• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.6
• /
• pp.1129-1135
• /
• 2007

Human face detection technique plays an important role in computer vision area. It has lots of applications such as face recognition, video surveillance, human computer interface, face image database management, and querying image databases. In this paper, a fast face detection approach using Principal Component Analysis (PCA) and Support Vector Machines (SVM) is proposed based on the previous study on face detection technique. In the proposed detection system, firstly it filter the face potential area using statistical feature which is generated by analyzing the local histogram distribution the detection process is speeded up by eliminating most of the non-face area in this step. In the next step, PCA feature vectors are generated, and then detect whether there are faces present in the test image using SVM classifier. Finally, store the detection results and output the results on the test image. The test images in this paper are from CMU face database. The face and non-face samples are selected from the MIT data set. The experimental results indicate the proposed method has good performance for face detection.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.153-156
• /
• 2007

In this paper, we propose a fast face detection approach using PCA and SVM. In our detection system, first we filter the face potential area using statistical feature which is generated by analyzing local histogram distribution. And then, we use SVM classifier to detect whether there are faces present in the test image. Support Vector Machine (SVM) has great performance in classification task. PCA is used for dimension reduction of sample data. After PCA transform, the feature vectors, which are used for training SVM classifier, are generated. Our tests in this paper are based on CMU face database.

• Tunnel and Underground Space
• /
• v.14 no.6 s.53
• /
• pp.391-398
• /
• 2004

An algebraic algorithm for predicting the joint trace distribution on the cut-face of rock slope based on the orientations and the locations of joints investigated in the borehole has been developed. Joint trace prediction is manipulated by utilizing the three dimensional plane equations of both joint planes and projection face, and the extent of trace within the projection area is calculated by considering the persistence of each joint plane. Joint trace prediction method is efficiently applied for analyzing the stability and the adequacy of support design of Gimhae Naesam cut-slope, which is structurally unstable due to slumping. Structural characteristics of rock mass is investigated by performing DOM drilling and the potential rock mass sliding inside slope face is analyzed by examining the orientations of joint planes which can induce the slope failure. Also, the efficiency of anchor support design is evaluated by considering the joint trace distribution on the anchor installation area and its sliding potential.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.1
• /
• pp.7-16
• /
• 2010

Face recognition of face images is an active subject in the area of computer pattern recognition, which has a wide range of potential. Automatic extraction of face image of the feature points is an important step during automatic face recognition. Whether correctly extract the facial feature has a direct influence to the face recognition. In this paper, a new method of facial feature extraction based on Discrete Wavelet Transform is proposed. Firstly, get the face image by using PC Camera. Secondly, decompose the face image using discrete wavelet transform. Finally, we use the horizontal direction, vertical direction projection method to extract the features of human face. According to the results of the features of human face, we can achieve face recognition. The result show that this method could extract feature points of human face quickly and accurately. This system not only can detect the face feature points with great accuracy, but also more robust than the tradition method to locate facial feature image.

• Proceedings of the SCSK Conference
• /
• 2003.09a
• /
• pp.686-697
• /
• 2003

A new colloidal silver (Ag) system is present in which a fine colloidal Ag is in situ deposited onto functionalized porous poly (ethylene glycol dimethacrylate) (poly (EGDMA)) microspheres. The effectiveness of Ag deposition was investigated considering the surface characteristics of poly (EGDMA) microspheres. The result reported in this study illustrates that the control of surface area and surface functionality (in this study, a hydroxyl group) of poly (EGDMA) microspheres is an important factor that determines practically the degree of deposition of colloidal Ag. The x-ray analysis showed that Ag nanoparticles were dispersed evenly inner and outer surfaces and had a face center cubic (fee) phase. In the preservative efficacy test, the Ag-containing poly (EGDMA) microspheres had a powerful anti-bacterial activity, showing a high potential for a new preservative in cosmetic industry.

• Journal of Distribution Science
• /
• v.4 no.1
• /
• pp.161-173
• /
• 2006

The most important two decision-makings which a retail store owner face require which place of the store should geographically be established and which stock should be properly placed on the shelves. The problem of geographic positioning is the decision-making for the store's positioning and stock arrangement within the retail store is the decision-making for the placement store. In order to determine the positioning, the expected area should be analyzed so that the analysis of commercial area can usually be implemented in accordance with retail marketing strategy and therefore the sized of the potential market for example each distric's clientele, competition and, a municipal community's regulations, could be evaluated. But I contend that with only the size of potential market does not give an adequate answer to the problem of a store's positioning. Through the estimation of commercial are in combination with feng-shui, the theory of divination based on topography, the store's position could be selected, taking a positive energy, Gi. This thesis is the starting point of these trials. In the long run, the actual analysis of the study should be continued in a more scientific, systematic, statistical way.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.11
• /
• pp.6797-6802
• /
• 2013

Background: Prevalence of tobacco use is higher in the rural than urban areas of India. Unlike tobacco cessation clinics located in urban areas, community-based smoking cessation intervention has the potential to reach a wider section of the community to assist in smoking cessation in the rural setting. The present study aimed to assess the effectiveness of a cessation intervention in rural Kerala state, India. Materials and Methods: Current daily smoking resident males in the age group 18-60 years from four community development blocks in rural Kerala were randomly allocated to intervention and control groups. The intervention group received multiple approaches in which priority was given to face-to-face interviews and telephone counselling. Initially educational materials on tobacco hazards were distributed. Further, four rounds of counselling sessions were conducted which included a group counselling with a medical camp as well as individual counselling by trained medical social workers. The control group received general awareness training on tobacco hazards along with an anti-tobacco leaflet. Self-reported smoking status was assessed after 6 and 12 months. Factors associated with tobacco cessation were estimated using binomial regression method. Results: Overall prevalence of smoking abstinence was 14.7% in the intervention and 6.8% in the control group (Relative risk: 1.85, 95% CI: 1.05, 3.25). A total of 41.3% subjects in the intervention area and 13.6% in the control area had reduced smoking by 50% or more at the end of 12 months. Lower number of cigarettes/ bidi used, low nicotine dependence and consultation with a doctor for a medical ailment were the statistically significant predictors for smoking cessation. Conclusions: Rigorous approaches for smoking cessation programmes can enhance quit rates in smoking in rural areas of India.

• Archives of Plastic Surgery
• /
• v.44 no.4
• /
• pp.261-265
• /
• 2017

Periauricular paresthesia may afflict patients for a significant amount of time after facelift surgery. When performing face and neck lift surgery, temple and posterior auricular flap dissection is undertaken directly over the auriculotemporal, great auricular, and lesser occipital nerve territory, leading to potential damage to the nerve. The auriculotemporal nerve remains under the thin outer superficial fascia just below the subfollicular level in the prehelical area. To prevent damage to the auriculotemporal nerve and to protect the temporal hair follicle, the dissection plane should be kept just above the thin fascia covering the auriculotemporal nerve. Around the McKinney point, the adipose tissue covering the deep fascia is apt to be elevated from the deep fascia due to its denser fascial relationship with the skin, which leaves the great auricular nerve open to exposure. In order to prevent damage to the posterior branches of the great auricular nerve, the skin flap at the posterior auricular sulcus should be elevated above the auricularis posterior muscle. Fixating the superficial muscular aponeurotic system flap deeper and higher to the tympano-parotid fascia is recommended in order to avoid compromising the lobular branch of the great auricular nerve. The lesser occipital nerve (C2, C3) travels superficially at a proximal and variable level that makes it vulnerable to compromise in the mastoid dissection. Leaving the adipose tissue at the level of the deep fascia puts the branches of the great auricular nerve and lesser occipital nerve at less risk, and has been confirmed not to compromise either tissue perfusion or hair follicles.

• Journal of the Korean Society of Costume
• /
• v.59 no.10
• /
• pp.85-97
• /
• 2009

This study aims at applying Photoshop functions to digital make-up(DM) for aging effect based upon the knowledge of phrenology, comparing the result with that of the real or off-line make-up(OM) and identifying any possible difference between two methods: which contributes to understanding the potential and problems of DM at application level. This study aims at suggesting a method to apply computer graphics(CGs) to special effect make-up for aging effect through a case, contributing to attracting academic concerns and building theoretical frameworks for DM. It used 'Aging Process' in Adobe Photoshop CS4 Extended(CS4E) to change a young girl into a senior lady. In the process of DM, the study applies various tools and methods to making face wrinkled, finds the most effective way among them for each area of face, suggests a method to integrate the ways and shows the result of the method. Compared with OM, DM using CS4E is the less constrained work regarding procedure and time. Specifically, it can save the time tremendously because the reiterative operation of work can be omitted, when the same work is repeated, using 'Action' function which memorizes the history of the work. Once a DM work is produced, since it is durable, reusable and convertible to various images with additional operations, it seems very economical as well as highly promising to market the work through on-line sales. Regarding face features and skin, it reviewed literature in make-up and phrenology while it used Photoshop CS4 Extended tools to demonstrate a case of aging effect by combining and painting pictures of a young lady and a senior citizen.

• Information Systems Review
• /
• v.13 no.1
• /
• pp.33-59
• /
• 2011

Although online social network services widely used in human networking and recruiting industries, it is showing off its limitations in followings-it's hard to reach the status of seamless connection between offline and online; the incompletion and low credibility of the information came from non-face-to-face profile exchange; and the restraint of user autonomy due to centralized control. This paper defines the ubiquitous social network management which enables the seamless real-time face-to-face social interactions of the users based on WPAN (Wireless Personal Area Network) who share the same interest in real word and deduces a ubiquitous social network management framework based on it. As an instance of ubiquitous social network management, u-Recruiting service model will be designed and analyzed. The Analysis using the business model will be followed by the possible scenario of service model. The role, value proposition and potential benefits of the each participants in this service model and will be given as well. In order to evaluate relative advantages of the model suggested by this study, 6 cases will be compared.