• Korean Journal of Remote Sensing
• /
• v.9 no.2
• /
• pp.21-34
• /
• 1993

Digitalized topographic information is necessary for many areas such as landscape analysis, civil engineering planning and design, and geographic information systems. It can also be used in flight simulator and automatic navigation of unmanned plane if it is stored in computer in relevant format. Topographic information is coded with various symbols including contour lines, and is analyzed by trained personnels. The information should be stored in computer for automatic analysis, but it requires a lot of time and manpower to enter the contours using manual input devices such as digitizing tablet. This paper deals with automatic extraction and reconstruction of 3D topographic information from 2D terrain map. Several algorithms were developed in this work including contour segment finding algorithm and contour segment linking algorithm. The algorithm were tested using real 2D terrain map.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.729-748
• /
• 2021

Vocal detection is one of the fundamental steps in musical information retrieval. Typically, the detection process consists of feature extraction and classification steps. Recently, neural networks are shown to outperform traditional classifiers. In this paper, we report our study on how to improve detection accuracy further by carefully choosing the parameters of the deep network model. Through experiments, we conclude that a feature-classifier model is still better than an end-to-end model. The recommended model uses a spectrogram as the input plane and the classifier is an 18-layer convolutional neural network (CNN). With this arrangement, when compared with existing literature, the proposed model improves the accuracy from 91.8% to 94.1% in Jamendo dataset. As the dataset has an accuracy of more than 90%, the improvement of 2.3% is difficult and valuable. If even higher accuracy is required, the ensemble learning may be used. The recommend setting is a majority vote with seven proposed models. Doing so, the accuracy increases by about 1.1% in Jamendo dataset.

• The korean journal of orthodontics
• /
• v.35 no.6 s.113
• /
• pp.451-458
• /
• 2005

Cephalometric superimposition is unable to evaluate tooth movement along the occlusal plane and the errors of photographing and superimposition of the occlusogram is also inevitable. The purpose of the present study was to evaluate the rotational movements of the maxillary posterior teeth following space closure after extraction of maxillary first premolars. using 3D dental images. In 19 adult females. analysis of rotational movements of the maxillary posterior teeth was performed between the initial and final 3D dental images superimposed on the maxillary hard palate. The results showed a diversity of rotational movements of posterior teeth. The causes of various rotational movements may be different rotation of molars in each case at the beginning of treatment. individual characters of the dental arch and tooth morphology. The results of the study indicate that accurate evaluation of rotational movements of posterior teeth following space closure after extraction of premolars using 3D dental images can be obtained through the subdivision of tooth movement during the initial aligning, space closure and finishing stages.

• Journal of KIISE
• /
• v.42 no.12
• /
• pp.1535-1543
• /
• 2015

The brain-computer interface obtains a user's electroencephalogram as a replacement communication unit for the disabled such that the user is able to control machines by simply thinking instead of using hands or feet. In this paper, we propose a feature extraction method based on a non-selected filter by SBCSP to classify motor imagery EEG. First, we divide frequencies (4~40 Hz) into 4-Hz units and apply CSP to each Unit. Second, we obtain the FLD score vector by combining FLD results. Finally, the FLD score vector is projected onto the optimal plane for classification using PCA. We use BCI Competition III dataset IVa, and Extracted features are used as input for LS-SVM. The classification accuracy of the proposed method was evaluated using $10{\times}10$ fold cross-validation. For subjects 'aa', 'al', 'av', 'aw', and 'ay', results were $85.29{\pm}0.93%$, $95.43{\pm}0.57%$, $72.57{\pm}2.37%$, $91.82{\pm}1.38%$, and $93.50{\pm}0.69%$, respectively.

• The korean journal of orthodontics
• /
• v.34 no.1 s.102
• /
• pp.1-11
• /
• 2004

Predicting the arch length discrepancy by simply comparing the available arch perimeter with tooth materials is merely a 2-dimensional analysis of the teeth movement. However, the real teeth movement takes place 3-dimensionally and is affected by various factors such as, the arch fen the curve of Spee and the axis of the incisors. The purpose of this study is to clarify the relationship between the decrease in the arch perimeter and the horizontal positional change of the incisors after extraction of the 1st bicuspids, for more analytic evaluation of the arch length discrepancy at pre-treatment model analysis stage. In addition to that to evaluate the effect of the curve of Spee, teeth axis to the basal plane, and the incisional crowding to the treatment outcome. All patients were treated at the department of orthodontics, dental hospital, Yonsei university. Inclusion criteria for patients selection were as follows. $\cdot$ Angle classification I malocclusion with bialveolar protrusion $\cdot$ Extraction of 4 1st bicuspids $\cdot$ No tooth anomaly or prosthesis $\cdot$ No abnormal attrition $\cdot$ No ectopically erupted teeth $\cdot$ Angle classification I canine and molar relationship $\cdot$ Less than 3mm of crowding Model analysis of the above patients was performed and the following conclusions were obtained. 1. When the intercanine distance was maintained, the available space for the distal movement of the mandibular incisors after the extraction of the 4 1st bicuspids was larger than the space provided by the extraction of the 4 1st bicuspids. However the difference was less than 1mm. The more tapered the anterior arch form, the larger the difference. 2. Compared to the situation in which the intercanine distance was maintained, when the intercanine distance was expanded to meet the width of the Posterior teeth, the incisors could move about 3mm more distally. 3. The positional difference of the incisal tip was insignificant whether the central incisors were moved by tipping or bodily movement. 4. When the anterior crowding was solved without changing the intercanine distance, the larger the anterior arch length was, the more the anterior movement of the incisors. 5. When the curve of Spee was levelled, the increase in the arch perimeter was less than half of the deepest curve of Spee.

• The korean journal of orthodontics
• /
• v.35 no.3 s.110
• /
• pp.182-195
• /
• 2005

The purpose of this retrospective study was to estimate the pretreatment characteristics of growing patients with Class II malocclusion. who had been treated with maxillary second molar extractions The sample comprised of 51 subjects; 18 subjects were classified into the molar extraction group, and 33 subjects were treated without extraction and classified into the nonextraction group. Pretreatment lateral cephalograms were calculated and analyzed by independent t-test and stepwise discriminant analysis. In measurements for skeletal pattern, no anteroposterior measurements and proportions of various vertical dimensions were significantly different. and only some measurements such as $AB-MP(^{\circ)$, Na-We(mm), AVD (mm) were significantly different between the two treatment groups (p<0.05). In measurements for dentoalveolar pattern. some measurements, which were related to the position and angulation of the upper and lower permanent first molars, and the angulation of the upper third molars, were significantly different between the two treatment groups In particular, the maxillary second molar extraction group exhibited more mesial angulation of maxillary first molar to the occlusal plane.

• Journal of KIISE:Software and Applications
• /
• v.31 no.1
• /
• pp.54-60
• /
• 2004

Face recognition is one of the problems to be solved by appearance based matching technique. However, the appearance of face image is very sensitive to variation in illumination. One of the easiest ways for better performance is to collect more training samples acquired under variable lightings but it is not practical in real world. ]:n object recognition, it is desirable to focus on feature extraction or normalization technique rather than focus on classifier. This paper presents a simple approach to normalization of faces subject to directional illumination. This is one of the significant issues that cause error in the face recognition process. The proposed method, ICR(illumination Compensation based on Multiple Linear Regression), is to find the plane that best fits the intensity distribution of the face image using the multiple linear regression, then use this plane to normalize the face image. The advantages of our method are simple and practical. The planar approximation of a face image is mathematically defined by the simple linear model. We provide experimental results to demonstrate the performance of the proposed ICR method on public face databases and our database. The experimental results show a significant improvement of the recognition accuracy.

• The korean journal of orthodontics
• /
• v.25 no.3 s.50
• /
• pp.247-261
• /
• 1995

The purpose of this study was to quantitate differences in the nature of the correction of Angle's Class II div 1 malocclusion dependent on the patient's age at the time of treatment. The sample consisted of 27 female patients in the adolescent group with a mean initial records age of 11.8 years and 25 female patients in the adult group with a mean starting age of 21.1 yrs. Lateral cephalometric head films were taken before and after orthodontic treatment with four bicuspid extraction. The results were obtained as follows. 1. None of maxillary skeletal parameters exhibited a significantly different in treatment change between adolescents and adults. But, in mandibular skeletal measurements, there were significant differences between two groups. (P<0.05) 2. Measures of vertical dimension in the adults remained unchanged during treatment, reflecting the effective absence of growth. 3. The steepness of occlusal plane in the adults changed significantly.(P<0.05) In contrast, the adolescents displayed stability of the occlusal plane. 4. According to the Johnston analysis, there was a significant difference in the total molar correction between two groups.(P<0.05) 5. According to the Johnston analysis, differential mandibular growth in the adolescents contrubuted $63\%$ of the total molar correction, with orthodontic tooth movement accounting for the remaining $37\%$. In the adults, dental movement comprised $99\%$ of the correction.

• Journal of Dental Rehabilitation and Applied Science
• /
• v.29 no.3
• /
• pp.249-258
• /
• 2013

The purpose of this study was to investigate how image magnification in dental panoramic radiography is influenced by object position. Five metal balls (4 mm in diameter, 2 for the anterior and 3 for the posterior region on the right side) were placed above alveolar crest of dry skull considering extraction socket and dental arch. Dry skull was radiographed using OP-100D (Instrumentarium Imaging Co., Tuusula, Finland) at proper and displaced position along the sagittal and transverse plane at 3 mm, 6 mm, 9 mm, 12 mm and 15 mm using special mount which can control precise movement. Images were stored in DICOM files and were measured by ruler equipped within INFINITT PACS software (Infinitt Co., Ltd., Seoul, Korea). The mean horizontal magnification was 1.224-1.439 and mean vertical magnification was 1.286 - 1.345 at proper position. Vertical magnification resulted in less variation (1.245-1.418) than horizontal magnification (0.798-6.297) according to the sagittal and transverse displacements. Head positioning is important for linear measurement on panoramic radiography and inclusion of standard object (for instance, metal ball) is helpful to anticipate exact magnification of panoramic radiographs at various location.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_3
• /
• pp.1425-1434
• /
• 2021

Continuous and periodic data acquisition must be preceded to maintain and manage the river facilities effectively. Adapting the existing general facilities methods, which include river surveying methods such as terrestrial laser scanners, total stations, and Global Navigation Satellite System (GNSS), has limitation in terms of its costs, manpower, and times to acquire spatial information since the river facilities are distributed across the wide and long area. On the other hand, the Mobile Mapping System (MMS) has comparative advantage in acquiring the data of river facilities since it constructs three-dimensional spatial information while moving. By using the MMS, 184,646,009 points could be attained for Anyang stream with a length of 4 kilometers only in 20 minutes. Levee points were divided at intervals of 10 meters so that about 378 levee cross sections were generated. In addition, the waterside maximum and average slope could be automatically calculated by separating slope plane form levee point cloud, and the accuracy of RMSE was confirmed by comparing with manually calculated slope. The reference slope was calculated manually by plotting point cloud of levee slope plane and selecting two points that use location information when calculating the slope. Also, as a result of comparing the water side slope with slope standard in basic river plan for Anyang stream, it is confirmed that inspecting the river facilities with the MMS point cloud is highly recommended than the existing river survey.