• The KIPS Transactions:PartB
• /
• v.13B no.7 s.110
• /
• pp.689-698
• /
• 2006

Pattern recognition is the study of how machines can observe the environment, learn to distinguish patterns of interest from their background, and make sound and reasonable decisions about the categories of the patterns. Color image consists of various color patterns. And most pattern recognition methods use the information of color which has been trained and extract the feature of the color. This thesis extracts adaptively specific color feature from images with several limited colors. Because the number of the color patterns is limited, the distribution of the color in the image is similar. But, when there are some noises and distortions in the image, its distribution can be various. Therefore we cannot extract specific color regions in the standard image that is well expressed in special color patterns to extract, and special color regions of the image to test. We suggest new method to reduce the error of recognition by extracting the specific color feature adaptively for images with the low distortion, and six test images with some degree of noises and distortion. We consequently found that proposed method shouws more accurate results than those of statistical pattern recognition.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.10
• /
• pp.61-67
• /
• 2016

With the current high distribution rate of smart devices and the recent development of computing technology, user interest in multimedia, such as photos, videos, and so on, has rapidly increased, which is a departure from the simple pattern of information retrieval. Because of these increasing interests, image processing techniques, which generate and process images for diverse applications, are being developed. In entertainment recently, there are some techniques that present a celebrity's image as a mosaic comprising many small images. In addition, studies into the mosaic technique are actively conducted. However, conventional mosaic techniques result in a long processing time as the number of database images increases, because they compare the images in the databases sequentially. Therefore, to increase search efficiency, this paper proposes an algorithm to generate a mosaic image using a discrete cosine transform (DCT) hash. The proposed photo mosaic-generation algorithm is composed of database creation and mosaic image generation. In database creation, it first segments images into blocks with a predefined size. And then, it computes and stores a DCT hash set for each segmented block. In mosaic generation, it efficiently searches for the most similar blocks in the database via DCT hash for every block of the input image, and then it generates the final mosaic. With diverse experimental results, the proposed photo mosaic-creation algorithm can effectively generate a mosaic, regardless of the various types of images and sizes.

• Journal of Korean Society of Transportation
• /
• v.23 no.2
• /
• pp.107-116
• /
• 2005

The information on travel time in providing the information of traffic to drivers is one of the most important data to control a traffic congestion efficiently. Especially, this information is the major element of route choice of drivers, and based on the premise that it has the high degree of confidence in real situation. This study developed a vehicle arrival time prediction algorithm called as "VAT-DV" for 6 corridors in total 6.1Km of "Nam-san area trffic information system" in order to give an information of congestion to drivers using VMS, ARS, and WEB. The spatial scope of this study is 2.5km~3km sections of each corridor, but there are various situations of traffic flow in a short period because they have signalized intersections in a departure point and an arrival point of each corridor, so they have almost characteristics of interrupted and uninterrupted traffic flow. The algorithm uses the information on a demand volume and a queue length. The demand volume is estimated from density of each points based on the Greenburg model, and the queue length is from the density and speed of each point. In order to settle the variation of the unit time, the result of this algorithm is strategically regulated by importing the AVI(Automatic Vehicle Identification), one of the number plate matching methods. In this study, the AVI travel time information is composed by Hybrid Model in order to use it as the basic parameter to make one travel time in a day using ILD to classify the characteristics of the traffic flow along the queue length. According to the result of this study, in congestion situation, this algorithm has about more than 84% degree of accuracy. Specially, the result of providing the information of "Nam-san area traffic information system" shows that 72.6% of drivers are available.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.10
• /
• pp.1916-1923
• /
• 2007

We have studied to obtain the SAW filter for the passband was formed on the Langasite substrate and was evaporated by Aluminum-Copper alloy and thin we performed computer-simulated by simulator. We cm fabricate that the block weighted type IDT as an input transducer of the filter and the withdrawal weighted type IDT as an output transducer of the filter from the results of our computer-simulation. Also, we have performed to obtain the properly design conditions about phase shift of the SAW filter for WCDMA. We have employed that the number of pairs of the input and output IDT are 50 pairs and the thickness and the width of reflector are $5000\;{\AA}$ and $3.6{\mu}m$ respectively. And we have employed that the distances from the hot electrode to the reflector are $2.0{\mu}m$, $2.4{\mu}m$ and the distance from the hot electrode to the ground is $1.5{\mu}m$ respectively. Frequency response of the fabricated SAW filter has the property that the center frequency is about 190MHz and bandwidth at the 3dB is probably 7,8MHz. And we could obtain that return loss is less then -18dB, ripple characteristics is probably 3dB and triple transit echo is less then -25dB after when we have matched impedance.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.847-859
• /
• 2021

Recently, as the number of high-resolution satellite SAR images increases, the demand for precise matching of SAR imagesin change detection and image fusion is consistently increasing. RMSE (Root Mean Square Error) values using GCPs (Ground Control Points) selected by analysts have been widely used for quantitative evaluation of image registration results, while it is difficult to find an approach for automatically measuring the registration accuracy. In this study, a feasibility analysis was conducted on using the FSIM (Feature Similarity) index as a measure to evaluate the registration accuracy. TerraSAR-X (TSX) staring spotlight data collected from various incidence angles and orbit directions were used for the analysis. FSIM was almost independent on the spatial resolution of the SAR image. Using a single SAR image, the FSIM with respect to registration errors was analyzed, then use it to compare with the value estimated from TSX data with different imaging geometry. FSIM index slightly decreased due to the differencesin imaging geometry such as different look angles, different orbit tracks. As the result of analyzing the FSIM value by land cover type, the change in the FSIM index according to the co-registration error was most evident in the urban area. Therefore, the FSIM index calculated in the urban was mostsuitable for determining the accuracy of image registration. It islikely that the FSIM index has sufficient potential to be used as an index for the co-registration accuracy of SAR image.

• Journal of vocational education research
• /
• v.36 no.4
• /
• pp.57-78
• /
• 2017

This study aimed to make proposals to develop an apprenticeship program and organize the apprenticeship curriculum by conducting an overall analysis of how vocational education and training high schools participating in the apprenticeship system(apprenticeship schools) organized the apprenticeship program in the school curriculum. To that end, the study analyzed the current state of the apprenticeship curriculum of 33 apprenticeship schools and came up with the following results: First, the apprenticeship class and the general class had a similar relevance between 'departments' and 'areas and goals of student training' and between 'departments' and 'qualifications,' while the apprenticeship class had a higher relevance between 'areas and goals of student training' and 'qualifications' than the general class. Second, both the required and optional competency units of the apprenticeship program were relatively evenly included in the Off-JT and OJT. Third, the competency units of the apprentice program were included in the technical subjects of the 2009 revised curriculum as well as the NCS practical subjects of the 2015 revised curriculum. Fourth, although most of the competency units of the apprenticeship program have a high correlation with the technical subjects of the school curriculum, there were also many schools showing a low correlation. Fifth, although the hierarchy of organizing the competency units of the apprenticeship program by semester was mostly high, there were a considerable number of schools with a low hierarchy. As a result, this study made the following policy proposals: granting a grace period for approval of the changes in the curriculum of the apprenticeship, distributing the matching table before and after the revision of the NCS competency units, organizing subjects not included in the national curriculum, creating subjects specialized for companies, and monitoring and consulting the curriculum of the apprenticeship schools.

• Tuberculosis and Respiratory Diseases
• /
• v.82 no.3
• /
• pp.234-241
• /
• 2019

Background: The utility of computed tomography (CT) in the differential diagnosis of patients with chronic obstructive pulmonary disease (COPD) exacerbation remains uncertain. However, due to the low cost associated with CT scan along with the impact of Koreas' health insurance system, there has been a rise in the number of CT scans in the patients with initial diagnosis of COPD exacerbations. Therefore, the utility of CT in the differential diagnosis was investigated to determine whether performing CT scans affect the clinical outcomes of the patients with an initial diagnosis of COPD exacerbation. Methods: This study involved 202 COPD patients hospitalized with an initial diagnosis of COPD exacerbation. We evaluated the change in diagnosis or treatment after performing a CT scan, and compared the clinical outcomes of patient groups with vs. without performing CT (non-CT group vs. CT group). Results: After performing CT, the diagnosis was changed for two (3.0%) while additional diagnoses were made for 27 of the 64 patients (42.1%). However, the treatment changed for only one (1.5%), and six patients (9.3%) received supplementary medication. There were no difference in the median length of hospital stay (8 [6-13] days vs. 8 [6-12] days, p=0.786) and intensive care unit care (14 [10.1%] vs. 11 [16.7%], p=0.236) between the CT and non-CT groups, respectively. These findings remained consistent even after the propensity score matching. Conclusion: Utility of CT in patients with acute COPD exacerbation might not be helpful; therefore, we do not recommend chest CT scan as a routine initial diagnostic tool.

• The Journal of Advanced Prosthodontics
• /
• v.11 no.5
• /
• pp.239-246
• /
• 2019

PURPOSE. The purpose of this study was to propose and assess a shade guide for pink gingival aesthetics using a Spanish population sample. MATERIALS AND METHODS. The $L^*$, $C^*$, h, $a^*$ and $b^*$ coordinates of 259 participants were measured using a spectrophotometer in 3 standardized points along the attached gingiva of the maxillary central incisors. A hierarchical clustering analysis was applied to obtain separate solutions regarding the number of shade tabs. For each of the solutions obtained, color differences (${\Delta}E^*$) were calculated using the CIELab and CIEDE2000 formulas, and the proposed shade guide was selected considering (1) the color differences between tabs and (2) the coverage error of each of the solutions. RESULTS. The proposed shade guide consisted of 8 gingival shade tabs and achieved CIELab and CIEDE2000 coverage errors of less than the respective 50:50% acceptability thresholds (${\Delta}E^*=4.6$ units and ${\Delta}E_{00}=4.1$). The coordinates for the various gingival shade tabs were as follows: Tab 1: $L^*43.3$, $a^*21.9$, $b^*12.3$ (1.6); Tab 2: $L^*42.9$, $a^*34.1$, $b^*19.1$; Tab 3: $L^*46.5$, $a^*25.8$, $b^*10.9$; Tab 4: $L^*46.5$, $a^*27.3$, $b^*15.1$; Tab 5: $L^*49.6$, $a^*23.5$, $b^*16.8$; Tab 6: $L^*51.5$, $a^*19.7$, $b^*13.6$; Tab 7: $L^*55.9$, $a^*22.0$, $b^*15.0$; and Tab 8: $L^*56.0$, $a^*19.9$, $b^*18.8$. CONCLUSION. The CIELab and CIEDE2000 coverage errors for the 8 shade tabs of the proposed gingival shade guide were significantly lower than those of other guides. Therefore, despite the limitations of this study, the proposed guide is more appropriate for matching gingival shade in the Spanish general population.

• Journal of Veterinary Science
• /
• v.23 no.4
• /
• pp.55.1-55.12
• /
• 2022

Background: ASF was first reported in Kenya in 1910 in 1921. In China, ASF spread to 31 provinces including Henan and Jiangsu within six months after it was first reported on August 3, 2018. The epidemic almost affected the whole China, causing direct economic losses of tens of billions of yuan. Cause great loss to our pig industry. As ELISA is cheap and easy to operate, OIE regards it as the preferred serological method for ASF detection. P54 protein has good antigenicity and is an ideal antigen for detection. Objective: To identify a conservative site in the African swine fever virus (ASFV) p54 protein and perform a Cloth-enzyme-linked immunosorbent assay (ELISA) for detecting the ASFV antibody in order to reduce risks posed by using the live virus in diagnostic assays. Method: We used bioinformatics methods to predict the antigen epitope of the ASFV p54 protein in combination with the antigenic index and artificially synthesized the predicted antigen epitope peptides. Using ASFV-positive serum and specific monoclonal antibodies (mAbs), we performed indirect ELISA and blocking ELISA to verify the immunological properties of the predicted epitope polypeptide. Results: The results of our prediction revealed that the possible antigen epitope regions were A23-29, A36-45, A72-94, A114-120, A124-130, and A137-150. The indirect ELISA showed that the peptides A23-29, A36-45, A72-94, A114-120, and A137-150 have good antigenicity. Moreover, the A36-45 polypeptide can react specifically with the mAb secreted by hybridoma cells, and its binding site contains a minimum number of essential amino acids in the sequence 37DIQFINPY44. Conclusions: Our study confirmed a conservative antigenic site in the ASFV p54 protein and its amino acid sequence. A competitive ELISA method for detecting ASFV antibodies was established based on recombinant p54 and matching mAb. Moreover, testing the protein sequence alignment verified that the method can theoretically detect antibodies produced by pigs affected by nearly all ASFVs worldwide.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.5
• /
• pp.30-42
• /
• 2022

Due to the increase in construction of tunnels, the burdens of maintenance works for tunnel structures have been increasing in Korea. In addition, the increase of traffic volume and aging of materials also threatens the safety of tunnel facilities, therefore, maintenance costs are expected to increase significantly in the future. Accordingly, automated condition assessment technologies like image-based tunnel scanning system for inspection and diagnosis of tunnel facilities have been proposed. For image-based tunnel scanning system, it is key to create a planar image through stitching of multiple images captured by tunnel scanning system. In this study, performance of feature-based stitching algorithms suitable for stitching tunnel scanning images was evaluated. In order to find a suitable algorithm SIFT, ORB, and BRISK are compared. The performance of the proposed algorithm was determined by the number of feature extraction, calculation speed, accuracy of feature matching, and image stitching result. As for stitching performance, SIFT algorithm was the best in all parts of tunnel image. ORB and BRISK also showed satisfactory performance and short calculation time. SIFT can be used to generate precise planar images. ORB and BRISK also showed satisfactory stitching results, confirming the possibility of being used when real-time stitching is required.