• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.11
• /
• pp.137-145
• /
• 2014

This paper suggests an LDA-based long distance face recognition algorithm for intelligent surveillance system. The existing face recognition algorithm using single distance face image as training images caused a problem that face recognition rate is decreased with increasing distance. The face recognition algorithm using face images by actual distance as training images showed good performance. However, this also causes user inconvenience as it requires the user to move one to five meters in person to acquire face images for initial user registration. In this paper, proposed method is used for training images by using single distance face image to automatically create face images by various distances. The test result showed that the proposed face recognition technique generated better performance by average 16.3% in short distance and 18.0% in long distance than the technique using the existing single distance face image as training. When it was compared with the technique that used face images by distance as training, the performance fell 4.3% on average at a close distance and remained the same at a long distance.

• Journal of Satellite, Information and Communications
• /
• v.6 no.2
• /
• pp.1-9
• /
• 2011

The Communication Ocean and Meteorological Satellite(COMS), the first geostationary observation satellite, was successfully launched on June 27th in 2010. The raw data of Meteorological Imager(MI) and Geostationary Ocean Color Imager(GOCI), the main payloads of COMS, is delivered to end-users through the on-ground processing. The COMS Image Data Acquisition and Control System(IDACS) developed by Korea Aerospace Research Institute(KARI) in domestic technologies performs radiometric and geometric corrections to raw data and disseminates pre-processed image data and additional data to end-users through the satellite. Currently the IDACS is in the nominal operations phase after successful in-orbit testing and operates in National Meteorological Satellite Center, Korea Ocean Satellite Center, and Satellite Operations Center, During the in-orbit test period, validations on functionalities and performance IDACS were divided into 1) image data acquisition and transmission, 2) preprocessing of MI and GOCI raw data, and 3) end-user dissemination. This paper presents that IDACS' operational validation results performed during the in-orbit test period after COMS' launch.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.11
• /
• pp.43-52
• /
• 2014

In this paper, we propose the target detection method using image displacement, and classification method using SURF(Speeded Up Robust Features) feature points and BAS(Beam Angle Statistics) in infrared images. The SURF method that is a typical correspondence matching method in the area of image processing has been widely used, because it is significantly faster than the SIFT(Scale Invariant Feature Transform) method, and produces a similar performance. In addition, in most SURF based object recognition method, it consists of feature point extraction and matching process. In proposed method, it detects the target area using the displacement, and target classification is performed by using the geometry of SURF feature points. The proposed method was applied to the unmanned target detection/recognition system. The experimental results in virtual images and real images, we have approximately 73~85% of the classification performance.

• Journal of KIISE:Software and Applications
• /
• v.32 no.2
• /
• pp.128-139
• /
• 2005

Moving object boundary is very important for moving object segmentation. But the moving object boundary shows broken boundary We invent a novel space-oriented boundary linking algorithm to link the broken boundary The boundary linking algorithm forms a quadrant around the terminating pixel in the broken boundary and searches forward other terminating pixel to link within a radius. The boundary linking algorithm guarantees shortest distance linking. We also register the background from image sequence. We construct two object masks, one from the result of boundary linking and the other from the registered background, and use these two complementary object masks together for moving object segmentation. We also suppress the moving cast shadow using Roberts gradient operator. The major advantages of the proposed algorithms are more accurate moving object segmentation and the segmentation of the object which has holes in its region using these two object masks. We experiment the algorithms using the standard MPEG-4 test sequences and real video sequence. The proposed algorithms are very efficient and can process QCIF image more than 48 fps and CIF image more than 19 fps using a 2.0GHz Pentium-4 computer.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.2 s.308
• /
• pp.12-18
• /
• 2006

This paper presents a method to extract a good high-resolution image from a low-resolution video in an automatic manner. Since a high-resolution image reconstruction method utilizing several low-resolution input images works better than a conventional interpolation method utilizing single low-resolution input image only if the input images are well registered onto a common high-resolution grid, low-resolution input images should be carefully chosen so that the registration errors can be carefully considered. In this paper, the statistics obtained from the motion-compensated low-resolution images are utilized to evaluate the feasibility of the input image candidates. Maximum motion-compensation error is estimated from the high-resolution image observation model. U the motion-compensation error of the input image candidate is greater than the estimated maximum motion-compensation error, the input image candidate is discarded. The number of good input image candidates and the statistics of the motion-compensation errors are used to choose final input images. The final input images chosen from the input image selection block are given to the following high-resolution image reconstruction block. It is expected that the proposed method is utilized to extract a good high-resolution image efficiently from a low-resolution video without any user intervention.

• Progress in Medical Physics
• /
• v.14 no.3
• /
• pp.189-195
• /
• 2003

The comparative analysis of a portal image and a simulation image is a very important process in radiotherapy for verifying the accuracy of an actual treatment field. In this study, we applied a chamfer-matching algorithm to compare a portal image with a simulation image and verified the accuracy of the algorithm to analyze the field matching error in the portal image. We also developed an analysis program that could analyze the two images more effectively with a chamfer-matching method and demonstrated its efficacy through a feasibility study. With virtual portal images, the accuracy of the analysis algorithm were acceptable considering the average error of shift (0.64 mm), rotation (0.32$^{\circ}$), and scale (1.61%). When the portal images of a head and neck phantom were analyzed, the accuracy and suitability of the developed analysis program was proven considering the acceptable average error of shift (1.55 mm), rotation (0.80$^{\circ}$), and scale (1.72%). We verified the applicability of a chamfer-matching algorithm to the comparative analysis of a portal image with a simulation image. The analysis program developed in this study was a practical tool to calculate the quantitative error of the treatment field in a portal image.

• The Journal of Korean Academy of Prosthodontics
• /
• v.31 no.2
• /
• pp.249-270
• /
• 1993

For understanding of anatomy, physiology, and diseases of human TMJ, it is required to evaluate quantitatively the movement of the disc and condyle head of mandible. The histologic section of cadaver TMJ were examined, and the magnification of the MR image and its details of anatomy were evaluated. And then a quantitative analytic method, by comparing the Sectograph and the MR image of vital human TMJ, was proposed. For this study, 15 subjects(Male, 24~35years) were selected from a prosthodontic examination randomly, and each subject’s five interocclusal rubber registration records were made on the ICP, and 5, 10, 15, and 20mmjaw opening positions. All subjects were radiographed with a Denar Quint Sectograph Image System(Denar Corp., USA), and imaged with a MRP-20EX MR Image System(0.2T, Permanent Magnet Type, Hitachi Medical Corp., Japan) using an 100mm diameter bilateral type surface coil. These images were traced on the acetate tracing paper, and analyzed In this study, the findings led to the following conclusions. 1. In comparison of the histologic section of autopsy specimen with the MR image at the same section, the size(dimension) of MR image was 70% of the real one. It was possible to recognize the shape of articular disc, anterior and posterior attachments, and adjacent soft tissues, because of the excellent reproducibility of anatomical structure. 2. When we compared the amount of joint space on MR image with that of joint space on sectograph, the amount of joint space on sectograph was significantly greater than that of joint space on MR image, except at the top of condylar head. 3. The position of minimum joint space on sectograph at intercuspal position didn't coincide with the middle position of articular disc on MR image, and was approximately in the anterior third of posterior band of articular disc. 4. The amount of condylar movement on MR image at opening movement was greater than that of articular disc movement. From Intercuspal position to 5mm jaw-opening movement, the condylar movement showed hinge one, and over the range 5mm jaw-opening it suggested hinge & translatory one. 5. In terms of area variation of articular disc measured on MR image in sagittal plane, the area of posterior band increased with increasing the amount of Jaw opening, but the area of anterior band decreased conversely.

• Journal of Korean Academy of Oral and Maxillofacial Radiology
• /
• v.23 no.1
• /
• pp.125-136
• /
• 1993

The geometrically standardized intraoral radiographs using 5 occlusal registration materials were taken serially from immediate, 1 day, 2, 4, 8, 12, and 16 weeks after making the bite blocks. And the resultant images were digitally subtracted using the immediately taken film as reference images. The qualities of those subtracted images were evaluated to check the degree of reproducibility of each impression material. The results were as follows: 1. The standard deviations of the grey scales of the overall subtracted images were 4.9 for Exal1ex, 7.2 for Pattern resin, 9.0 for Tooth Shade Acrylic, 12.2 for XCP only, 14.8 for Impregum. the lesser the standard deviation, the better the quality of the subtracted images. 2. The standard deviation of the grey scales of the overall subtracted images were grossly related to those of the localized horizontal line of interest. 3. Exaflex which showed the best subtracted image quality had 15 cases of straight, 14 cases of wave, 1 case of canyon shape. Impregum which showed the worst subtracted image quality had 4 cases of straight, 8 cases of wave, 18 cases of canyon shape respectively.

• Journal of Information Technology Services
• /
• v.11 no.sup
• /
• pp.103-111
• /
• 2012

In epigraph field to study ancient scripts, alternative readability improvement technologies have been developed to replace existing rubbing method which has low resolution and causes surface pollution of heritages from the viewpoints of extraction process and used materials. Recently many methods which are based on analysis of pixel data for extracting outlines of the specific image have been developed with advancement of image processing techniques. But these methods are not applicable and the results are not satisfied in the damaged inscriptions which are weathered by wind and rain for a long time and in the narrowed one. In this paper laser scanning techniques which uses optical triangulation measurement principle are developed to minimize scanning error. The proposed techniques are consisted of 3 parts：(1) the understanding of optical triangulation measurement principle to find scanning guideline (2) determinations of points interval, scanning distance and scanning angle to guarantee scanning data quality (3) identification of valid point data area which will be used in registration process. The proposed character identification method contributed in decoding an ancient inscription on SeukBingGo in Kyungju.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.11
• /
• pp.994-999
• /
• 2014

Nowadays we use biometrics such as face, fingerprint or palm print for registration and authentication with smart phone. When use camera function of smart phone, normally they overlay a specific image on camera preview as guideline and induce user to take picture uniformly. In this paper, use palm print for authentication factor with smart phone, we propose a new guideline and show the result about user experiment in terms of authentication success ratio.