• Imaging Science in Dentistry
• /
• v.42 no.3
• /
• pp.147-154
• /
• 2012

Purpose: This study was performed to evaluate the incidence and degree of external apical root resorption of maxillary incisors after orthodontic treatment and to evaluate particular associated factors related to external apical root resorption. Materials and Methods: The records and maxillary incisor periapical radiographs of 181 patients were investigated. Crown and root lengths were measured and compared on the pre- and post-treatment periapical radiographs. Crown length was measured from the center of the incisal edge to the midpoint of the cemento-enamel junction (CEJ). Root length was measured from the CEJ midpoint to the root apex. A correction factor for the enlargement difference was used to calculate root resorption. Results: The periapical radiographs of 564 teeth showed that the average root resorption was $1.39{\pm}1.27$ ($8.24{\pm}7.22$%) and $1.69{\pm}1.14$ mm ($10.16{\pm}6.78%$) for the maxillary central and lateral incisors, respectively. The results showed that the dilacerated or pointed roots, maxillary premolar extraction cases, and treatment duration were highly significant factors for root resorption (p<0.001). Allergic condition was a significant factor at p<0.01. Age at the start of treatment, large overjet, and history of facial trauma were also factors significantly associated with root resorption (p<0.05). There was no statistically significant difference in root resorption among the factors of gender, overbite, tongue-thrusting habit, types of malocclusion, and types of bracket. Conclusion: These results suggested that orthodontic treatment should be carefully performed in pre-treatment extraction patients who have pointed or dilacerated roots and need long treatment duration.

• The Journal of Korean Institute of Information Technology
• /
• v.16 no.11
• /
• pp.105-113
• /
• 2018

In this paper, we proposed a method for effective classification of eye, nose, and mouth of human face. Most recent image classification uses Convolutional Neural Network(CNN). However, the features extracted by CNN are not sufficient and the classification effect is not too high. We proposed a new algorithm to improve the classification effect. The proposed method can be roughly divided into three parts. First, the Haar feature extraction algorithm is used to construct the eye, nose, and mouth dataset of face. The second, the model extracts CNN features of image using AlexNet. Finally, Haar-CNN features are extracted by performing convolution after Haar feature extraction. After that, CNN features and Haar-CNN features are fused and classify images using softmax. Recognition rate using mixed features could be increased about 4% than CNN feature. Experiments have demonstrated the performance of the proposed algorithm.

• Journal of Korea Multimedia Society
• /
• v.15 no.1
• /
• pp.63-70
• /
• 2012

In this paper an extension to an original active shape model(ASM) for facial feature extraction is presented. The original ASM suffers from poor shape alignment by aligning the shape model to a new instant of the object in a given image using a simple similarity transformation. It exploits only informations such as scale, rotation and shift in horizontal and vertical directions, which does not cope effectively with the complex pose variation. To solve the problem, new shape alignment with 6 degrees of freedom is derived, which corresponds to an affine transformation. Another extension is to speed up the calculation of the Mahalanobis distance for 2-D profiles by trimming the profile covariance matrices. Extensive experiment is conducted with several images of varying poses to check the performance of the proposed method to segment the human faces.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.537-540
• /
• 2005

본 논문에서는 사람의 감정, 건강상태, 정신상태등 다양한 정보를 포함하고 있는 웃음, 슬픔, 졸림, 놀람, 윙크, 무표정 등의 표정을 인식하기 위한 표정의 특징이 되는 얼굴의 국부적 요소인 눈과 입을 검출하여 표정의 특징을 추출한다. 표정 특징의 추출을 위한 전체적인 알고리즘 과정으로는 입력영상으로부터 칼라 정보를 이용하여 얼굴 영역을 검출하여 얼굴에서 특징점의 위치 정보를 이용하여 국부적 요소인 특징점 눈과 입을 추출한다. 이러한 특징점 추출 과정에서는 에지, 이진화, 모폴로지, 레이블링 등의 전처리 알고리즘을 적용한다. 레이블 영역의 크기를 이용하여 얼굴에서 눈, 눈썹, 코, 입 등의 1차 특징점을 추출하고 누적 히스토그램 값과 구조적인 위치 관계를 이용하여 2차 특징점 추출 과정을 거쳐 정확한 눈과 입을 추출한다. 표정 변화에 대한 표정의 특징을 정량적으로 측정하기 위해 추출된 특징점 눈과 입의 눈과 입의 크기와 면적, 미간 사이의 거리 그리고 눈에서 입까지의 거리 등 기하학적 정보를 이용하여 6가지 표정에 대한 표정의 특징을 추출한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.631-653
• /
• 2020

Sign language is a natural, visually oriented and non-verbal communication channel between people that facilitates communication through facial/bodily expressions, postures and a set of gestures. It is basically used for communication with people who are deaf or hard of hearing. In order to understand such communication quickly and accurately, the design of a successful sign language translation system is considered in this paper. The proposed system includes object detection and classification stages. Firstly, Single Shot Multi Box Detection (SSD) architecture is utilized for hand detection, then a deep learning structure based on the Inception v3 plus Support Vector Machine (SVM) that combines feature extraction and classification stages is proposed to constructively translate the detected hand gestures. A sign language fingerspelling dataset is used for the design of the proposed model. The obtained results and comparative analysis demonstrate the efficiency of using the proposed hybrid structure in sign language translation.

• The Journal of the Korean dental association
• /
• v.54 no.8
• /
• pp.592-603
• /
• 2016

Pathologic tooth migration (PTM) caused by periodontal disease is a relatively common disease with a prevalance rate of 30~55%. It is one of the reasons for periodontal treatment of patients. PTM occurs when various factors related to the position of the tooth are altered and clinical features of PTM include facial flaring, diastema, proximal tilting, rotation, and extrusion of teeth. The purpose of this study was to assess the treatment of teeth of hopeless prognosis through the practice of modified intentional replantation on pathologic migrated tooth. This study presents cases using modified intentional replantation for the treatment of pathologic tooth migration caused by severe periodontitis. Modified intentional replantation is a technique that prepares extraction socket by using an implant drill. Based on 3 cases performed with modified intentional replantation, an improvement of clinical periodontal indicators such as probing pocket depth, bleeding on probing, tooth mobility, and pathologic teeth migration was observed after surgery. Also, the patients were satisfied with the functional and esthetic improvement.

• The korean journal of orthodontics
• /
• v.31 no.6 s.89
• /
• pp.611-618
• /
• 2001

This is a case report of a 12.5-year-old girl who presented with moderate to severe anterior dental crowding and rotations. Treatment involved no extraction, but expansion of both the maxillary and the mandibular arches. Maxillary expansion was assisted by rapid palatal expansion despite the fact that this patient did not present with posterior crossbite. Crowding and rotations in both arches were corrected and good occlusal function and improved facial esthetic were achieved, with acceptable overbite and overjet. The application of rapid maxillary expansion in cases with no posterior crossbite, which has increased in recent years, calls for re-evaluation of the diagnostic basis and indications for the use of this technique.

• The Journal of the Korean dental association
• /
• v.48 no.11
• /
• pp.819-828
• /
• 2010

Activator is a removable functional appliance used for correcting the skeletal Class II malocclusion in children with the mandibular deficiency. Berlin standard activator modified from Andresen activator has following characters; do not cover the palatal surface for tongue space, relief on lingual surface of mandibular incisors and resin capping 1/3-1/2 of crown height on mandibular incisors for preventing labioversion of mandibular incisors, L-hook between maxillary lateral incisor and canine for anterior high pull headgear, relief on mandibular posterior bite block for differential eruption of posterior teeth. Two cases presented here had a mandibular deficiency and slight maxillary protrusion. First case (an 11-year-old girl) treated with Berlin standard activator and anterior high pull headgear for 13 months followed by fixed orthodontic appliance for another 29 months. Second case (a 12-year-old boy) treated with Berlin standard activator for 6 months followed by fixed appliance for another 24 months. Treatment results showed a significant improvement in sagittal skeletal and occlusal relationship without premolar extraction. Mandibular condyles were concentric in TMJ [ossa, and masticatory muscle activities were normalized after treatment. In the retention period facial harmony and occlusal stability was maintained.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.7
• /
• pp.503-506
• /
• 2013

In this paper, we propose the face recognition method combining the ECSP preprocessing technique which is modified version of previous CS-LBP and the illumination-robust D2D-PCA feature. The performance evaluation of proposed method was carried out using various binary pattern operators and feature extraction algorithms such as well-known PCA and 2D-PCA on the Yale B database. As a results, the proposed method showed the best recognition accuracy compared to different approaches, and we confirmed that the proposed approach is robust to illumination variation.

• International Journal of Contents
• /
• v.7 no.1
• /
• pp.14-22
• /
• 2011

Temporal Sign Language Recognition (TSLR) from hand motion is an active area of gesture recognition research in facilitating efficient communication with deaf people. TSLR systems consist of two stages: a motion sensing step which extracts useful features from signers' motion and a classification process which classifies these features as a performed sign. This work focuses on two of the research problems, namely unknown time varying signal of sign languages in feature extraction stage and computing complexity and time consumption in classification stage due to a very large sign sequences database. In this paper, we propose a combination of Dynamic Time Warping (DTW) and application of the Single hidden Layer Feedforward Neural networks (SLFNs) trained by Extreme Learning Machine (ELM) to cope the limitations. DTW has several advantages over other approaches in that it can align the length of the time series data to a same prior size, while ELM is a useful technique for classifying these warped features. Our experiment demonstrates the efficiency of the proposed method with the recognition accuracy up to 98.67%. The proposed approach can be generalized to more detailed measurements so as to recognize hand gestures, body motion and facial expression.