• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.705-710
• /
• 2003

Recent years, as a rapid development of multimedia technology, video database system to retrieve video data efficiently seems to core technology in the oriented society. This thesis describes an efficient automatic frame detection and location method for content based retrieval of video. Frame extraction part is consist of incoming / outgoing car frame extraction and car number frame extraction stage. We gain star/end time of car video also car number frames. Frames are selected at fixed time interval from video and key frames are selected by color scale histogram and edge operation method. Car frame recognized can be searched by content based retrieval method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.10C
• /
• pp.983-991
• /
• 2005

Human faces are commonly found in a video such as a drama and provide useful information for video content analysis. Therefore, face detection plays an important role in applications such as face recognition, and face image database management. In this paper, we propose a face detection algorithm based on pre-processing of scene change detection for indexing and cast searching in video. The proposed algorithm consists of three stages: scene change detection stage, face region detection stage, and eyes and mouth detection stage. Experimental results show that the proposed algorithm can detect faces successfully over a wide range of facial variations in scale, rotation, pose, and position, and the performance is improved by $24\%$with profile images comparing with conventional methods using color components.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.493-496
• /
• 2005

In this paper, we propose a new approach to detect candidate area of vehicle license plate using compounded color and vertical edge information it's own. Also, we propose a verification course, to compressed image generated by Fast DCT, using SVM to increase accuracy of extracted vechicle license plate area. Proposed method is consider that vehicle's position, become a object of it's license plate recognition, has various angle, scale and include enough environment informations. As a experimental results, proposed method shows a superior performance compared with the case that not includes verification course using SVM.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.27 no.5
• /
• pp.505-516
• /
• 2003

The purpose of this study was to develop the measurement of fashion sensibility and to verify the validity and utility. The survey has been done 91 photos selected in fashion magazines with 25 semantic differential hi-polar scale. The obtained data were analyzed by MDS, Discriminant analysis and Regression analysis. The major findings of this research were as follows. 1. According to the sensibility positioning, fashion image was classified by 4 group and agreed with constructing factors of fashion. 2. As result of the discrimination analysis, distinguishable fashion sensibility among design elements of clothing was related to refined, pleasant, feel like buying sensibility. 3. As result of the regression analysis, Preference was related to looking good, refined, and sweet, Buying needs related to likable, looking good and natural, Riches related to elegant, neat and refined, Pleasure related to looking good, elegant and bright. 4. The fashion design properties were different regarding Preference, Buying needs. Riches and Pleasure. Preference and Buying needs were related to H-line, similarity color combination, cotton and linen, Riches related to brilliance texture, ruffle and flounces, Pleasure related to fit and sexy design of clothing.

• Journal of Korea Multimedia Society
• /
• v.17 no.3
• /
• pp.300-311
• /
• 2014

According to fast change of the environment, the structured study of the ecosystem by analyzing the plant leaves are needed. Expecially, the methodology that searches and classifies the leaves from captured from the smart device have received numerous concerns in the field of computer science and ecology. In this paper, we propose a plant leaf classification technique using shape descriptor by combining Scale Invarinat Feature Transform (SIFT) and Histogram of Oriented Gradient (HOG) from the image segmented from the background via Graphcut algorithm. The shape descriptor is coded in the field of Locality-constrained Linear Coding to optimize the meaningful features from a high degree of freedom. It is connected to Support Vector Machines (SVM) for efficient classification. The experimental results show that our proposed approach is very efficient to classify the leaves which have similar color, and shape.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.46 no.11
• /
• pp.40-47
• /
• 2009

In this paper, we present the design of a source driver of QVGA scale TFT-LCD driver IC which uses a mixed driving method and performs $\gamma$-correction to improve image. The source driver with 240 RGB ${\times}$ 320 dots resolution drives a TFT-LCD panel through 720 channels and implements 262k colors using 18-bit RGB data format. The mixed driving method is a mixture the channel amp. driving method with high drivability and the gray amp. driving method with small area, which remarkably reduces channel driver areas. The driver has been designed using the $0.35{\mu}m$ Magnachip embedded DRAM technology and simulated using the HSPICE simulator. The results show that our source driver operates well with y-correction and the channel driver has $17{\mu}s$ channel driving time with only 78 driving amplifiers and control logic.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.7 no.3
• /
• pp.157-165
• /
• 2005

The purpose of this research is to investigate the actual conditions of the manufacturer's design processes. Questionnaires were sent out, and 57 interviews were used as research methods including designers, programmers, and merchandisers working for a knit manufacturer in Seoul, followed by a frequency analysis using SPSS 12.0. The results are as follows: knitted fabric goods were the top choices in casual wear. Brand image depended on 'elegance', 'modernity', and 'romanticism', among other lifestyle pursuits. The distribution ratio of the 'basic' and the 'trendy' knit was at 3:7 or 7:3, while the ratio of 6:4 or 4:6 was more common. Knit structure was proven to be the most important factor in the changes in designs. Style and yam ranked second and third, respectively. In addition, details (embroidery and beading), color, pattern, and processing were among the other factors, in order of importance. Based on the difficulty in designing and manufacturing knitted fabric goods, 'manufacturing cost:' 'lack of a manufacturing facility for small production,' and 'limited delivery time' were among the reasons cited in the questionnaire. These results appeared to have been caused by small-scale manufacturers or small-scale manufacturing facilities that made small volume production difficult. The results of the interviews on knitted fabrics that were most frequently used and with the highest sales volumes showed that plain, lace, links & links, miss, and 1:1 rib were ranked accordingly for S/S use, while jacquard, cable, 1:1 rib, links & links, milano, plain, and half cardigan were ranked accordingly for F/W use.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.20 no.1
• /
• pp.59-67
• /
• 2002

Recently, much demand of vector data have increased rapidly such as a digital map instead of traditional a paper map and the raster data such as a high-resolution orthoimage have been used for many GIS application with the advent of industrial high-resolution satellites and development of aerial optical sensor technologies. Aerial photogrammetric technologies using an airship can offer cost-effective and high-resolution color images as well as real time images, different from conventional remote sensing measurements. Also, it can acquire images easily and its processing procedure is short and simple relatively. On the other hand, it has often been used for the production of a small-scale land use map not required high accuracy, monitoring of linear infrastructure features through mosaicking strip images and construction of GIS data. Through this study, the developed aerial photogrammetric system using the airship expects to be applied to not only producing of scale 1:5, 000 digital map but also verifying, editing, and updating the digital map which was need to be reproduced. Further more, providing the various type of video-images, it expects to use many other GIS applications such as facilities management, scenery management and construction of GIS data for Urban area.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.5
• /
• pp.423-432
• /
• 2018

Surface water mapping has been widely used in various remote sensing applications. Water indices have been commonly used to distinguish water bodies from land; however, determining the optimal threshold and discriminating water bodies from similar objects such as shadows and snow is difficult. Deep learning algorithms have greatly advanced image segmentation and classification. In particular, FCN (Fully Convolutional Network) is state-of-the-art in per-pixel image segmentation and are used in most benchmarks such as PASCAL VOC2012 and Microsoft COCO (Common Objects in Context). However, these data sets are designed for daily scenarios and a few studies have conducted on applications of FCN using large scale remotely sensed data set. This paper aims to fine-tune the pre-trained FCN network using the CRMS (Coastwide Reference Monitoring System) data set for surface water mapping. The CRMS provides color infrared aerial photos and ground truth maps for the monitoring and restoration of wetlands in Louisiana, USA. To effectively learn the characteristics of surface water, we used pre-trained the DeepWaterMap network, which classifies water, land, snow, ice, clouds, and shadows using Landsat satellite images. Furthermore, the DeepWaterMap network was fine-tuned for the CRMS data set using two classes: water and land. The fine-tuned network finally classifies surface water without any additional learning process. The experimental results show that the proposed method enables high-quality surface mapping from CRMS data set and show the suitability of pre-trained FCN networks using remote sensing data for surface water mapping.

• Journal of Broadcast Engineering
• /
• v.16 no.4
• /
• pp.602-613
• /
• 2011

In this paper, we propose a hybrid stereoscopic camera system which acquires and utilizes stereoscopic images from two different camera modules, the main-camera module and the sub-camera module. Hybrid stereoscopic camera can effectively reduce the price and the size of a stereoscopic camera by using a relatively small and cheap sub-camera module such as a mobile phone camera. Images from the two different camera modules are very different from each other in aspects of color, angle of view, scale, resolution and so on. The proposed system performs an efficient hybrid stereoscopic image registration algorithm that transforms hybrid stereoscopic images into normal stereoscopic images based-on camera geometry. As experimental results, the registered stereoscopic images and applications of the proposed system are shown to demonstrate the performance and the functionality of the proposed camera system.