• Journal of the Korea Convergence Society
• /
• v.9 no.8
• /
• pp.1-8
• /
• 2018

In the field of biometric security such as face and iris recognition, it is essential to extract facial features such as eyes and lips. In this paper, we have studied a method of detecting eye and lip region in face image using faster R-CNN. The faster R-CNN is an object detection method using deep running and is well known to have superior performance compared to the conventional feature-based method. In this paper, feature maps are extracted by applying convolution, linear rectification process, and max pooling process to facial images in order. The RPN(region proposal network) is learned using the feature map to detect the region proposal. Then, eye and lip detector are learned by using the region proposal and feature map. In order to examine the performance of the proposed method, we experimented with 800 face images of Korean men and women. We used 480 images for the learning phase and 320 images for the test one. Computer simulation showed that the average precision of eye and lip region detection for 50 epoch cases is 97.7% and 91.0%, respectively.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.19 no.1
• /
• pp.96-96
• /
• 2001

The aim of this study was to find out and confirm the project formulation, feasibility, scale and locations on the farmland development projects such as planned and ongoing tideland reclamation and irrigation facilities along the western coast of North Korea using satellite image data, Landsat TM, JERS OPS and SPOT PAN and aged maps. In order to apply to the study, remote sensing technologies such as geometric correction. digital mosaicking, image merging, linear extraction and land cover classification were studied. As the results of the study, the reclaimable tidal flats are recognized at about 178,000 ha equivalent to 59% of announced 300,000ha. and 16,000 ha of completed, 17,000 ha of ongoing project areas although 27,000 ha were revealed to be completed during 1987-1993. Almost planned projects are appeared to be shortage of water supply due to their small watersheds, however, most projects are connected with 2000 mile canal system.

• Korean Journal of Geomatics
• /
• v.3 no.1
• /
• pp.15-22
• /
• 2003

This study aims to construct a management system of road position information as part of the build-up to a maintenance and management system of highways. First, information on the positions of the roads were obtained by a real-time kinematic satellite surveying, and then the degree of accuracy was analyzed in comparison with the data of the existing design drawings. The linear coordinates of road center line obtained by using RTK GPS showed about 7.6-13.2cm errors in X and Y directions in the case of the national road No.2 section, and about 8.4-9.2cm errors in the case of local road No.1045 section. These errors were within the tolerance scope regulated by the TS survey, and could be practically used. In the case of vertical alignment, there were about 6.2cm errors in the Z direction in local road No.1045 section. Aerial photographs are normally used in producing numerical maps, and it can be practically used because the tolerance scope of the elevation control point is l0cm when the scale of aerial photographs is 1/1000. The management system of road position information, utilizing Object-Oriented Programming(OOP), was built having the data acquired in this way as the attribute data. The system developed in this way can enable us to spot the positions of road facilities, the target of management with ease, to easily update the data in case of changes in the positions of roads and road facilities, and to manage the positions of roads and road facilities more effectively.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.9
• /
• pp.5446-5451
• /
• 2014

Because there are some mistakes by hand in processing electronic maps using a navigation terminal, this paper proposes an automatic offline recognition for traffic signs, which are considered ingredient navigation information. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA), which have been used widely in the field of 2D face recognition as computer vision and pattern recognition applications, was used to recognize traffic signs. First, using PCA, a high-dimensional 2D image data was projected to a low-dimensional feature vector. The LDA maximized the between scatter matrix and minimized the within scatter matrix using the low-dimensional feature vector obtained from PCA. The extracted traffic signs under a real-world road environment were recognized successfully with a 92.3% recognition rate using the 40 feature vectors created by the proposed algorithm.

• Asian Journal for Public Opinion Research
• /
• v.5 no.1
• /
• pp.41-62
• /
• 2017

The political reformation in Indonesia is a determinant factor of the change in political communications and the roles of media. Currently, the political elites need media support, since it contextually has a significant role. Whoever has a good relationship with the media, will be loved by the public. On the other hand, the media also have a vested interest in the elite in running businesses and building the power of industry. Policies and capital pose a challenge to maintaining the continuity of the media. Independence and control of media are at stake, when the interests of the media and the elite collaborate with each other and then build a benefit on both sides. Meanwhile, the role of social media also cannot be neglected. The Indonesian political communication system is characterized by the presence of social media in a pseudo-relationship between the elite and the public. This paper tries to explain the growing trends of research in the academic environment and the research trends in political practice in Indonesia after the occurrence of post-reformation era in legislative and executive elections. The method used is the meta-analysis of research outcomes of university (dissertations) and secondary data sources. Data processing is done by meta-analysis of secondary data. The results of meta-analysis research indicate that, the objective conditions, in Indonesia, especially the political conditions, stimulate new spaces in communication research. The study of political communication becomes dominant in the academic environment. In addition, communication research is also characterized by a shift from the linear perspective (positivistic paradigm) to the interactive perspective (naturalistic paradigm). On the other hand, the development of politic and governance situations in Indonesia has prompted the establishment of polling agencies that help citizens understand the maps of political power and candidates in general elections and regional head elections.

• Journal of Broadcast Engineering
• /
• v.25 no.1
• /
• pp.48-57
• /
• 2020

Recently, with the rapid development of image recognition technology, the demand for object analysis in road CCTV videos is increasing. In this paper, we propose a method that can adaptively find the counting line for traffic analysis in road CCTV videos. First, vehicles on the road are detected, and the corresponding positions of the detected vehicles are modeled as the two-dimensional pointwise Gaussian map. The paths of vehicles are estimated by accumulating pointwise Gaussian maps on successive video frames. Then, we apply clustering and linear regression to the accumulated Gaussian map to find the principal direction of the road, which is highly relevant to the counting line. Experimental results show that the proposed method for detecting the counting line is effective in various situations.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.1
• /
• pp.333-342
• /
• 2012

This paper presents a vowel onset point (VOP) detection method based on the human auditory system. This method maps the "perceptual" frequency scale, i.e. Mel scale onto a linear acoustic frequency, and then establishes a series of Triangular Mel-weighted Filter Bank simulate the function of band pass filtering in human ear. This nonlinear critical-band filter bank helps greatly reduce the data dimensionality, and eliminate the effect of harmonic waves to make the formants more prominent in the nonlinear spaced Mel spectrum. The sum of mel spectrum peaks energy is extracted as feature for each frame, and the instinct at which the energy amplitude starts rising sharply is detected as VOP, by convolving with Gabor window. For the single-word database which contains 12 vowels articulated with different kinds of consonants, the experimental results showed a good average detection rate of 72.73%, higher than other vowel detection methods based on short-time energy and zero-crossing rate.

• International Journal of Highway Engineering
• /
• v.20 no.4
• /
• pp.73-84
• /
• 2018

PURPOSES : Most of the traffic surveys are carried out by an inspection method by the manpower. In some cases, the video equipment is used only in some regions when the traffic volume is surveyed. In this case, there is environmental restriction that the road equipment to fix the video equipment should exist. Also, in areas where information such as digital maps and satellite photographs is old or not provided, they are forced to rely on manpower research, but it is difficult to put huge amounts of time and money into the research in places where labor supply and demand is difficult. This difficulty is particularly pronounced in overseas business. METHODS : The purpose of this study is to improve the efficiency of business by using the drones in the traffic investigation through analysis of the cost reduction effect between the existing method and the proposed method in the overseas business traffic survey. The scope of the research is limited to the scope of research, and based on the case of overseas projects, the method of using drone for each research sector is suggested. RESULTS : In the traffic condition survey section, we propose the use of drone for traffic survey and queue length survey, and it is confirmed that there is a cost saving effect of 16% ~ 27% compared with the existing method. In the road condition survey, we propose the use of drones for road surface linear survey, geometry survey, and obstacle survey, and it was confirmed that the cost reduction effect is 39% ~ 93% compared to the existing method. CONCLUSIONS : In addition to overseas business, it is expected that it will have a positive effect on research time and cost reduction by using drone in traffic survey in domestic area where labor supply is not easy or basic data is insufficient.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.19 no.1
• /
• pp.95-106
• /
• 2001

The aim of this study was to find out and confirm the project formulation, feasibility, scale and locations on the farmland development projects such as planned and ongoing tideland reclamation and irrigation facilities along the western coast of North Korea using satellite image data, Landsat TM, JERS OPS and SPOT PAN and aged maps. In order to apply to the study, remote sensing technologies such as geometric correction. digital mosaicking, image merging, linear extraction and land cover classification were studied. As the results of the study, the reclaimable tidal flats are recognized at about 178, 000 ha equivalent to 59% of announced 300, 000ha. and 16, 000 ha of completed, 17, 000 ha of ongoing project areas although 27, 000 ha were revealed to be completed during 1987-1993. Almost planned projects are appeared to be shortage of water supply due to their small watersheds, however, most projects are connected with 2000 mile canal system.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.11 no.3
• /
• pp.28-38
• /
• 2008

The purpose of this study are to compare existing presence-absence predictive models and to predict suitable habitat for Goral (Nemorhaedus caudatus raddeanus) that is an endangered and protected species in Seoraksan national park using the best model among existing predictive models. The methods of this study are as follows. First, 375 location data and 9 environmental data layers were implemented to build a model. Secondly, 4 existing presence-absence models : Generalized Linear Model (GLM), Generalized Addictive Model (GAM), Classification and Regression Tree (CART), and Artificial Neural Network (ANN) were tested to predict the Goal habitat. Thirdly, ROC (Receiver Operating Characteristic) and Kappa statistics were used to calculate a model performance. Lastly, we verified models and created habitat suitability maps. The ROC AUC (Area Under the Curve) and Kappa values were 0.697/0.266 (GLM), 0.729/0.313 (GAM), 0.776/0.453 (CART), and 0.858/0.559 (ANN). Therefore, ANN was selected as the best model among 4 models. The models showed that elevation, slope, and distance to stream were the significant factors for Goal habitat. The ratio of predicted area of ANN using a threshold was 31.29%, but the area decreased when human effect was considered. We need to investigate the difference of various models to build a suitable wildlife habitat model under a given condition.