• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.18 no.36
• /
• pp.41-47
• /
• 1995

This study present a systematic and more economical anthropometric technique to acquire 3-D anthropometric data by the use of moire interferometry, image processing and computer vision techniques. An experiment was performed to measure in anthopometric variables (head and face), such as head length, head breath, length of ear to top of head, contained face areas, etc. We took fourty-five subjects with wide range of ages(18 years to 33 years old). The face area was calculated based on contour information. The results were then compared with plaster bandage methods. It turned out that the proposed method had 90.85% consistancy.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.10 no.1
• /
• pp.67-75
• /
• 2002

A study to investigate the influence of combustion chamber shape, especially piston top face configuration, on the combustion stability is presented with CFD analysis and single cylinder GDI engine test. Initial configuration of the piston bowl was designed with CFD analysis and further parametric studies of the design factors on the piston top face were carried out through the single cylinder GDI engine test. It was found that both the geometry of piston top face and the compression ratio have great influences on the combustion stability. Of interest is that the design factors of the GDI piston to prevent mixture diffusion out of the piston bowl have important roles for the stable combustion at the stratified mixture condition. Also the relationship between spray impingement and flow pattern in a GDI piston bowl should be considered to design an optimal bowl configuration for stable stratified combustion.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.4
• /
• pp.87-96
• /
• 1996

On face milling operation a newly optimal tool, which can minimize the resultant cutting forces resulted from the cutting force model, was designed and manufactrued. Cutting experiments using the new and conventional tools were carried out and the cutting forces resulted from those tools were analyzed in time and frequency domains. The performance of the optimized cutter was tested through the dynamic cutting forces resulted form the newly designed tool are much reduced in comparision with those from the conventional tool. By reducing the dynamic cutting force fluctuations, machine tool vibrations can be reduced, and stable cutting operation can be carried out.

• Proceedings of the IEEK Conference
• /
• 2001.06d
• /
• pp.231-234
• /
• 2001

This paper proposes a face recognition technique that effectively combines elastic graph matching (EGM) and Fisherface algorithm. EGM as one of dynamic lint architecture uses not only face-shape but also the gray information of image, and Fisherface algorithm as a class specific method is robust about variations such as lighting direction and facial expression. In the proposed face recognition adopting the above two methods, the linear projection per node of an image graph reduces dimensionality of labeled graph vector and provides a feature space to be used effectively for the classification. In comparison with a conventional method, the proposed approach could obtain satisfactory results in the perspectives of recognition rates and speeds. Especially, we could get maximum recognition rate of 99.3% by leaving-one-out method for the experiments with the Yale Face Databases.

• Journal of Korea Multimedia Society
• /
• v.18 no.2
• /
• pp.244-252
• /
• 2015

This paper describes the design and implementation of a System-on-a-Chip (SoC) for face recognition to use in wearable/mobile products. The design flow starts from the system specification to implementation process on silicon. The entire process is carried out using a FPGA-based prototyping platform environment for design and verification of the target SoC. To ensure that the implemented face recognition SoC satisfies the required performances metrics, time analysis and recognition tests were performed. The motivation behind the work is a single chip implementation of face recognition system for target applications.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.714-718
• /
• 2009

3D reconstruction of a human face from an image sequence remains an important problem in computer vision. We propose a method, based on a factorization algorithm, that reconstructs a 3D face model from short image sequences exhibiting rotational motion. Factorization algorithms can recover structure and motion simultaneously from one image sequence, but they usually require that all feature points be well tracked. Under rotational motion, however, feature tracking often fails due to occlusion and frame out of features. Additionally, the paucity of images may make feature tracking more difficult or decrease reconstruction accuracy. The proposed 3D reconstruction approach can handle short image sequences exhibiting rotational motion wherein feature points are likely to be missing. We implement the proposal as a reconstruction method; it employs image sequence division and a feature tracking method that uses Active Appearance Models to avoid the failure of feature tracking. Experiments conducted on an image sequence of a human face demonstrate the effectiveness of the proposed method.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2013.05a
• /
• pp.160-161
• /
• 2013

Progress measurement is one of key tasks for cost and schedule management in construction management. However, there has been shortage of effort to implement for automated progress measurement. This paper proposes to use a face recognition (FR) technology for automated progress measurement and management in construction sites. The FR technology can acquire detailed progress data that includes the in and out information of labors by location. The expected effectiveness of the proposed system is to provide accurate labor information for progress measurement by utilizing automated data acquisition technology (DAT) with high-speed reading face. In addition, it could be applied to real-time safety and quality management by using the camera images.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.783-788
• /
• 2003

In this paper, we present a new approach to detect and recognize human face in the image from vision camera equipped on the mobile robot platform. Due to the mobility of camera platform, obtained facial image is small and pose-various. For this condition, new algorithm should cope with these constraints and can detect and recognize face in nearly real time. In detection step, ‘coarse to fine’ detection strategy is used. Firstly, region boundary including face is roughly located by dual ellipse templates of facial color and on this region, the locations of three main facial features- two eyes and mouth-are estimated. For this, simplified facial feature maps using characteristic chrominance are made out and candidate pixels are segmented as eye or mouth pixels group. These candidate facial features are verified whether the length and orientation of feature pairs are suitable for face geometry. In recognition step, pseudo-convex hull area of gray face image is defined which area includes feature triangle connecting two eyes and mouth. And random lattice line set are composed and laid on this convex hull area, and then 2D appearance of this area is represented. From these procedures, facial information of detected face is obtained and face DB images are similarly processed for each person class. Based on facial information of these areas, distance measure of match of lattice lines is calculated and face image is recognized using this measure as a classifier. This proposed detection and recognition algorithms overcome the constraints of previous approach [15], make real-time face detection and recognition possible, and guarantee the correct recognition irregardless of some pose variation of face. The usefulness at mobile robot application is demonstrated.

• Journal of IKEEE
• /
• v.6 no.2 s.11
• /
• pp.152-160
• /
• 2002

This paper is the realization of the face recognition system for multimedia application. This system is focused on the design concerning the improvement of recognition rate and the reduction of processing time for face recognition. The non-modificated application of typical RGB color system enables the reduction of time required for color system transform. The neural network and the application of algorithm using face characteristic improves the recognition rate. After mosaicking an image, a face-color block has been selected through the color analysis of mosaic block. The characteristic of the face removes the mis-checked face-color candidate block. Finally, from the face color block, four special values are obtained. These values are processed to the neural network using the back propagation algorithm. The output values are the touchstone to decide the genuineness of face field. The realized system showed 90% of face recognition rate with less than 0.1 second of processing time. This result can be understood as sufficient processing time and recognition rate to find out the face block for multimedia application in dynamic image.

• The korean journal of orthodontics
• /
• v.24 no.2
• /
• pp.395-403
• /
• 1994

To find out the antero-posterior morphology of the upper face in Angle's class III malocclusion patients, 90 patients, adults in Heilman's Dental age, were used as samples and following results were obtained after the relative comparision of antero-posterior relationship of upper facial structures between Angle's class I malocclusion patients and Angle's class III malocclusion patients and of antero-posterior size of upper facial structures to horizontal and vertical structures in each patients. 1. After comparison of the distance from PMV line to anterior margin of maxillary sinus and cheek, which determines the antero-posterior position of the upper face, upper face in Angle's class III patients are underdeveloped relative to Angle's class I patients. The distance between orbitale and anterior margin of maxillary sinus were greater in Angle's class I patients, whic implies thart the upper face in Angle's class III are depressed. 2. Antero-posterior dimension of anterior cranial base from PMV line and vertical dimension of upper face are statistically insignificant between two groups. After comparing antero-posterior position of upper face to anterior cranial base, the upper face in Angle's class Et patients are depressed antero-posteriorly in relation to anterior cranial base. Following the comparision of antero-posterior position of upper face in relation to vertical dimension of upper face, the upper face in Angle's class III patients seem to be narrow antero-posteriorly