• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.7
• /
• pp.1104-1113
• /
• 2015

In this paper, we propose Two-Dimensional Robust Face Recognition System Realized with the Aid of Facial Symmetry with Illumination Variation. Preprocessing process is carried out to obtain mirror image which means new image rearranged by using difference between light and shade of right and left face based on a vertical axis of original face image. After image preprocessing, high dimensional image data is transformed to low-dimensional feature data through 2-directional and 2-dimensional Principal Component Analysis (2D)2PCA, which is one of dimensional reduction techniques. Polynomial-based Radial Basis Function Neural Network pattern classifier is used for face recognition. While FCM clustering is applied in the hidden layer, connection weights are defined as a linear polynomial function. In addition, the coefficients of linear function are learned through Weighted Least Square Estimation(WLSE). The Structural as well as parametric factors of the proposed classifier are optimized by using Particle Swarm Optimization(PSO). In the experiment, Yale B data is employed in order to confirm the advantage of the proposed methodology designed in the diverse illumination variation

• Journal of KIISE:Software and Applications
• /
• v.33 no.10
• /
• pp.862-867
• /
• 2006

To restore image degraded by blur and additive noise in the optical and electrical system, a regularized iterative restoration is used. A regularization operator is usually applied to all over the image without considering the local characteristics of image in conventional method. As a result, ringing artifacts appear in edge regions and the noise is amplified in flat regions. To solve these problems we propose an adaptive regularization iterative restoration considering the characteristic of edge and flat regions using directional regularization operator. Experimental results show that the proposed method suppresses the noise amplification in flat regions, and restores the edge more sharply in edge regions.

• Journal of Space Technology and Applications
• /
• v.2 no.3
• /
• pp.187-194
• /
• 2022

Although the magnitude of the disturbance caused by the driving of the motor operated to secure the high-speed and precise directivity of the antenna is small, it acts as a major cause of impairing the image quality of the observation satellite, which requires precision directing performance. In order to acquire high-resolution image information through the improvement of the high-resolution observation satellite, proper vibration isolation and reduction design are required so that jitter generated when the directional antenna motor is driven is not transmitted to the main mission equipment. In this paper, the development process of the directional antenna vibration reduction device applied to real satellites and the effect of micro vibration reduction before and after application will be examined. This device was designed as a way to significantly improve the jitter problem by replacing only one gear in the directional antenna driving unit with a spring damper gear without any additional interface equipment. It was first applied and launched to a high-resolution earth observation satellite, and has been successfully operated so far.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.63-69
• /
• 2021

When a person sees a sentence and understands the sentence, the person understands the sentence by reminiscent of the main word in the sentence as an image. Text-to-image is what allows computers to do this associative process. The previous deep learning-based text-to-image model extracts text features using Convolutional Neural Network (CNN)-Long Short Term Memory (LSTM) and bi-directional LSTM, and generates an image by inputting it to the GAN. The previous text-to-image model uses basic embedding in text feature extraction, and it takes a long time to train because images are generated using several modules. Therefore, in this research, we propose a method of extracting features by using the attention mechanism, which has improved performance in the natural language processing field, for sentence embedding, and generating an image by inputting the extracted features into the GAN. As a result of the experiment, the inception score was higher than that of the model used in the previous study, and when judged with the naked eye, an image that expresses the features well in the input sentence was created. In addition, even when a long sentence is input, an image that expresses the sentence well was created.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.34 no.3
• /
• pp.329-338
• /
• 2016

As the need of indoor spatial information has grown, many applications have been developed. Nevertheless, the major representations of indoor spatial information are on the 2D or 3D, recently, the service based on omni-directional image has increased. Current service based on omni-directional image is used just for viewer. To provide various applications which can serve the identifying the attribute of indoor space, query based services and so on, topological data which can define the spatial relationships between spaces is required. For developing diverse applications based on omni-directional image, this study proposes the method to generate IndoorGML data which is the international standard of indoor topological data model. The proposed method is consist of 3 step to generate IndoorGML data; 1) Analysis the core elements to adopt IndoorGML concept to image, 2) Propose the method to identify the element of ‘Space’ which is the core element of IndoorGML concept, 3) Define the connectivity of indoor spaces. The proposed method is implemented at the 6-floor of 21centurybuilding of the University of Seoul to generate IndoorGML data and the demo service is implemented based on the generated data. This study has the significance to propose a method to generate the indoor topological data for the indoor spatial information services based on the IndoorGML.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.2
• /
• pp.211-221
• /
• 2012

To utilize omni-directional images acquired by a rotating line camera for indoor spatial information services, we should register precisely the images with respect to an indoor coordinate system. In this study, we thus develop a georeferencing method to estimate the exterior orientation parameters of an omni-directional image - the position and attitude of the camera at the acquisition time. First, we derive the collinearity equations for the omni-directional image by geometrically modeling the rotating line camera. We then estimate the exterior orientation parameters using the collinearity equations with indoor control points. The experimental results from the application to real data indicate that the exterior orientation parameters is estimated with the precision of 1.4 mm and $0.05^{\circ}$ for the position and attitude, respectively. The residuals are within 3 and 10 pixels in horizontal and vertical directions, respectively. Particularly, the residuals in the vertical direction retain systematic errors mainly due to the lens distortion, which should be eliminated through a camera calibration process. Using omni-directional images georeferenced precisely with the proposed method, we can generate high resolution indoor 3D models and sophisticated augmented reality services based on the models.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.3
• /
• pp.90-97
• /
• 2007

For a highly reliable fingerprint recognition system, the precise and accurate feature extraction is indispensable. In this paper, We propose a highly efficient crease extraction method, which can improve the accuracy of feature extraction within the fingerprint image. The proposed method applies the 1-dimensional directional slit for each pixel in fingerprint image. And then it calculates the average grey level and variance to determine whether the current pixel composes the crease, and estimates the direction of crease. Once the direction of every pixel in crease candidate area is estimated, it is decomposed into 8 different images depending on their direction. From the 8 directional images, the crease clusters are estimated by utilizing the property of crease area. The proposed method finally extracts the crease from the crease clusters estimated from directional images. In conclusion, the proposed method highly improved the accuracy of overall feature extraction by accurate and precise extraction of the crease from fingerprint image.

• Journal of Broadcast Engineering
• /
• v.14 no.6
• /
• pp.807-810
• /
• 2009

This paper deals with a real-time image based relighting system for tangible video teleconference. The proposed image based relighting system renders the extracted human object using the virtual environmental images. The proposed system can homogenize virtually the lighting environments of remote users on the video teleconference, or render the humans like they are in the virtual places. To realize the video teleconference, the paper obtains the 3D object models of users in real-time using the controlled lighting system. In this paper, we use single color camera and synchronized two directional flash lights. Proposed system generates pure shading images using on and off flash images subtraction. One pure shading reflectance map generates a directional normal map from multiplication of each reflectance map and basic normal vector map. Each directional basic normal map is generated by inner vector calculation of incident light vector and camera viewing vector. And the basic normal vector means a basis component of real surface normal vector. The proposed system enables the users to immerse video teleconference just as they are in the virtual environments.

• Journal of Broadcast Engineering
• /
• v.14 no.5
• /
• pp.589-600
• /
• 2009

This paper is ready to change a trend of a ultra high definition (UHD) video image, and it will contribute to improve the performance of the latest H.264 through the Uni-directional $8{\times}8$ intra-prediction idea which is based on developing a intra prediction compression. The Uni-directional $8{\times}8$ intra prediction is focused on a $8{\times}8$ block intra prediction using $4{\times}4$ block based prediction which is using the same direction of intra prediction. This paper describes that the uni-directional $8{\times}8$ intra-prediction gets a improvement around 7.3% BDBR only in the $8{\times}8$ block size, and it gets a improvement around 1.3% BDBR in the H.264 applied to the multi block size structures. In the case of a larger image size, it can be changed to a good algorithm. Because the video codec which is optimized for UHD resolution can be used a different block size which is bigger than before(currently a minimum of $4{\times}4$ blocks of units).

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.2
• /
• pp.237-242
• /
• 2009

Comparing with fixed-type Robots, Mobile Robots have the advantage of extending their workspaces. But this advantage need some sensors to detect mobile robot's position and find their goal point. This article describe the navigation teaching method of mobile robot using omni-directional position detection system. This system offers the brief position data to a processor with simple devices. In other words, when user points a goal point, this system revise the error by comparing its heading angle and position with the goal. For these processes, this system use a conic mirror and a single camera. As a result, this system reduce the image processing time to search the target for mobile robot navigation ordered by user.