• Korean Institute of Interior Design Journal
• /
• v.23 no.6
• /
• pp.22-32
• /
• 2014

Development of digital technology, which is individualizing and differentiating the world, makes time and space facilitate multi-layering in the contemporary society. It gives a large influence on the contemporary architecture that inducing the visual and spatial experience. Also, It generates new images through the skin of architecture, which implies the contingent and fluid characteristics. These phenomenon show that various parameters are working on the architectural skin simultaneously. Such complexity make the structure of open space and diversity that are homogenized and synchronized. Like this, the architectural skin implies 'multiplicity': qualitative difference which is enable to change and create new images. This characteristic generates instant images changing variously and semantics constantly by the function of skin as a filter. Also, the architectural skin integrates or relocates of relationships between the various information and elements appearing in contemporary society in order to escape the customary relationship between internal and external. Furthermore, the inside and outside of the mixture as a collection of sense has been recognized as one image. This image of mixture consists of one unified continuous integration and extend the meaning of a fluid interface not just surface of the building. The skin of the contemporary architecture is very technical, so its meaning and role is expanded as a complex that exchange interaction. This means that the skin itself has functional elements of the integrated multiple skin to assist. Also it can form a multi-layered relationship and act as a wide range of interfaces depending on the perception of the observer. Therefore the multiplicity of the architectural skin indicates the importance as a boundary that generate images of new life through the sensory perception and implicit force. And it shows potential as the intermediary to try to communicate.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.12
• /
• pp.1100-1108
• /
• 2015

A camera-based real-time hand posture and gesture recognition system is proposed for controlling various devices inside automobiles. It uses an imaging system composed of a camera with a proper filter and an infrared lighting device to acquire images of hand-motion sequences. Several steps of pre-processing algorithms are applied, followed by a background normalization process before segmenting the hand from the background. The hand posture is determined by first separating the fingers from the main body of the hand and then by finding the relative position of the fingers from the center of the hand. The beginning and ending of the hand motion from the sequence of the acquired images are detected using pre-defined motion rules to start the hand gesture recognition. A set of carefully designed features is computed and extracted from the raw sequence and is fed into a decision tree-like decision rule for determining the hand gesture. Many experiments are performed to verify the system. In this paper, we show the performance results from tests on the 550 sequences of hand motion images collected from five different individuals to cover the variations among many users of the system in a real-time environment. Among them, 539 sequences are correctly recognized, showing a recognition rate of 98%.

• Clinical and Experimental Pediatrics
• /
• v.61 no.8
• /
• pp.245-252
• /
• 2018

Purpose: This study investigated patterns of ischemic injury observed in brain images from patients with neonatal group B Streptococcal (GBS) meningitis. Methods: Clinical findings and brain images from eight term or near-term newborn infants with GBS meningitis were reviewed. Results: GBS meningitis was confirmed in all 8 infants via cerebrospinal fluid (CSF) analysis, and patients tested positive for GBS in both blood and CSF cultures. Six infants (75.0%) showed early onset manifestation of the disease (<7 days); the remaining 2 (25.0%) showed late onset manifestation. In 6 infants (75%), cranial ultrasonography showed focal or diffuse echogenicity, suggesting hypoxic-ischemic injury in the basal ganglia, cerebral hemispheres, and periventricular or subcortical white matter; these findings are compatible with meningitis. Findings from magnetic resonance imaging (MRI) were compatible with bacterial meningitis, showing prominent leptomeningeal enhancement, a widening echogenic interhemisphere, and ventricular wall thickening in all infants. Restrictive ischemic lesions observed through diffusion-weighted imaging were evident in all eight infants. Patterns of ischemic injury as detected through MRI were subdivided into 3 groups: 3 infants (37.5%) predominantly showed multiple punctuate lesions in the basal ganglia, 2 infants (25.0%) showed focal or diffuse cerebral infarcts, and 3 infants (37.5%) predominantly showed focal subcortical or periventricular white matter lesions. Four infants (50%) showed significant developmental delay or cerebral palsy. Conclusion: Certain patterns of ischemic injury are commonly recognized in brain images from patients with neonatal GBS meningitis, and this ischemic complication may modify disease processes and contribute to poor neurologic outcomes.

• Journal of radiological science and technology
• /
• v.39 no.2
• /
• pp.257-262
• /
• 2016

This study aimed to suggest a novel method of modeling a hearing aid ear shell based on Digital Imaging and Communication in Medicine (DICOM) in the hearing aid ear shell manufacturing method using a 3D printer. In the experiment, a 3D external auditory meatus was extracted by using the critical values in the DICOM volume images, and the modeling surface structures were compared in standard type STL (STereoLithography) files which could be recognized by a 3D printer. In this 3D modeling method, a conventional ear model was prepared, and the gaps between adjacent isograms produced by a 3D scanner were filled with 3D surface fragments to express the modeling structure. In this study, the same type of triangular surface structures were prepared by using the DICOM images. The result showed that the modeling surface structure based on the DICOM images provide the same environment that the conventional 3D printers may recognize, eventually enabling to print out the hearing aid ear shell shape.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.12A
• /
• pp.2019-2026
• /
• 2001

In this paper, we proposed the car license plate extraction and recognition algorithm using both the dynamical thresholding method and the kohonen algorithm. In general, the areas of car license plate in the car images have distinguishing characteristics, such as the differences in intensity between the areas of characters and the background of the plates, the fixed ratio of width to height of the plates, and the higher dynamical thresholded density rate 7han the other areas, etc. Taking advantage of the characteristics, the thresholded images were created from the original images, and also the density rates were computed. A candidate area was selected, whose density rate was corresponding to the properties of the car license plate obtained from the car license plate. The contour tracking method by utilizing the Kohonen algorithm was applied to extract the specific area which included characters and numbers from an extracted plate area. The characters and numbers of the license place were recognized by using Kohonen algorithm. Kohonen algorithm was very effective o? suppressing noises scattered around the contour. In this study, 80 car images were tested. The result indicate that we proposed is superior in performance.

• Archives of design research
• /
• v.19 no.4 s.66
• /
• pp.205-208
• /
• 2006

This work is a interactive digital art work which used the multiplex of jitter. It is an work which used a cross concept of two images. This work shows two kinds of images. One is on the wall through the gap of fluorescent lamp screen, and the other is on the fluorescent lamp screen. Two images are intercepted and comes out to the length as the multiplex of the jitter. The appearance of the spectator be recognized on the fluorescent lamp screen or on the wall, by two branch image which comes out intersecting of a length with multiplex function of the jitter. Two branch features of the image which it produces and the spectator which is input at real-time is equally divided, or in impression of juxtaposition goes in the spectator. It expresses the duplicity of the human being, with physical existence space divides the time space which we feel and there is a governing grammar which is different with each other and to express the thing it becomes. It used the image of the screen which it produces with the fluorescent lamp and cross concept.

• The Journal of the Korea Contents Association
• /
• v.11 no.5
• /
• pp.125-137
• /
• 2011

Recently the research on the system using images taken from camera phones as input is actively conducted. This paper proposed a system that shows wine pictures which are similar to the input wine label in order. For the calculation of the similarity of images, the representative color of each cell of the image, the recognized text color, background color and distribution of feature points are used as the features. In order to calculate the difference of the colors, RGB is converted into CIE-Lab and the feature points are extracted by using Harris Corner Detection Algorithm. The weights of representative color of each cell of image, text color and background color are applied. The image similarity is calculated by normalizing the difference of color similarity and distribution of feature points. After calculating the similarity between the input image and the images in the database, the images in Database are shown in the descent order of the similarity so that the effort of users to search for similar wine labels again from the searched result is reduced.

• Journal of the Korean Institute of Rural Architecture
• /
• v.24 no.3
• /
• pp.1-11
• /
• 2022

Purpose: This place, which is currently becoming an issue due to historical preservation and landscape protection, is also a place where urban residents around Taereung actually visit often. Thus, this study aims to analyze the importance of the evaluating factors in creating a relatable image of the city. Methods: Evaluation items were selected by reviewing related books and research literatures and reassessing the reviewed items through an expert group interview (FGI). For the selected evaluation items, the relative importance of the evaluation items for the place image was analyzed by applying the hierarchical analysis technique (AHP) to each user group. Result: A place becomes a memory in people's experiences and time, and it has the image and identity of the region where those experiences and memories are found again as a space called "place". The method of analyzing the importance of evaluation items between place images used in this study quantified the factors recognized as abstract images and identified the degree of influence between elements, but has limitation in that it targeted specific places. However, the analysis method on the place image recognition suggests the use of itemized variables for characteristics between place images, so future research on the identity of other place images can be conducted together. Also, the evaluation method of the image that recognizes the place has an objective meaning in that it can measure the image of the place quantitatively. In the future, it can be applied in creating an image forming factor or urban identity for place recognition in many regions

• Journal of Korea Multimedia Society
• /
• v.25 no.10
• /
• pp.1375-1385
• /
• 2022

In this paper, we propose a semi-supervised domain adaptation solution to deal with practical face recognition (FR) scenarios where a single face image for each target identity (to be recognized) is only available in the training phase. Main goal of the proposed method is to reduce the discrepancy between the target and the source domain face images, which ultimately improves FR performances. The proposed method is based on the Domain Adatation network (DAN) using an MMD loss function to reduce the discrepancy between domains. In order to train more effectively, we develop a novel loss function learning strategy in which MMD loss and cross-entropy loss functions are adopted by using different weights according to the progress of each epoch during the learning. The proposed weight adoptation focuses on the training of the source domain in the initial learning phase to learn facial feature information such as eyes, nose, and mouth. After the initial learning is completed, the resulting feature information is used to training a deep network using the target domain images. To evaluate the effectiveness of the proposed method, FR performances were evaluated with pretrained model trained only with CASIA-webface (source images) and fine-tuned model trained only with FERET's gallery (target images) under the same FR scenarios. The experimental results showed that the proposed semi-supervised domain adaptation can be improved by 24.78% compared to the pre-trained model and 28.42% compared to the fine-tuned model. In addition, the proposed method outperformed other state-of-the-arts domain adaptation approaches by 9.41%.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.31 no.2 s.161
• /
• pp.225-235
• /
• 2007

The purpose of this study is to grasp the character of consumers and the situation of domestic kidult fashion market. By grasping the distribution of kidult generation and the factors of product-selection based on products images, this research could be a substantial data to kidult associated company product planning and marketers. Subjects for this study were 213 Daegu women from 20 to 30 yearn of age who have high propensity to kidult. The statistical treatment of material used by SPSS 1.0 program consists of frequency analysis, factor analysis, multiple regression analysis, cluster analysis, and t-test. As a results, the characteristics of kidult consumers are classified as six factors. On image toward of kidult fashion goods, there was a significant difference 20 and 30 aged generation. According to fashion goods group, each group recognized on image of fashion products as follow: Group A is 'fancy', group B is 'childish', group C are 'familiarity', group D was recognized as 'fancy' and was identical to A on adjective expression, but was different A on recognition. All consumer characteristics of fun, character, girlish, nostalgia have a significant relation with the recurrence of products selection factor, and its order was character, girlish, nostalgia, and fun.