• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.6
• /
• pp.81-89
• /
• 2004

In this paper, we compare face recognition rate by PCA algorithm using distance change and embedded data being input left side and right side image in stereo images. The proposed method detects face region from RGB color space to YCbCr color space. Also, The extracted face image's scale up/down according to distance change and extracts more robust face region. The proposed method through an experiment could establish standard distance (100cm) in distance about 30∼200cm, and get 99.05% (100cm) as an average recognition result by scale change. The definition of super state is specification region in normalized size (92${\times}$112), and the embedded data extracts the inner factor of defined super state, achieved face recognition through PCA algorithm. The orignal images can receive specification data in limited image's size (92${\times}$112) because embedded data to do learning not that do all learning, in image of 92${\times}$112 size averagely 99.05%, shows face recognition rate of test 1 99.05%, test 2 98.93%, test 3 98.54%, test 4 97.85%. Therefore, the proposed method through an experiment showed that if apply distance change rate could get high recognition rate, and the processing speed improved as well as reduce face information.

• Journal of Digital Contents Society
• /
• v.13 no.2
• /
• pp.225-233
• /
• 2012

The 3D stereoscopic image contents have been emerging as the blue chip of the contents market of the next generation since the . However, all the 3D contents created commercially in the country have failed to enter box office. It is because the quality of Korean 3D contents is much lower than that of overseas contents and also current 3D post production process is based on 2D. Considering all these facts, the 3D editing process has connection with the quality of contents. The current 3D editing processes of the production case of are using the way that edits with the system on basis of 2D, followed by checking with 3D display system and modifying, if there are any problems. In order to improve those conditions, I suggest that the 3D editing process contain more objectivity by visualizing the depth data applied in some composition work such as Disparity map, Depth map, and the current 3D editing process. The proposed process has been used in the music drama , comparing with those of the film . The 3D values could be checked among cuts which have been changed a lot since those of , while the 3D value of drew an equal result in general. Since the current process is based on an artist's subjective sense of 3D, it could be changed according to the condition and state of the artist. Furthermore, it is impossible for us to predict the positive range, so it is apprehended that the cubic effect of space might be perverted by showing each different 3D value according to cuts in the same space or a limited space. On the other hand, the objective 3D editing by applying the visualization of depth data can adjust itself to the cubic effect of the same space and the whole content equally, which will enrich the 3D contents. It will even be able to solve some problems such as distortion of cubic effect and visual fatigue, etc.

• Journal of the Korean Geographical Society
• /
• v.29 no.2
• /
• pp.137-165
• /
• 1994

Structural adjustment of industry (or industrial restructuring) seems to be inherent in the process of capitalist economic development, which tends to be proceeded with shifts from one stage to another in order to overcome structural crises generated in each stage. The structural adjustment of industry is necessarily accompanied with regional restructuring, since it is not only projected on spece, but also mediated by space. Such a restructuring necessitates industrial and uneven regional devlopment through which capital can seek excessive profits over the rate of socio-spatial average. The industrial restructuring and uneven regional development in the 1980s in Korea can be seen as a process in which capital attempted with a strong support of the govenment to overcome the crises in the end of 1970s and hence to go on rapid economic growth. In this process, capital, especially monopoly capital concentrated into few conglomerates, pursued both extensive expansion and intensive development of industry simultaneously. In results, the Korean economy could eliminate some of peripheral characters and maturate the Fordist accumulation system. The extensive expansion of the Korean industry in the 1980s was stimulated mainly through the enlargement and adjustment of investment for equipment facilities which was planned to exclude or rationalize traditional light industries on some places, and to continue rapid growth of key heavy-chemical industries, especially of fabricated metal industry, on other places. In this process, keeping mainly the existing developmental axis which polarized the Seoul Metroplitan region and the Southeast region in Korea, the enhancing spatial mobiiity of capital and the further differentiating division of labour enforced a tendency of concentration of all types of industry in the Seoul Metropolitan region, and at the same time provoked the diffusion of some industries over Jeolla and Chungchong regions in a considerable extent. The intensive development of industriai structure in the 1980s was pursued through the strategic encouragement of subcontracting small firms mainly which produced assembling components, the technical enhancement and factory (semi-) automation, and the enrichment of service industries for estate management, finance, distribution and retailing which supported and complemented the production of goods. In this process, enabling capital to extend and elaborate its domination over space through the reorganization of regulating systems, the Fordist division of labour generated a socio-spatial hierarchy in the nation-wide scale that characterized: the Seoul Metropolitan region as an overmaturated (or overarching) Fordist region performing the conceptive functions of management, research and development, in which all types of industry (including service industries) tended to be reconcentrated; Kyungsang region as a maturated Fordist region with excutive branches of large conglomerates and with subcontracting firms around them which produced standardized products through the automized production processes in secialized Fordist industries or rationalized traditional industries; and Jeolla and Chungchong regions as newly devloping Fordist regions with newly migrated branches and some subcontracting small firms-in relatively older Fordist industries or partly rationalized traditional industries. From these analyses, it can be argued that the structural adjustment of the Korean industry in the 1980s, which had carried out both through the extensive expansion and the intensive deveiopment, strengthened further uneven regional development process, even though it appears to have reduced apparently the economic and regional disparity by balancing numerically large and small firms and by extending the Fordist industrial space nation-wideiy. And it seems more persuasive to see that the Korean industrial structure in the 1980s maturated the Fordist system of accumulation, but not yet transformed towards the post-Fordist (or the so-called flexible) accumulation system, even though the Korean economy in the 1990s seems to be under a pressure of restructuring towards the latter system.

• International Journal of Highway Engineering
• /
• v.13 no.3
• /
• pp.147-156
• /
• 2011

Since the urbanization process has been taking place, negative outcomes such as environmental pollution and traffic congestion have produced as well. Reflecting the phenomenon, our study assumed that physical structure of urban form were implicit in relation to both economic performance and cost. It can be interpreted that as the urban space has been growing bigger, economic performances such as regional product output, economy of scale and the effect of agglomeration economies are increased. On the contrary, the negative effects such as environmental pollution and traffic congestion were incurred as economic loss and expenses. It means that even though economic performance can help increase regional product output, we should consider the loss on economic expenses which are paid for social problems such as environmental pollution and traffic congestion, which are caused by urbanization. Therefore, this study aims to statistically validate the relationship between traffic congestion as the most representative economy costs and physical characteristics of urban in a large city such as Seoul and to suggest its implications. As a result of model development for empirical analysis, GRDP(0.604), the population(0.582), employment GINI coefficients(0.296), population GINI coefficients(0.254) in order led to congestion cost. We can come to the conclusion that in case of scale factor such as the population, if the population tends to concentrate, urban becomes more crowded and that if GINI coefficients (the population, employment) which are variable on inequality according to region have the disparity with surrounding areas, congestion cost is caused a lot on account of movement related with employment. In addition, this phenomenon was caused if both the population and employment were geographically biased on one side.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.3 s.309
• /
• pp.30-38
• /
• 2006

In this paper, we improved to drops recognition rate according to distance using distance and depth information with 3D from stereo face images. A monocular face image has problem to drops recognition rate by uncertainty information such as distance of an object, size, moving, rotation, and depth. Also, if image information was not acquired such as rotation, illumination, and pose change for recognition, it has a very many fault. So, we wish to solve such problem. Proposed method consists of an eyes detection algorithm, analysis a pose of face, md principal component analysis (PCA). We also convert the YCbCr space from the RGB for detect with fast face in a limited region. We create multi-layered relative intensity map in face candidate region and decide whether it is face from facial geometry. It can acquire the depth information of distance, eyes, and mouth in stereo face images. Proposed method detects face according to scale, moving, and rotation by using distance and depth. We train by using PCA the detected left face and estimated direction difference. Simulation results with face recognition rate of 95.83% (100cm) in the front and 98.3% with the pose change were obtained successfully. Therefore, proposed method can be used to obtain high recognition rate with an appropriate scaling and pose change according to the distance.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.1
• /
• pp.58-63
• /
• 2020

This paper proposes the method for improving the localization accuracy of the mobile robot based on the stereo camera. To restore the position information from stereo images obtained by the stereo camera, the corresponding point which corresponds to one pixel on the left image should be found on the right image. For this, there is the general method to search for corresponding point by calculating the similarity of pixel with pixels on the epipolar line. However, there are some disadvantages because all pixels on the epipolar line should be calculated and the similarity is calculated by only pixel value like RGB color space. To make up for this weak point, this paper implements the method to search for the corresponding point simply by calculating the gap of x-coordinate when the feature points, which are extracted by feature extraction and matched by feature matching method, are a pair and located on the same y-coordinate on the left/right image. In addition, the proposed method tries to preserve the number of feature points as much as possible by finding the corresponding points through the conventional algorithm in case of unmatched features. Because the number of the feature points has effect on the accuracy of the localization. The position of the mobile robot is compensated based on 3-D coordinates of the features which are restored by the feature points and corresponding points. As experimental results, by the proposed method, the number of the feature points are increased for compensating the position and the position of the mobile robot can be compensated more than only feature extraction.

• Investigative Magnetic Resonance Imaging
• /
• v.16 no.1
• /
• pp.67-75
• /
• 2012

Purpose : We studied enhanced method to view the vessels in the brain using Magnetic Resonance Angiography (MRA). Noticing that Maximum Intensity Projection (MIP) image is often used to evaluate the arteries of the neck and brain, we propose a new method for view brain vessels to stereo image in 3D space with more superior and more correct compared with conventional method. Materials and Methods: We use 3T Siemens Tim Trio MRI scanner with 4 channel head coil and get a 3D MRA brain data by fixing volunteers head and radiating Phase Contrast pulse sequence. MRA brain data is 3D rotated according to the view angle of each eyes. Optimal view angle (projection angle) is determined by the distance between eye and center of the data. Newly acquired MRA data are projected along with the projection line and display only the highest values. Each left and right view MIP image is integrated through anaglyph imaging method and optimal stereoscopic MIP image is acquired. Results: Result image shows that proposed method let enable to view MIP image at any direction of MRA data that is impossible to the conventional method. Moreover, considering disparity and distance from viewer to center of MRA data at spherical coordinates, we can get more realistic stereo image. In conclusion, we can get optimal stereoscopic images according to the position that viewers want to see and distance between viewer and MRA data. Conclusion: Proposed method overcome problems of conventional method that shows only specific projected image (z-axis projection) and give optimal depth information by converting mono MIP image to stereoscopic image considering viewers position. And can display any view of MRA data at spherical coordinates. If the optimization algorithm and parallel processing is applied, it may give useful medical information for diagnosis and treatment planning in real-time.