• Journal of KIISE:Software and Applications
• /
• v.28 no.12
• /
• pp.947-954
• /
• 2001

In this paper, we propose a method for the recognition of various head gestures with automata technique applied to the sequence of facial pose states. Facial regions as detected by using the optimum facial color of I-component in YIQ model and the difference of images adaptively selected. And eye regions are extracted by using Sobel operator, projection, and the geometric location of eyes Hierarchical feature analysis is used to classify facial states, and automata technique is applied to the sequence of facial pose states to recognize 13 gestures: Gaze Upward, Downward, Left ward, Rightward, Forward, Backward Left Wink Right Wink Left Double Wink, Left Double Wink , Right Double Wink Yes, and No As an experimental result with total 1,488 frames acquired from 8 persons, it shows 99.3% extraction rate for facial regions, 95.3% extraction rate for eye regions 94.1% recognition rate for facial states and finally 99.3% recognition rate for head gestures. .

• The korean journal of orthodontics
• /
• v.49 no.6
• /
• pp.393-403
• /
• 2019

Objective: Sliding mechanics using orthodontic miniscrews is widely used to stabilize the anchorage during extraction space closure. However, previous studies have reported that both posterior segment displacement and anterior segment displacement are possible, depending on the mechanical properties of the archwire. The present study aimed to investigate the effect of archwire stiffness and friction change on the displacement pattern of the maxillary posterior segment during anterior segment retraction with orthodontic miniscrews in sliding mechanics. Methods: A three-dimensional finite element model was constructed. The retraction point was set at the archwire level between the lateral incisor and canine, and the orthodontic miniscrew was located at a height of 8 mm from the archwire between the second premolar and first molar. Archwire stiffness was simulated with rectangular stainless steel wires and a rigid body was used as a control. Various friction levels were set for the surface contact model. Displacement patterns for the posterior and anterior segments were compared between the conditions. Results: Both the anterior and posterior segments exhibited backward rotation, regardless of archwire stiffness or friction. Among the conditions tested in this study, the least undesirable rotation was found with low archwire stiffness and low friction. Conclusions: Posterior segment displacement may be unavoidable but reducing the stiffness and friction of the main archwire may minimize unwanted rotations during extraction space closure.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.447-450
• /
• 2003

In this research, we propose an automatic knowledge acquisition and composite knowledge expression mechanism based on machine learning and relational database. Most of traditional approaches to develop a knowledge base and inference engine of expert systems were based on IF-THEN rules, AND-OR graph, Semantic networks, and Frame separately. However, there are some limitations such as automatic knowledge acquisition, complicate knowledge expression, expansibility of knowledge base, speed of inference, and hierarchies among rules. To overcome these limitations, many of researchers tried to develop an automatic knowledge acquisition, composite knowledge expression, and fast inference method. As a result, the adaptability of the expert systems was improved rapidly. Nonetheless, they didn't suggest a hybrid and generalized solution to support the entire process of development of expert systems. Our proposed mechanism has five advantages empirically. First, it could extract the specific domain knowledge from incomplete database based on machine learning algorithm. Second, this mechanism could reduce the number of rules efficiently according to the rule extraction mechanism used in machine learning. Third, our proposed mechanism could expand the knowledge base unlimitedly by using relational database. Fourth, the backward inference engine developed in this study, could manipulate the knowledge base stored in relational database rapidly. Therefore, the speed of inference is faster than traditional text -oriented inference mechanism. Fifth, our composite knowledge expression mechanism could reflect the traditional knowledge expression method such as IF-THEN rules, AND-OR graph, and Relationship matrix simultaneously. To validate the inference ability of our system, a real data set was adopted from a clinical diagnosis classifying the dermatology disease.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.4
• /
• pp.466-471
• /
• 2006

IAn important problem of pattern recognition is to extract or select feature set, which is included in the pre-processing stage. In order to extract feature set, Principal component analysis has been usually used and SFS(Sequential Forward Selection) and SBS(Sequential Backward Selection) have been used as a feature selection method. This paper applies genetic algorithm which is a popular method for nonlinear optimization problem to the feature selection problem. So, we call it Genetic Algorithm Feature Selection(GAFS) and this algorithm is compared to other methods in the performance aspect.

• MALSORI
• /
• no.59
• /
• pp.53-68
• /
• 2006

We report the evaluation results of the Korean speech recognition platform called ECHOS. The platform has an object-oriented and reusable architecture so that researchers can easily evaluate their own algorithms. The platform has all intrinsic modules to build a large vocabulary speech recognizer: Noise reduction, end-point detection, feature extraction, hidden Markov model (HMM)-based acoustic modeling, cross-word modeling, n-gram language modeling, n-best search, word graph generation, and Korean-specific language processing. The platform supports both lexical search trees and finite-state networks. It performs word-dependent n-best search with bigram in the forward search stage, and rescores the lattice with trigram in the backward stage. In an 8000-word continuous speech recognition task, the platform with a lexical tree increases 40% of word errors but decreases 50% of recognition time compared to the HTK platform with flat lexicon. ECHOS reduces 40% of recognition errors through incorporation of cross-word modeling. With the number of Gaussian mixtures increasing to 16, it yields word accuracy comparable to the previous lexical tree-based platform, Julius.

• Fashion & Textile Research Journal
• /
• v.25 no.1
• /
• pp.92-103
• /
• 2023

As the body shape change which occurs after middle age is the main factor affecting the fit of ready-to-wear clothes, this study was designed to classify and analyze the torso shapes of middle-aged men. This study sorted 3D body scans of 200 men aged 40-64 from the 8th Size Korea (2021) database and extracted their 47 measurement values using the Grasshopper algorithm for automatic extraction landmarks and measurements, developed by the previous research (Ryu & Song, 2022). Eight principal components (torso length, shoulder size, overall body size, abdomen prominence, back protrusion, neck inclination, upper body slope, and hip prominence) were identified and four torso shapes were classified. Shape 1 (28.5%) exhibited the shortest torso length, the narrowest shoulders, and the most protruding back. Shape 2 (21.0%) exhibited the skinniest body and the largest backward inclination of the upper body. Hence, the back appeared to be protruding, and the abdomen looked prominent. Shape 3 (25.5%) had the largest overall body size. Thus, the abdomen looked the least protruding, and it exhibited the flattest back. Shape 4 (25.0%) had the longest torso, widest shoulders, straightest neck, and the least protruding hips. This study suggested these three discriminant functions to identify a new person's torso type.

• The korean journal of orthodontics
• /
• v.42 no.6
• /
• pp.280-290
• /
• 2012

Objective: This study aimed to compare the effects of conventional and orthodontic mini-implant (OMI) anchorage on tooth movement and arch-dimension changes in the maxillary dentition in Class II division 1 (CII div.1) patients. Methods: CII div.1 patients treated with extraction of the maxillary first and mandibular second premolars and sliding mechanics were allotted to conventional anchorage group (CA, n = 12) or OMI anchorage group (OA, n = 12). Pre- and post-treatment three-dimensional virtual maxillary models were superimposed using the best-fit method. Linear, angular, and arch-dimension variables were measured with software program. Mann-Whitney U-test and Wilcoxon signed-rank test were performed for statistical analysis. Results: Compared to the CA group, the OMI group showed more backward movement of the maxillary central and lateral incisors and canine (MXCI, MXLI, MXC, respectively; 1.6 mm, p < 0.001; 0.9 mm, p < 0.05; 1.2 mm, p < 0.001); more intrusion of the MXCI and MXC (1.3 mm, 0.5 mm, all p < 0.01); less forward movement of the maxillary second premolar, first, and second molars (MXP2, MXM1, MXM2, respectively; all 1.0 mm, all p < 0.05); less contraction of the MXP2 and MXM1 (0.7 mm, p < 0.05; 0.9 mm, p < 0.001); less mesial-in rotation of the MXM1 and MXM2 ($2.6^{\circ}$, $2.5^{\circ}$, all p < 0.05); and less decrease of the inter-MXP2, MXM1, and MXM2 widths (1.8 mm, 1.5 mm, 2.0 mm, all p < 0.05). Conclusions: In treatment of CII div.1 malocclusion, OA provided better anchorage and less arch-dimension change in the maxillary posterior teeth than CA during en-masse retraction of the maxillary anterior teeth.

• The korean journal of orthodontics
• /
• v.41 no.4
• /
• pp.297-306
• /
• 2011

Nonextraction camouflage treatment in mild Class III malocclusion is achieved by backward movement of the lower dentition and forward movement of the upper dentition. Many camouflage treatment modalities have been used for distal tipping and distal movement of mandibular posterior teeth. The amount of distal movement of mandibular dentition can be improved in cases of severe crowding, even without the patient's cooperation, by using miniscrews for anchorage. However, miniscrew insertion may be unsuccessful, and it may contact the adjacent root because of the distal movement of dentition. Distal tipping of mandibular dentition can be achieved using multiloop edgewise archwires and intermaxillary elastics. However, the complexity of this wire design causes discomfort to patients. Recently, a new treatment using improved superelastic NiTi wires (ISWs) and intermaxillary elastics has been introduced. ISWs can deliver orthodontic force more effectively, and their use with molar tip-back treatment has several advantages-this approach is effective, simple, and easy to use and reduces patient discomfort. The aim of this study was to report a case of camouflage treatment using ISW with tip-back and intermaxillary elastics for distal tipping of mandibular posterior dentition and to evaluate the effectiveness of this treatment in a clinical setting.

• Korean Journal of Soil Science and Fertilizer
• /
• v.50 no.5
• /
• pp.422-433
• /
• 2017

Unmanned Aerial Vehicle (UAV) has several advantages over conventional remote sensing techniques. They can acquire high-resolution images quickly and repeatedly. And with a comparatively lower flight altitude, they can obtain good quality images even in cloudy weather. In this paper, we developed for estimating garlic growth at field scale model in major cultivation regions. We used the $NDVI_{UAV}$ that reflects the crop conditions, and seven meteorological elements for 3 major cultivation regions from 2015 to 2017. For this study, UAV imagery was taken at Taean, Changnyeong, and Hapcheon regions nine times from early February to late June during the garlic growing season. Four plant growth parameters, plant height (P.H.), leaf number (L.N.), plant diameter (P.D.), and fresh weight (F.W.) were measured for twenty plants per plot for each field campaign. The multiple linear regression models were suggested by using backward elimination and stepwise selection in the extraction of independent variables. As a result, model of cold type explain 82.1%, 65.9%, 64.5%, and 61.7% of the P.H., F.W., L.N., P.D. with a root mean square error (RMSE) of 7.98 cm, 5.91 g, 1.05, and 3.43 cm. Especially, model of warm type explain 92.9%, 88.6%, 62.8%, 54.6% of the P.H., P.D., L.N., F.W. with a root mean square error (RMSE) of 16.41 cm, 9.08 cm, 1.12, 19.51 g. The spatial distribution map of garlic growth was in strong agreement with the field measurements in terms of field variation and relative numerical values when $NDVI_{UAV}$ was applied to multiple linear regression models. These results will also be useful for determining the UAV multi-spectral imagery necessary to estimate growth parameters of garlic.