• Journal of Korea Multimedia Society
• /
• v.7 no.10
• /
• pp.1378-1388
• /
• 2004

This paper proposes method to improve the image quality degradation that show when reconstructing compressed images at low bit rate by using wavelet transform. The image quality distortion is blocking artifacts and noise in DCT's compression but blocking artifacts of wavelet transform does not appear and ringing artifacts was appeared near the edge. This proposed technique is classified to part which is ringing artifacts of the edge vicinity appears which is not, apply adaptive filter to each region improved image. A edge region which is harsh to the eye is applied by Canny mask and finding strong edge region, search the neighborhood classify the flat region and the texture region, and apply to each region suitable filter, As experiment result, PSNR value of method that is proposed in that low bit rate compression image that ringing artifact appears became low about 0.05db, but 0.023db degree rose strong edge region and nat region's image. Also, showed picture quality improved more than ringing artifacts in nat region when see from subjective viewpoint of human.

• The Journal of the Korea Contents Association
• /
• v.13 no.8
• /
• pp.1-10
• /
• 2013

This paper proposes a method to detect vanishing points of an indoor scene using line segment classification. Two-stage vanishing points detection is carried out to detect vanishing point in indoor scene efficiently. In the first stage, the method examines whether the image composition is a one-point perspective projection or a two-point one. If it is a two-point perspective projection, a horizontal line through the detected vanishing point is found for line segment classification. In the second stage, the method detects two vanishing points exactly using line segment classification. The method is evaluated by synthetic images and an image DB. In the synthetic image which some noise is added in, vanishing point detection error is under 16 pixels until the percent of the noise to the image becomes 60%. Vanishing points detection ratio by A.Quattoni and A.Torralba's image DB is over 87%.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.9 no.1
• /
• pp.39-52
• /
• 1998

The purpose of this study is to design the solution for creating full-text database of Korean dissertaion, After considering file formats for text based and image based database, Viewer, Search, Copy Right, Abstracts and Indexes, situation of Korea University Library, decided the principles of creating database. And suggested the design to produce the database for Korea University Library, that is easy to get file format conversion in case of the introducing new technology for the future.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.18 no.4
• /
• pp.387-394
• /
• 2000

The biggest factor of errors which is constructed to the database of aerial photo image is happen to process of scanning with aerial photogrammetric scanner. For the quality assurance of aerial phto image database, we are need to the verification process of aerial photogrammetric scanner. This study is purposed to exhibit quality assurance method of aerial photo image database which is established to verification method of accuracy for aerial photogrammetric scanner. As the results of this study, we are established to verification method of accuracy for aerial photogrammetric scanner. And, the proposed methods according to this study are known to contributequality assurance of aerial photo image database.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.15 no.5
• /
• pp.37-43
• /
• 2006

The target of this study is development of web based mold discrimination system by matching vision information with CAD database. The use of 2D vision image makes possible speedy mold discrimination from many databases. The image processing such as preprocessing, cleaning is done for obtaining vivid image with object information. The web-based system is a program which runs to exchange messages between a server and a client by making of ActiveX control and the result of mold discrimination is shown on web-browser. For effective feature classification and extraction, signature method is used to make sensible information from 2D data. As a result, the possibility of proposed system is shown as matching feature information from vision image with CAD database samples.

• Journal of Internet Computing and Services
• /
• v.13 no.3
• /
• pp.17-22
• /
• 2012

In this paper, a photoelectric image detection system is proposed using an APD(Avalanche Photodiode) sensor, a LED illuminator, and fiberoptic waveguides. This proposed pinhole detection system can detect the pinholes of 100 micron with the speed rate of 1,000mpm(meter per minute). And detecting performance of image system is improved by the SQL based DB analysis of classifying pinhole's detected location and size using image detection algorithms.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.2
• /
• pp.48-55
• /
• 2008

In this paper we propose a novel method for image retrieval system using image segmentation and salient points. The proposed method consists of four steps. In the first step, images are segmented into several regions by JSEG algorithm. In the second step, for the segmented regions, dominant colors and the corresponding color histogram are constructed. By using dominant colors and color histogram, we identify candidate regions where objects may exist. In the third step, real object regions are detected from candidate regions by SIFT matching. In the final step, we measure the similarity between the query image and DB image by using the color correlogram technique. Color correlogram is computed in the query image and object region of DB image. By experimental results, it has been shown that the proposed method detects multi-object very well and it provides better retrieval performance compared with object-based retrieval systems.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.4
• /
• pp.293-300
• /
• 2013

Road signs are important infrastructures for safe and smooth traffic by providing useful information to drivers. It is necessary to establish road sign DB for managing road signs systematically. To provide such DB, manually detection and recognition from imagery can be done. However, it is time and cost consuming. In this study, we proposed algorithms for automatic recognition of direction information in road sign image. Also we developed algorithm code using OpenCV library, and applied it to road sign image. To automatically detect and recognize direction information, we developed program which is composed of various modules such as image enhancement, image binarization, arrow region extraction, interesting point extraction, and template image matching. As a result, we can confirm the possibility of automatic recognition of direction information in road sign image.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2002.11a
• /
• pp.239-242
• /
• 2002

With existing illumination rendering system being used in domestic, internationally developed common programs are taking over the market more than 90%. However, since the programs are established with DB designed to be most suitable for their own products, accuracy in analysis and visualized image are hardly reliable. This raises the necessities of establishing DB for domestic developed products. A method of establishing artificial luminair DB, which was studied on DB establishment in consideration of optical characteristics of domestic products with using RADIANCE program was presented in this study, and it is considered as the program of simulating light movement most accurately among all rendering programs developed so far.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.4
• /
• pp.110-110
• /
• 2001

본 논문에서는 공간 히스토그램과 웨이브렛 모멘트를 융합하여 검색 효율을 크게 향상시키는 방법을 제안한다. 이 방법에서는 질의영상과 DB영상간의 유사도를 구할 때 히스토그램의 유사도와 웨이브렛 모멘트의 유사도를 효과적으로 융합한다. 즉, 공간적 이동, 회전 등에 강한 히스토그램 특징과 주파수 대역별로 구해지는 웨이브렛 모멘트 특징을 잘 융합함으로써 검색성능의 향상을 추구한다. 제안한 방법의 성능을 평가하기 위한 시험영상 DB로는 Brodatz 질간 영상 DB와 Corel Draw Photo 영상 DB를 사용하였다. 실험 결과, 제안한 방법으로 구한 검색율이 Brodatz DB에서 히스토그램이나 웨이브렛 모멘트만으로 구한 검색율보다 각각 5.3%와 13.8% 향상되었고, Corel Draw Photo DB에서는 각각 15.5%와 3.2% 향상됨을 확인할 수 있었다.