the introduction and maintenance of national HPV vaccination programmes in the region. Materials and Methods: A cross-sectional questionnaire-based survey among ministry of health officials from 21 Pacific Island countries and territories (n=21). Results: Cervical cancer prevention was rated as highly important, but implementation of prevention programs were insufficient, with only two of 21 countries and territories having achieved coverage of cervical cancer screening above 40%. Ten of 21 countries and territories had included HPV vaccination in their immunization schedule, but only two countries reported coverage of HPV vaccination above 60% among the targeted population. Key barriers to the introduction and continuation of HPV vaccination were reported to be: (i) Lack of sustainable financing for HPV vaccine programs; (ii) Lack of visible government endorsement; (iii) Critical public perception of the value and safety of the HPV vaccine; and (iv) Lack of clear guidelines and policies for HPV vaccination. Conclusion: Current practices to prevent cervical cancer in the Pacific Region do not match the high burden of disease from cervical cancer. A regional approach, including reducing vaccine prices by bulk purchase of vaccine, technical support for implementation of prevention programs, operational research and advocacy could strengthen political momentum for cervical cancer prevention and avoid risking the lives of many women in the Pacific.