• Journal of the Korea Computer Graphics Society
• /
• v.24 no.2
• /
• pp.1-9
• /
• 2018

In this paper, we propose a method to restore corrupted black and white facial images to color. Previous studies have shown that when coloring damaged black and white photographs, such as old ID photographs, the area around the damaged area is often incorrectly colored. To solve this problem, this paper proposes a method of restoring the damaged area of input photo first and then performing colorization based on the result. The proposed method consists of two steps: BEGAN (Boundary Equivalent Generative Adversarial Networks) model based restoration and CNN (Convolutional Neural Network) based coloring. Our method uses the BEGAN model, which enables a clearer and higher resolution image restoration than the existing methods using the DCGAN (Deep Convolutional Generative Adversarial Networks) model for image restoration, and performs colorization based on the restored black and white image. Finally, we confirmed that the experimental results of various types of facial images and masks can show realistic color restoration results in many cases compared with the previous studies.

• Journal of the Korea Convergence Society
• /
• v.11 no.7
• /
• pp.19-24
• /
• 2020

WHO declared a global pandemic on March 11th for Corona 19. However, there is a situation where you have to go to building for face-to-face education or seminars for economic and social activities. The first check method of COVID-19 infection is to measure body temperature, so the primary entrance and exit is blocked for near-field body temperature measurement. However, since it is troublesome to check directly, thermal camera is installed at the entrance of the building, and body temperature is measured indirectly using the infrared camera to control access. In case of middle and high schools, universities, and lifelong education center, we need a system that is possible to interoperate with attendance checks and automatically recognizes whether to wear masks and can authenticate students. We proposed the system that is to confirm whether to wear a mask with a camera that is embedded in a smart mirror, and that authenticates the user through voice recognition of the user who wants to enter the building by using voice recognition technology and determines whether to enter them or not. The proposed system can check attendance if it is linked with near-field temperature measurement and attendance check APP of student's smart phone.

• Journal of Broadcast Engineering
• /
• v.25 no.3
• /
• pp.325-337
• /
• 2020

Versatile Video Coding (VVC) is a new video coding standard that is being developed by the Joint Video Experts Team of ISO/IEC/ITU-T and it has adopted various technologies including screen content coding tools. Screen contents have a feature that blocks are likely to have diagonal edges like character regions. If triangular partitioning coding is allowed for screen contents having such the feature, coding efficiency would increase. This paper proposes a intra prediction method using triangular partitioning prediction for screen content coding. Similar to the Triangular Prediction Mode of VVC that supports the triangular partitioning prediction, the proposed method derives two prediction blocks using Horizontal and Vertical modes and then it blends the predicted blocks applying masks with triangle shape to generate a final prediction block. The experimental results of the proposed method showed an average of 1.86%, 1.49%, and 1.55% coding efficiency in YUV, respectively, for VVC screen content test sequences.

• BMB Reports
• /
• v.36 no.2
• /
• pp.179-184
• /
• 2003

Duchenne muscular dystrophy (DMD) is the most common hereditary neuromuscular disease. It is inherited manifestations. In some rare cases, the disease can also be manifested in females. The aim of the present study was to determine the molecular alteration in two cases of nonrelated DMD symptomatic carriers with no previous history of DMD. Multiplex PCR is commonly used to search for deletion in the DMD gene of affected males. This method could not be used in females because the normal X chromosome masks the deletion of the mutated one. Therefor, we used a set of seven highly polymorphic dinucleotide $(CA)_n$ repeat markers that lie within the human dystrophin gene. The deletions were evidenced by hemizygosity of the loci under study. We localized a deletion in the locus 7A (intron 7) on the maternal X chromosome in one case, and a deletion in the region of introns 49 and 50 on the paternal X chromosome in the other. The use of microsatellite genotyping within the DMD gene enables the detection of the mutant allele in female carriers. It is also a useful method to provide DMD families with more accurate genetic counseling.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.11
• /
• pp.41-45
• /
• 2010

Image processing techniques are fundamental in human vision-based image information processing. There have been widely studied areas such as image transformation, image enhancement, image restoration, and image compression. One of research subgoals in those areas is enhancing image information for the correct information retrieval. As a fundamental task for the image recognition and interpretation, image enhancement includes noise filtering techniques. Conventional filtering algorithms may have high noise removal rate but usually have difficulty in conserving boundary information. As a result, they often use additional image processing algorithms in compensation for the tradeoff of more CPU time and higher possibility of information loss. In this paper, we propose a Fuzzy Mask Filtering algorithm that has high noise removal rate but lesser problems in above-mentioned side-effects. Our algorithm firstly decides a threshold based on fuzzy logic with information from masks. Then it decides the output pixel value by that threshold. In a designed experiment that has random impulse noise and salt pepper noise, the proposed algorithm was more effective in noise removal without information loss.

• Archives of design research
• /
• v.17 no.4
• /
• pp.251-258
• /
• 2004

Today we seem to be flooded with digital culture as the age of information has reached its peak. As fusion culture has been generalized, in which the arts and culture of the East and the West are in harmony, and quality of life has been improved, people are enjoying more abundant cultural benefits than ever. In such a situation, we may lose the origin of our culture and disregard our traditional culture due to the mixture of cultures. In addition, it is necessary at this point to distinguish pure culture from mixed one and to re-illuminate the value of our original culture for the next generation. Therefore, the author took interested in Dongraeyaryu, a large-scale festival in Busan, which has been designated as an important intangible cultural property, and carried out a research for its continuous instruction and activation. among contents such as music, costume, dancing and stage properties that compose intangible cultural property, this study selected costume, which has significant visual effects and large differences in shape between old one and contemporary one, for development. By proposing modernized design of costume preferred by the new generation and in harmony with the masks, this study wished to narrow the generation gap, to direct young people's attention to the learning of tradition and to propose motives that activate the culture of local festival.

• Journal of Technologic Dentistry
• /
• v.22 no.1
• /
• pp.89-112
• /
• 2000

Although dental laboratory technicians are prone to be exposed to various work-related health hazardous materials such as dusts, chemicals, etc., the prevalence and nature of work-related health problems of them have not been a matter of great concern in the field of occupational health service in Korea. The purpose of the present investigation was to describe a collected profile of subjective health symptoms and their attributable factors in Korean dental laboratory technicians. A questionnaire listing five groups of health symptoms and five health symptom-related factors was mailed to randomly selected 1,900 dental laboratory technicians. Among them, 1,344 dental laboratory technicians filled out the questionnaires and returnde them. Five groups of health symptoms included musculoskeletal symptom, dermal symptoms, respiratory symptoms, eys symptoms, and ear symptoms. Five health symptom-related factors were occupational environment-related health risk factors, work history, health related habits and status, use of personal protective equipment and general characteristics. Detailed parameters of health risk factors were work posture, vibration, and chemical or physical hazards such as dust, fume, vapor, solvent, light, and noise for occupational environment-related factors; work place, area, number of employees, work hours, career, work part, and work load for work history; Broca's index, hours of sleep, eating, smoking, alcohol, exercise, health examination, and self assessed health status for health habits and status; face masks, goggles, and so on for use of personal protective equipment, and; age, sex, marital status, and education for general characteristics. Before the start of main survey, a pilot survey was carried out for validity and reliability tests of the questionnaire. All the data obtained were coded and analyzed with PC/SAS 6.12 program. The prevalence of health symptoms was the highest in musculoskelton (87.3%), and followde by eyes (78.9%), respiratory organs (64.3%), ears (57.8%), and skin (52.2%) in descending order. Statistically significant risk factors by multiple logistic regression analyses were sex, health examination, self assessed health status, and hand/finger posture in musculoskeletal symptoms; sex, self assessed health status, career, acid gas, and hand contact with resin mixture in deraml symptoms; Broka's smoking, exercise, self assessed health status, and face mask in respiratory symptoms; sex, hours of sleep, self assessed health status, work hours, work load, plaster dust, inadequate lighting, and goggle in eys symptoms, and eating, smoking, self assessed health status, and work load in ear symptoms. With the above considerations in mind, prevalence of subjective symptoms among Korean dental laboratory technicians was relatively high, and they were attributable to most of the occupational environment-related factors, work history, use of personal protective equipment, health habits and status, and general characteristics. Particularly, it is suggested that health promotion programs for promoting self- assessed health status and smoking cessation, preventive measures for protection of the female technicians’health, and reducing work load be necessary, since those factors were associated with more than one subjective symptom.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.45 no.5
• /
• pp.12-18
• /
• 2008

Ag paste was employed for source and drain electrode of OTFTs and for the data metal lines of OTFT-OLED array on PC(polycarbonate) substrate. We tested two kinds of Ag-pastes such as pastes for 325 mesh and 500 mesh screen mask to examine the pattern ability and electrical performance for OTFTs. The minimum feature size was 60 ${\mu}m$ for 325 mesh screen mask and 40 ${\mu}m$ for 500 mesh screen mask. The conductivity was 60 $m{\Omega}/\square$ for 325 mesh and 133.1 $m{\Omega}/\square$ for 500 mesh. For the OTFT performance the mobility was 0.35 $cm^2/V{\cdot}sec$ and 0.12 $cm^2/V{\cdot}sec$, threshold voltage was -4.7 V and 0.9 V, respectively, and on/off current ratio was ${\sim}10^5$, for both screen masks. We applied the 500 mash Ag paste to OTFT-OLED array because of its good patterning property. The pixel was composed of two OTFTs and one capacitor and one OLED in the area of $2mm{\times}2mm$. The panel successfully worked in active mode operation even though there were a few bad pixels.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.20
• /
• pp.9033-9038
• /
• 2014

Background: The purpose of this study was to assess the feasibility of deep inspiration breath-hold (DIBH) based volumetric modulated arc therapy (VMAT) for locally advanced left sided breast cancer patients undergoing radical mastectomy. DIBH immobilizes the tumor bed providing dosimetric benefits over free breathing (FB). Materials and Methods: Ten left sided post mastectomy patients were immobilized in a supine position with both the arms lifted above the head on a hemi-body vaclock. Two thermoplastic masks were prepared for each patient, one for normal free breathing and a second made with breath-hold to maintain reproducibility. DIBH CT scans were performed in the prospective mode of the Varian real time position management (RPM) system. The planning target volume (PTV) included the left chest wall and supraclavicular nodes and PTV prescription dose was 5000cGy in 25 fractions. DIBH-3DCRT planning was performed with the single iso-centre technique using a 6MV photon beam and the field-in-field technique. VMAT plans for FB and DIBH contained two partial arcs ($179^{\circ}-300^{\circ}CCW/CW$). Dose volume histograms of PTV and OAR's were analyzed for DIBH-VMAT, FB-VMAT and DIBH-3DCRT. In DIBH mode daily orthogonal ($0^{\circ}$ and $90^{\circ}$) KV images were taken to determine the setup variability and weekly twice CBCT to verify gating threshold level reproducibility. Results: DIBH-VMAT reduced the lung and heart dose compared to FB-VMAT, while maintaining similar PTV coverage. The mean heart $V_{30Gy}$ was $2.3%{\pm}2.7$, $5.1%{\pm}3.2$ and $3.3%{\pm}7.2$ and for left lung $V_{20Gy}$ was $18.57%{\pm}2.9$, $21.7%{\pm}3.9$ and $23.5%{\pm}5.1$ for DIBH-VMAT, FB-VMAT and DIBH-3DCRT respectively. Conclusions: DIBH-VMAT significantly reduced the heart and lung dose for left side chest wall patients compared to FB-VMAT. PTV conformity index, homogeneity index, ipsilateral lung dose and heart dose were better for DIBH-VMAT compared to DIBH-3DCRT. However, contralateral lung and breast volumes exposed to low doses were increased with DIBH-VMAT.

• Journal of the Institute of Convergence Signal Processing
• /
• v.10 no.1
• /
• pp.7-12
• /
• 2009

In this paper, we propose a directional feature extraction method for off-line handwritten numerals by using the morphological operations. Direction features are obtained from four directional line images, each of which contains horizontal, vertical, right-diagonal and left-diagonal lines in entire numeral lines. Conventional method for extracting directional features uses Kirsch masks which generate edge-shaped double line images for each direction, whereas our method uses directional erosion operations and generate single line images for each direction. To apply these directional erosion operations to the numeral image, preprocessing steps such as thinning and dilation are required, but resultant directional lines are more similar to numeral lines themselves. Our four [$4{\times}4$] directional features of a numeral are obtained from four directional line images through a zoning method. For obtaining the higher recognition rates of the handwrittern numerals, we use the multiple feature which is comprised of our proposed feature and the conventional features of a kirsch directional feature and a concavity feature. For recognition test with given features, we use a multi-layer perceptron neural network classifier which is trained with the back propagation algorithm. Through the experiments with the CENPARMI numeral database of Concordia University, we have achieved a recognition rate of 98.35%.