• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.8
• /
• pp.1827-1835
• /
• 2010

In this paper, facial feature areas in user picture are created by facial feature points extracted by ASM(Active Shape Model). In a existing virtual make-up application, users manually select a few features that are exactly. Users are uncomfortable with this method. We propose a virtual makeup application using ASM that does not require user input. In order to express a natural makeup, the modified alpha blendings for each cosmetic are used to blend skin color with cosmetic color. The Virtual makeup application was implemented to apply Foundation, Blush, Lip Stick, Lip Liner, Eye Pencil, Eye Liner and Eye Shadow.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.2
• /
• pp.11-23
• /
• 2011

In this paper, an accurate and fully automatic video object segmentation method is proposed for video conferencing systems in which the real-time performance is required. The proposed method consists of two steps: 1) accurate object extraction on the initial frame, 2) real-time object extraction from the next frame using the result of the first step. Object extraction on the initial frame starts with generating a cumulative edge map obtained from frame differences in the beginning. This is because we can estimate the initial shape of the foreground object from the cumulative motion. This estimated shape is used to assign the seeds for both object and background, which are needed for Graph-Cut segmentation. Once the foreground object is extracted by Graph-Cut segmentation, real-time object extraction is conducted using the extracted object and the double edge map obtained from the difference between two successive frames. Experimental results show that the proposed method is suitable for real-time processing even in VGA resolution videos contrary to previous methods, being a useful tool for immersive video conferencing systems.

• Journal of Ocean Engineering and Technology
• /
• v.35 no.4
• /
• pp.296-304
• /
• 2021

Research on the development of marine renewable energy is actively in progress. Various studies are being conducted on the development of wave energy converters. In this study, a numerical analysis of wave-energy extraction performance was performed according to the body shape and scale of the sloped oscillating water column (OWC) wave energy converter (WEC), which can be connected with the breakwater. The sloped OWC WEC was modeled in the time domain using a two-dimensional fully nonlinear numerical wave tank. The nonlinear free surface condition in the chamber was derived to represent the pneumatic pressure owing to the wave column motion and viscous energy loss at the chamber entrance. The free surface elevations in the sloped chamber were calculated at various incident wave periods. For verification, the results were compared with the 1:20 scaled model test. The maximum wave energy extraction was estimated with a pneumatic damping coefficient. To calculate the energy extraction of the actual size WEC, OWC models approximately 20 times larger than the scale model were calculated, and the viscous damping coefficient according to each size was predicted and applied. It was verified that the energy, owing to the airflow in the chamber, increased as the incident wave period increased, and the maximum efficiency of energy extraction was approximately 40% of the incident wave energy. Under the given incident wave conditions, the maximum extractable wave power at a chamber length of 5 m and a skirt draft of 2 m was approximately 4.59 kW/m.

• Journal of Korea Multimedia Society
• /
• v.20 no.11
• /
• pp.1720-1728
• /
• 2017

Active shape model is widely used in the field of image processing especially on arbitrary meaningful shape extraction from single gray level image. Cootes et. al. showed efficient detection of variable shape from image by using covariance and mean shape from learning. There are two stages of learning and testing. Hahn applied enhanced shape alignment method rather than using Cootes's rotation and scale scheme. Hahn did not modified the profile itself. In this paper, the method using directional one dimensional profile is proposed to enhance Cootes's one dimensional profile and the shape alignment algorithm of Hahn is combined. The performance of the proposed method was superior to Cootes's and Hahn's. Average landmark estimation error for each image was 27.72 pixels and 39.46 for Cootes's and 33.73 for Hahn's each.

• The korean journal of orthodontics
• /
• v.41 no.3
• /
• pp.174-183
• /
• 2011

Objective: Orthodontically induced root resorption (OIRR) involves partial loss of cementum and dentin of teeth caused by routine orthodontic treatment. It decreases root length and influences the function of affected teeth. In this study, the treatment and patient factors causing apical root resorption in Koreans were determined. The observed factors were extraction, gender, age, displacement of root apex, total treatment period, total teeth length, and shape of the root. Methods: The records of 137 patients treated with full, fixed edgewise appliances were obtained from the Department of Orthodontics, Dankook University Dental Hospital, from November 2007 to December 2008. Periapical radiographs of the maxillary central incisors and cephalometric radiographs of each patient were used to assess apical root resorption and type of tooth movement. Results: The mean amount of resorption was $1.62{\pm}1.58mm$. The amount of resorption in the extraction and non-extraction groups was $2.10{\pm}1.64mm$ and $1.18{\pm}1.39mm$, respectively. The amount of root resorption increased with the total tooth length. Severe root resorption (> 4 mm) was related to abnormal root shape (blunt, pointed, or eroded). Conclusions: The variables significantly related to OIRR were extraction, initial tooth length, and root shape.

• The KIPS Transactions:PartB
• /
• v.14B no.2
• /
• pp.71-80
• /
• 2007

In this paper, We propose face type classification, tongue region extraction and tongue color analysis method for Oriental medicine diagnosis system to supply web based medical treatment information. This presents to construct system that takes super aging society and uses ocular inspection and longue diagnosis in web-based to embody this by an IT Technology as generalization and popularization of medical benefit are social requirement and supplies medical treatment information. Place that reflect living body signal of human body ordinarily and appear becomes iris or tongue, five sensory organs etc. This paper proposes classification of face type, extraction of five sensory organs for observing a person's shape and color among diseases diagnosis based on home health care that propose to develop and region extraction and color analysis etc, of tongue which intensively represents the bio-signals of human-beings. Finally, the effectiveness of this paper is verified by several experiments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.4
• /
• pp.598-603
• /
• 2003

This paper presents a sub-band feature extraction approach in which the feature extraction method in the individual frequency sub-bands is determined in terms of speech recognition accuracy. As in the multi-band paradigm, features are extracted independently in frequency sub-regions of the speech signal. Since the spectral shape is well structured in the low frequency region, the all pole model is effective for feature extraction. But, in the high frequency region, the nonparametric transform, discrete cosine transform is effective for the extraction of cepstrum. Using the sub-band specific feature extraction method, the linguistic information in the individual frequency sub-bands can be extracted effectively for automatic speech recognition. The validity of the proposed method is shown by comparing the results of speech recognition experiments for our method with those obtained using a full-band feature extraction method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.4
• /
• pp.512-517
• /
• 2011

In this paper, we propose an Active Shape Model (ASM) and Lucas-Kanade (LK) optical flow-based feature extraction and analysis method for analyzing the emotional features from facial images. Considering the facial emotion feature regions are described by Facial Action Coding System, we construct the feature-related shape models based on the combination of landmarks and extract the LK optical flow vectors at each landmarks based on the centre pixels of motion vector window. The facial emotion features are modelled by the combination of the optical flow vectors and the emotional states of facial image can be estimated by the probabilistic estimation technique, such as Bayesian classifier. Also, we extract the optimal emotional features that are considered the high correlation between feature points and emotional states by using common spatial pattern (CSP) analysis in order to improvise the operational efficiency and accuracy of emotional feature extraction process.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.1
• /
• pp.11-18
• /
• 2001

In this paper, we proposed the image compression algorithm using triangular feature based GHA. In feature extraction, the input images are divided into eight areas of triangular shape, that has positional information for face image compression. The proposed algorithm reduces blocking effects in image reconstruction and contains informations of face feature and shapes of face as input images are divided into eight. We used triangular feature extraction for positional information and GHA for shape information of face images. Simulation results show that the proposed algorithm has a better performance than the block based K-means and non-parsed image based GHA in PSNR at the same bpp.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.4
• /
• pp.17-22
• /
• 2002

This paper used an active contour model which was based on level set algorithms and bidirectional curve evolution theory in order to track the shape of the heart acting continuously. Most active contour models would be failed in boundary extraction because of their unstable movement in the edge gap locations. In this paper, we suggest a new active contour model using only image intensity value and additional constraint needed for stable extraction. Our model was successfully run on either shape extraction or object tracking without any position constraints of initial curve. Also demonstrated stable movements and showed good results at weak or missing boundary locations.