• 대한두경부종양학회지
• /
• 제26권2호
• /
• pp.198-203
• /
• 2010

Objectives : Getting full information from axial CT images needs experiences and knowledge. Sagittal and coronal images could give more information but we have to draw 3-dimensional images in mind with above informations. With aid of 3D reconstruction softwares, CT data are converted to visible 3D images. We tried to compare medical photographs of 15 surgical specimens from neck tumors with 3D reconstructed images of same patients. Material and Methods : Fifteen patients with neck tumors treated surgically were recruited. Medical photograph of the surgical specimens were collected for comparison. 3D reconstruction of neck CT from same patients with aid of 3D-doctor software gave 3D images of neck masses. Width and height of tumors of each photos and images from the same cases were calculated and compared statistically. Visual similarities were rated between photos and 3D images. Results : No statatistical difference were found in size between medical photos and 3D images. Visual similarity score were higher between 2 groups of images. Conclusion : 3D reconstructed images of neck mass looked alike the real photographs of excised neck mass with similar calculated sizes. It could give us reliable visual information about the mass.

• 천문학회보
• /
• 제44권2호
• /
• pp.44.1-44.1
• /
• 2019

We generate new intermediate images between observed consecutive solar images using NVIDIA's SuperSloMo that is a novel video interpolation method. This technique creates intermediate frames between two successive frames to form a coherent video sequence for both spatially and temporally. By using SuperSloMo, we create 600 images (12-second interval) using the observed 121 SDO/AIA 304 Å images (1-minute interval) of a filament eruption event on December 3, 2012. We compare the generated images with the original 12-second images. For the generated 480 images the correlation coefficient (CC), the relative error (R1), and the normalized mean square error (R2) are 0.99, 0.40, and 0.86, respectively. We construct a video made of the generated images and find a smoother erupting movement. In addition, we generate nonexistent 2.4-second interval images using the original 12-second interval images, showing slow motions in the eruption. We will discuss possible applications of this method.

• 천문학논총
• /
• 제16권1호
• /
• pp.25-29
• /
• 2001

We obtained three-color composite. images of 78 celestial objects most of which are listed in Messier catalogue. In order to make color images, 118 raw image sets were taken with B, V, R, I and H-alpha filters. We used the 2k CCD camera attached to the 1.8 m telescope of Bohyunsan Optical Astronomy Observatory. These composite images are to be used for educational purposes or public releases. The images are presented on the website, http://www.boao.re.kr/-ybjeon/boao_images.htrnl.

• Imaging Science in Dentistry
• /
• 제33권4호
• /
• pp.199-205
• /
• 2003

Purpose: To compare the visibility of the mandibular canal at the different radiographic methods such as conventional panoramic radiographs, Vimplant multi planar reformatting (MPR)-CT panoramic images, Vimplant MPR-CT paraxial images and film-based DentaScan MPR-CT images. Materials and Methods: Data of 11 mandibular dental implant patients, who had been planned treatment utilizing both panoramic and MPR-CT examination with DentaScan software (GE Medical systems, Milwaukee, USA), were used in this study. The archived axial CT data stored on CD-R discs were transferred to a personal computer with 17' LCD monitor. Paraxial and panoramic images were reconstructed using Vimplant software (CyberMed Inc., Seoul, Korea). Conventional panoramic radiographs, monitor-based Vimplant MPR-CT panoramic images, monitor-based Vimplant MPR-CT paraxial images, and film-based DentaScan MPR-CT images were evaluated for visibility of the mandibular canal at the mental foramen, 1 cm, 2 cm, and 3 cm posterior to mental foramen using the 4-point grading score. Results: Vimplant MPR-CT panoramic, paraxial, and DentaScan MPR-CT images revealed significantly clearer images than conventional panoramic radiographs. Particularly at the region 1 em posterior to mental foramen, conventional panoramic radiographs showed a markedly lower percentage of 'excellent' mandibular canal images than images produced by other modalites. Vimplant MPR-CT and DentaScan MPR-CT images did not show significant difference in visibility of the mandibular canal. Conclusion: The study results show that Vimplant and DentaScan MPR-CT imaging systems offer significantly better images of the mandibular canal than conventional panoramic radiograph.

• Journal of Electrical Engineering and Technology
• /
• 제10권2호
• /
• pp.659-669
• /
• 2015

Face Recognition assumes much significance in the context of security based application. Normally, high resolution images offer more details about the image and recognizing a face from a reasonably high resolution image would be easier when compared to recognizing images from very low resolution images. This paper addresses the problem of recognizing faces from a very low resolution image whose size is as low as $8{\times}8$. With the use of CCTV(Closed Circuit Television) and with other surveillance camera-based application for security purposes, the need to overcome the shortcomings with very low resolution images has been on the rise. The present day face recognition algorithms could not provide adequate performance when employed to recognize images from VLR images. Existing methods use super-resolution (SR) methods and Relation Based Super Resolution methods to construct from very low resolution images. This paper uses a learning based super resolution method to extract and construct images from very low resolution images. Experimental results show that the proposed SR algorithm based on relationship learning outperforms the existing algorithms in public face databases.

• 지능정보연구
• /
• 제9권1호
• /
• pp.125-137
• /
• 2003

동양 문화권에서는 각종 계약과 서류 결재 등을 위하여 서명대신에 도장이 오랫동안 사용되어 왔으며 아직까지도 보편적인 인증 수단으로 사용되고 있다. 지문과 달리, 도장 영상은 유사한 패턴을 갖지 않고 도장이 찍히는 압력등 입력 상태에 따라서 선명도가 크게 달라진다. 본 연구에서는 입력 장치로부터 얻은 한글 또는 한자 도장 영상을 스트레칭, 이진화 및 잡음처리를 거쳐 판별하는 시스템을 개발하였다. 이 시스템을 가장 보편적으로 사용되는 원형모양의 50개의 도장 영상 (20개 한글 도장, 20개 한자 도장, 10개 유사 도장)에 대하여 실험한 결과, 46개의 도장 영상을 성공적으로 인식하여 비교적 높은 판별도 (92%)를 보였다. 한글과 한자 도장 사이의 차이는 거의 없었으며, 도장을 찍을 때의 각도 차이나 압력 차이가 판별도를 결정하는 중요한 요인으로 작용함을 알 수 있다. 인식할 수 있는 도장 영상의 모양을 원형뿐 아니라 타원과 사각형으로 확장하고 판별도를 좀더 향상하면, 현재 육안으로 확인하는 도장 영상 인식을 자동화하는데 실제로 유용하게 사용될 수 있을 것이다.

• 복식
• /
• 제64권1호
• /
• pp.64-76
• /
• 2014

This study aimed to analyze the expressive characteristics of design elements and fashion images shown in wedding dress styles in the 2000s. The findings were as follows. First, in wedding dress style the fashion images analysis showed that classic images appeared the most frequently, and fantastic, modern, kitsch, sexy, futuristic and ethnic images appeared the most, respectively. Second, design elements analysis of fashion images concluded that as for the appearance frequency of the silhouette, A line was the highest in classic, fantastic and kitsch images and H line was the highest in ethnic, modern, futuristic and sexy image. As for the appearance frequency of the necklines, bared top neckline was the highest in all of the fashion images. As for waistlines, natural waistlines except modern image of obscure waistlines appeared the most frequently in all of the images. As for sleeve, sleeveless appeared the most frequently in all of the images. As for material, see-through was the highest in ethnic, classic, sexy, fantastic and kitsch images. Luster material was the highest in modern and futuristic image. As for colors, white and achromatic, traditional wedding dress color, appeared the same in all of the seven fashion images, but chromatic colors appeared the most frequently in ethnic images. Third, the distinguishing expression features of fashion images shown in the wedding dress style of the times is as follows: 'Total fashion in wedding dress style', 'Emphasizes sexy image expression in wedding dress style', 'Various co-existence of wedding dress style', and 'Avant-garde expression in wedding dress style'.

• 대한원격탐사학회지
• /
• 제37권5_1호
• /
• pp.999-1011
• /
• 2021

다중 센서 영상으로부터 공간 및 시간해상도가 모두 높은 영상을 예측하는 시공간 융합에서 다중 센서 영상의 방사학적 불일치는 예측 성능에 영향을 미칠 수 있다. 이 연구에서는 다중 센서 위성영상의 서로 다른 분광학적 특성을 보정하는 방사보정이 융합 결과에 미치는 영향을 분석하였다. 두 농경지에서 얻어진 Sentinel-2, PlanetScope 및 RapidEye 영상을 이용한 사례연구를 통해 상대 방사보정의 효과를 정량적으로 분석하였다. 사례연구 결과, 상대 방사보정을 적용한 다중 센서 영상을 사용하였을 때 융합의 예측 정확도가 향상되었다. 특히 입력 자료 간 상관성이 낮은 경우에 상대 방사보정에 의한 예측 정확도 향상이 두드러졌다. 분광 특성의 차이를 보이는 다중 센서 자료를 서로 유사하게 변환함으로써 예측 성능이 향상된 것으로 보인다. 이 결과를 통해 상대 방사보정은 상관성이 낮은 다중 센서 위성영상의 시공간 융합에서 예측 능력을 향상시키기 위해 필요할 것으로 판단된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권1호
• /
• pp.180-194
• /
• 2021

For small image registration, feature-based approaches are likely to fail as feature detectors cannot detect enough feature points from low-resolution images. The classic FFT approach's prediction accuracy is high, but the registration time can be relatively long, about several seconds to register one image pair. To achieve real-time and high-precision rigid registration for small images, we apply deep neural networks for supervised rigid transformation prediction, which directly predicts the transformation parameters. We train deep registration models with rigidly transformed CIFAR-10 images and STL-10 images, and evaluate the generalization ability of deep registration models with transformed CIFAR-10 images, STL-10 images, and randomly generated images. Experimental results show that the deep registration models we propose can achieve comparable accuracy to the classic FFT approach for small CIFAR-10 images (32×32) and our LSTM registration model takes less than 1ms to register one pair of images. For moderate size STL-10 images (96×96), FFT significantly outperforms deep registration models in terms of accuracy but is also considerably slower. Our results suggest that deep registration models have competitive advantages over conventional approaches, at least for small images.

• 복식문화연구
• /
• 제26권6호
• /
• pp.872-887
• /
• 2018

This study aims to identify the differences between Korean and Chinese and males and females in terms of female image preferences. The survey was conducted for 1 month targeting male and female Korean and Chinese subjects. Among the 350 completed questionnaires, 309 were used for analysis. For the analysis, 11 female images were chosen based on theoretical study, then a t-test and a paired t-test were carried out using SPSS 19.0. The results of this study are as follows: First, differences in female image preferences were observed to depend on nationality and gender. Koreans prefer urban images while Chinese prefer cute, intelligent, and sexy images. Second, males prefer innocent or sexy images, while females prefer sophisticated images. Third, Korean males prefer innocent, active, sophisticated, gentle, cute, sexy, urban, natural, intelligent, spectacular, and neutral images in order. Chinese males prefer gentle, innocent, sexy, active, sophisticated, intelligent, cute, natural, urban, spectacular, and neutral images in order. Fourth, Korean females prefer sophisticated, gentle, urban, natural, intelligent, innocent, active, sexy, cute, spectacular, and neutral images in order. Chines females prefer sophisticated, intelligent, cute, gentle, innocent, active, natural, sexy, urban, spectacular, and neutral images in order. Using these results, it will be possible to design marketing strategies for global consumers.