• Journal of the Korea Society of Computer and Information
• /
• v.25 no.3
• /
• pp.51-55
• /
• 2020

In this paper, an improved FAM is proposed by adopting similarity learning in the existing FAM (Fuzzy Associative Memory) used in image restoration. Image restoration refers to the recovery of the latent clean image from its noise-corrupted version. In serious application like face recognition, this process should be noise-tolerant, robust, fast, and scalable. The existing FAM is a simple single layered neural network that can be applied to this domain with its robust fuzzy control but has low capacity problem in real world applications. That similarity measure is implied to the connection strength of the FAM structure to minimize the root mean square error between the recovered and the original image. The efficacy of the proposed algorithm is verified with significant low error magnitude from random noise in our experiment.

• Journal of Korean Society of Rural Planning
• /
• v.17 no.2
• /
• pp.33-41
• /
• 2011

To evaluate the value of a preserved tree as rural landscape resource, the growth environment and health condition was investigated, and the image evaluation was implemented on land~ape architectural major undergraduate students for zelkova trees in Yesan-gun. The image evaluation results of zelkova trees were as followings; 1) Typical image of preserved tree examined by Semantic Differential Scale were 'Old', 'Big', and 'Good'. 2) The 'big' image of zelkova tree and the height of tree, the width of tree crown, the breast girth of tree, the root girth of tree, the external formation of tree, and the health of tree bark is mutually related. Especially, the correlation between the 'big' and the external formation and the width of tree crown is high. 3) Typical image of preserved tree examined by Likert Scale were 'Natural', 'Green', 'Peaceful', and 'Rural'. 4) The preservation necessity for preserved tree was highly related with the state of ground, and the management necessity for preserved tree was highly related with contamination level and the state of ground. The appropriate management plan for preserved tree are proposed to improve the quality of rural landscape(basis of these results).

• The Journal of Korean Academy of Prosthodontics
• /
• v.32 no.3
• /
• pp.455-469
• /
• 1994

Regular radiographic examination has been considered an essential diagnositic method for osseointegrated dental implantation. This study investigated marginal bone loss through the measurement on periapical radiographs and changes in bone density through digital subtraction image radiographic method around 88 endoseous root-form dental implants in 43 human subjects. Four types of endosseous dental implants were investigated : Standard series, Mini series and Hex-lock system of Steri-Oss Dental implant system, and $Br{\aa}nemark$-type implant from 3i dental implant system, in a 3 month interval for a total period of 12 months. The results were as follows : 1. Rapid bone loss occurred in the first 3 months in all 4 groups, and the bone level stabilized at the first thread of the implant fixtures. Amount of bone loss for 12 months showed correlation with the length of the polished neck portion. 2. Most of the implant systems showed resorption of alveolar bone up to the polished neck portion although a long polished neck could delay the resolution. 3. Alveolar bone loss apical to the polished neck portion stabilized at the first thread of the fixtures with no correlation to either the time of exposure of the polished neck or types of implant systems. 4. No changes in bone density around the implant threads were observed throughout the experimental period. Bone density decreased at the marginal bone, and increased at the newly-formed alveolar crest. These results indicate that most of the alveolar bone loss occur within the first 12 months after installation of endosseous root-form dental implants resulting in the exposure of polished neck portions, and the bone level stabilizes thereafter at the first thread portions of the implant fixtures. The experimental period of 12 months seems insufficient for observing changes in bone density, and a long-term observation should be needed.

• Journal of the Society of Cosmetic Scientists of Korea
• /
• v.30 no.2
• /
• pp.207-210
• /
• 2004

Glycyrrhiza uralensis (licorice root) is very useful medicinal herb because of strong anti-inflammatory and anti-wrinkle effect. Therefore, it is widely used in functional cosmetics. However, it is insoluble and easily decomposed by light, heat, oxygen, etc. In this study, we first prepared NanoSolve-Licorice (30-50nm) using Glycyrrhiza uralensis and propylene glycol! hydrogenated lecithin/caprylic/capric triglyceride/glycerin/water system with microfluidizer. And then, NanoSolve-Licorice and porous PMMA are dispersed in ethanol. Finally, we could get a stabilized system with high-pressure homogenizer (1,000 Bar, 3 passes). According to HPLC measurement for glabridin content, our system is more stable compared with general liposome ones. Capsulated licorice has an enhanced anti-inflammatory effect on account of excellent skin penetration. We also evaluated our final product through image analyzer, particle size analyzer, FF-TEM and chromameter.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.6
• /
• pp.568-574
• /
• 2020

In this paper, we propose a method to reduce the square root computation having high computation complexity in Canny edge detection algorithm using image processing. The proposed method is to reduce the number of operation calculating gradient magnitude using pixel's continuity using make a specific pattern instead of square root computation in gradient magnitude calculating operation. Using various test images and changing number of hole pixels, we can check for calculate match rate about 97% for one hole, and 94%, 90%, 88% when the number of hole is increased and measure decreasing computation time about 0.2ms for one hole, and 0.398ms, 0.6ms, 0.8ms when the number of hole is increased. Through this method, we expect to implement low power embedded vision system through high accuracy and a reduced operation number using two-hole pixels.

• Restorative Dentistry and Endodontics
• /
• v.45 no.4
• /
• pp.46.1-46.8
• /
• 2020

Objectives: This study aimed to investigate the incidence and location of the second mesiobuccal root (MB2) canal in maxillary molars with the aid of various measuring points and lines using cone-beam computed tomography (CT). Materials and Methods: A total of 205 images of patients who underwent cone-beam CT examinations between 2011 and 2015 as part of their dental diagnosis and treatment were included. There were 76 images of the maxillary first molar and 135 images of the maxillary second molar. Canal orifices were detected at -1 mm from the top of the pulpal floor on cone-beam CT images. Image assessment was performed by 2 observers in reformatted image planes using software. Assessments included measurement of the distance between the MB1 and MB2 canals, and the angles between the lines connecting the MB1-MB2 and distobuccal (DB)-palatal (P) canals. The data were analyzed using the student's t-test. Results: The prevalence of the MB2 canal was 86.8% in the first molar and 28.9% in the second molar. The angle between the lines connecting the MB1-MB2 and DB-P canals was 2.3° ± 5.7° in the first molar and -3.95° ± 7.73° in the second molar. The distance between the MB1 and MB2 canals was 2.1 ± 0.44 mm in the first molar and 1.98 ± 0.42 mm in the second molar. Conclusions: The angles between the lines connecting the MB1-MB2 and DB-P canals was almost parallel. These findings may aid in the prediction of the location of the MB2 canal orifice.

• Journal of the Korean Society of Radiology
• /
• v.18 no.3
• /
• pp.267-273
• /
• 2024

Using a cloud-based vertex AI platform that can develop an artificial intelligence learning model without coding, this study easily developed an artificial intelligence learning model by the non-professional general public and confirmed its clinical applicability. Nine dental diseases and 2,999 root disease X-ray images released on the Kaggle site were used for the learning data, and learning, verification, and test data images were randomly classified. Image classification and multi-label learning were performed through hyper-parameter tuning work using a learning pipeline in vertex AI's basic learning model workflow. As a result of performing AutoML(Automated Machine Learning), AUC(Area Under Curve) was found to be 0.967, precision was 95.6%, and reproduction rate was 95.2%. It was confirmed that the learned artificial intelligence model was sufficient for clinical diagnosis.

• Restorative Dentistry and Endodontics
• /
• v.32 no.2
• /
• pp.87-94
• /
• 2007

This study was done to evaluate transportation of the apical foramen after 0.5 mm overinstrumentation by ProFile, ProTaper and $K^3$ in simulated resin root canal. Sixty simulated resin root canal with a curvature of J and S-shape were divided into two groups. Each group consisted of three subgroups with 10 blocks according to the instruments used: $ProFile^{(R)},\;ProTaper^{TM},\;and\;K^{3TM}$. Simulated resin root canal was prepared by ProFile, ProTaper and $K^3$ with 300 rpm by the crown-down preparation technique. Pre- and post-instrumentation apical foramen images were overlapped and recorded with Image-analyzing microscope 100X (Camcope, Sometech Inc, Korea). The amounts of difference in width and dimension on overlapped images were measured after reference points were determined by Image Analysis program ($Image-Pro^{(R)}$ Express, Media Cybernetic, USA). Data were analyzed using Kruskal-Wallis and Mann-Whitney U-test. The results suggest that ProFile showed significantly less canal transportation and maintained original apical foramen shape better than $K^3$ and ProTaper.

• Journal of the Korean Society of Radiology
• /
• v.16 no.1
• /
• pp.7-13
• /
• 2022

This study compared the aortic root image by using the ECG gating and non-ECG gating methods. We observed the presence or absence of progression of the aortic root image in the images examined by the high pitch (flash) chest pain protocol method and in the patients tested without ECG gating by the conventional method. The AAPM phantom was scanned by using high pitch (flash) chest pain protocol and general chest pain protocol. CTDI values were compared. By ECG gating, the blurring of ascending aorta was significantly reduced compared to the existing non-ECG gating test method, and the image quality of the aortic root was improved. Within the parametar range that did not show differences in noise, uniformity, and high contrast resolution, CTDI values were lower when tested with the high-pitch chest pain protocol. It was found that there is an advantage in dose reduction, and if it is applied and applied to diagnostic fields such as dissection using the dose reduction mode in the cardiac field, it is a very important test for patients who need rapid diagnosis and prompt treatment as well as a dramatic reduction in exposure dose. It is presumed to be a method.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2017.06a
• /
• pp.183-183
• /
• 2017

In the early part of rice growth, root volume primarily limits the amount of plant-accessible nitrogen (N). Therefore, knowledge of the root development is important for modeling N uptake of rice. The timing when the volume of rhizosphere cover the whole soil is also important to carry out timely top dressing. However, information about initial root expansion and associated N uptake is limited due to intrinsic technical difficulties in assessing below-ground processes. Some studies, however, showed a close relationship between below-ground root and above-ground leaf development, suggesting a possibility that above-ground attributes could serve as surrogates for the root processes. In this study, we investigated the relationship between below-ground and above-ground development of rice. Field experiments were conducted where we cultivated Koshihikari (a leading cultivar in Japan) for four different cropping schedules in 2012. In 2016, Gimbozu (HEG4) and three flowering time mutant lines of Gimbozu (X61 (se13), HS276 (ef7), DMG9 (se13, ef7)) were examined for a single season. Experiments were performed with three replications in a completely randomized design. We monitored ammonium-N concentration ([NH4+-N]) in soil solution by repeatedly taking samples from a porous tubing (10-cm long) vertically inserted at the most distant point from surrounding rice hills. Samples were taken in triplicate (= triplicate tubes) and every three days from transplanting in each experimental unit. For above-ground attributes, leaf area index (LAI) was measured in 2012, whereas soil coverage ratio was estimated by image processing in 2016. Results showed that [NH4+-N] increased gradually after transplanting and then rapidly decreased from a certain day. This distinct drop in [NH4+-N] informed us the timing at which the rice root system reached the point of porous tubing and thus essentially covered the whole soil volume. The LAI at the dropping point was about 0.43 regardless of the cropping schedules in 2012 experiment. In 2016, the coverage ratio at the N dropping point was within the range of 0.12 to 0.19 for four genotypes having different growth durations. In addition, the coverage ratios at seven weeks after the transplanting showed a good correspondence to LAI across the four genotypes. We therefore conclude that both LAI and coverage ratio may serve as robust indicators for root development and might be useful to estimate the timing when the root system fully cover the soil volume. Results obtained here will also contribute to develop models that can predict not only above-ground canopy development but also associated below-ground processes.