• 제목/요약/키워드: national image

검색결과 10,174건 처리시간 0.035초

관개용수로 CCTV 이미지를 이용한 CNN 딥러닝 이미지 모델 적용 (Application of CCTV Image and Semantic Segmentation Model for Water Level Estimation of Irrigation Channel)

  • 김귀훈;김마가;윤푸른;방재홍;명우호;최진용;최규훈
    • 한국농공학회논문집
    • /
    • 제64권3호
    • /
    • pp.63-73
    • /
    • 2022
  • A more accurate understanding of the irrigation water supply is necessary for efficient agricultural water management. Although we measure water levels in an irrigation canal using ultrasonic water level gauges, some errors occur due to malfunctions or the surrounding environment. This study aims to apply CNN (Convolutional Neural Network) Deep-learning-based image classification and segmentation models to the irrigation canal's CCTV (Closed-Circuit Television) images. The CCTV images were acquired from the irrigation canal of the agricultural reservoir in Cheorwon-gun, Gangwon-do. We used the ResNet-50 model for the image classification model and the U-Net model for the image segmentation model. Using the Natural Breaks algorithm, we divided water level data into 2, 4, and 8 groups for image classification models. The classification models of 2, 4, and 8 groups showed the accuracy of 1.000, 0.987, and 0.634, respectively. The image segmentation model showed a Dice score of 0.998 and predicted water levels showed R2 of 0.97 and MAE (Mean Absolute Error) of 0.02 m. The image classification models can be applied to the automatic gate-controller at four divisions of water levels. Also, the image segmentation model results can be applied to the alternative measurement for ultrasonic water gauges. We expect that the results of this study can provide a more scientific and efficient approach for agricultural water management.

국가이미지, 제품이미지 및 구매의도의 관계 (Relationships among the Country Image, Product Image and Purchase Intention)

  • 웅건용;무연연;김원겸
    • 한국콘텐츠학회논문지
    • /
    • 제10권12호
    • /
    • pp.267-273
    • /
    • 2010
  • 본 연구는 한국 대학생들을 대상으로 중국산 의류제품에 대한 중국 국가이미, 제품이미지 및 구매의도의 관계를 고찰하는데 주된 목적을 두었다. 분석 결과 중국 국가이미지 중 경제적 이미지, 문화적 이미지가 제품이미지에 긍정적인 영향을 미치고, 제품이미지는 구매의도에 긍정적인 영향을 미치는 것으로 나타났다. 연구 결과에 따르면 국가이미지를 중심으로 제품의 이미지에 초점을 맞추어 촉진활동을 하면 소비자의 구매행동유도에 효과적인 결과를 얻을 수 있을 것이다. 따라서 중국산 의류제품의 발전을 도모하기 위해서는 먼저 중국 국가차원의 국가이미지를 제고해야 하며, 그 결과로 제품이미지 및 구매의도를 향상시킬 수 있음을 시사하고 있다.

히스토그램 평형 기법을 이용한 자기 공명 두뇌 영상 콘트라스트 향상 (Magnetic Resonance Brain Image Contrast Enhancement Using Histogram Equalization Techniques)

  • ;이수현
    • 한국컴퓨터정보학회:학술대회논문집
    • /
    • 한국컴퓨터정보학회 2019년도 제59차 동계학술대회논문집 27권1호
    • /
    • pp.83-86
    • /
    • 2019
  • Histogram equalization is extensively used for image contrast enhancement in various applications due to its effectiveness and its modest functions. In image research, image enhancement is one of the most significant and arduous technique. The image enhancement aim is to improve the visual appearance of an image. Different kinds of images such as satellite images, medical images, aerial images are affected from noise and poor contrast. So it is important to remove the noise and improve the contrast of the image. Therefore, for this purpose, we apply a median filter on MR image as the median filter remove the noise and preserve the edges effectively. After applying median filter on MR image we have used intensity transformation function on the filtered image to increase the contrast of the image. Than applied the histogram equalization (HE) technique on the filtered image. The simple histogram equalization technique over enhances the brightness of the image due to which the important information can be lost. Therefore, adaptive histogram equalization (AHE) and contrast limited histogram equalization (CLAHE) techniques are used to enhance the image without losing any information.

  • PDF

Background Removing for Digital image self-adaptive acquisition in medical X-ray imaging

  • Li, Xun;Kim, Young-Ju;Song, Young-Jun
    • International Journal of Contents
    • /
    • 제4권1호
    • /
    • pp.12-15
    • /
    • 2008
  • In this paper, we propose a new method of background removing for digital self-adaptive acquisition in medical X-ray imaging. We analysis the construction of video digital acquisition system and main factors of acquired image quality, propose a more efficiency method to against background non-uniformly. With proposed method, non-uniform illumination back ground was well removed without image quality degradation.

Marine (sea) Familiarity Index and Its Influence to National Image

  • Rui, Dong-Gen;Jung, Yong-Ki;Lee, Chun-Su
    • 동아시아경상학회지
    • /
    • 제7권3호
    • /
    • pp.1-11
    • /
    • 2019
  • Purposes - This study discusses various aspects of familiarity with the sea and how familiarity with the sea is perceived. This study also summarizes the literature on the factors of previous researches that affect the formation or decision of national image. Research design and methodology - Sea familiarity index was derived from the results of recognition of free association with the sea, friendliness with the sea, association of the sea with life, interest to the sea, Korea's representative marine regions, and sea related emotionalism. The familiarity with the sea (ocean) perceived by foreign visitors or foreigners in the future will be helpful in deriving a comparative research. Results - This study has identified the marine tourism resources, marine ecology, and the cognitive and emotional situations consumers feel that should be developed practically. If a continuous time series research is conducted in the future through these, it will be a chance to provide a basis for consumers' dynamic awareness. Conclusions - Through this study, it is pointed out that the research utilizing the sea and ocean to form national image highly suggested an opportunity to add and utilize new variables academically. This study on the perspective of the formation of national image suggests a new approach to add and utilize new variables to future research using the sea and ocean.

림프절의 자기공명영상의 특징: 가토에서 T1과 T2 강조영상의 비교 (Magnetic resonance imaging characteristic of lymph nodes: Comparison of T1 and T2 weighted image in normal rabbits)

  • 이기창;최민철;최호정;윤정희;최승홍;문우경;정진욱
    • 대한수의학회지
    • /
    • 제44권2호
    • /
    • pp.311-315
    • /
    • 2004
  • The detection of lymph node metastasis is an important step in tumor staging and is significant for therapy planning. It has been challenged to yield an appropriate image with diagnostic methods such as Magnetic Resonance (MR) and Computed Tomography (CT). Though CT has been used widely and accessed easily to show internal organs, it can hardly provide difference between lymph node and adjacent vessel or fat tissue. It has been well established that MR can reveal the subtle discrepancy within soft tissue. This study investigated the suitability of MR lymph node imaging without contrast enhancement by comparison of T1-weighted image (T1WI) and T2- weighted image (T2WI) in ten normal rabbits. According to the pulse sequence optimized from preliminary study, T1-weighted spin-echo (repetition time/echo time=400/12 ms) and T-2 weighted fast spin-echo (repetition time/echo time=3500/84 ms) images covering the hind limbs and pelvic region were acquired at 1.5 T. Two radiologists scrupulously evaluated the MR images in consensus. And signal intensity of lymph nodes was compared with that of adjacent fat. Statistical analysis showed that T1-weighted coronal image visualized the lymph nodes (iliac, superficial inguinal and popliteal lymph nodes) quickly and consistently rather than T2-weighted one. Conclusively, T1WI for evaluation of lymph nodes is moderately better than T2WI and appears to have potential for quick and sufficient mapping of the lymph nodes. In addition, this normal MR image of lymph nodes could be applied to further study for the evaluation of lymphatic system in abscess and tumor bearing animal model.

영상 해상도 개선을 위한 고속 다중 혼합 영상 보간법 (Fast Multiple Mixed Image Interpolation Method for Image Resolution Enhancement)

  • 김원희;김종남;정신일
    • 방송공학회논문지
    • /
    • 제19권1호
    • /
    • pp.118-121
    • /
    • 2014
  • 영상 보간법은 영상의 크기 변환에서 나타나는 새로운 좌표의 화소의 값을 결정하는 방법이다. 영상 콘텐츠가 대용량화되면서 고속으로 개선된 결과 영상을 생성할 수 있는 영상 보간법이 요구된다. 따라서 본 논문에서는 영상 해상도 개선을 위한 고속 다중 혼합영상 보간법을 제안한다. 제안하는 방법은 입력 영상의 4개의 부영상으로부터 12개의 예상되는 부족분을 추정하고, 추정된 부족분과 입력 영상을 결합한 후 보간 함수를 거쳐서 결과 영상을 생성한다. 제안하는 방법은 비교 방법들보다 PSNR에서 최대 1.9dB, SSIM에서 최대 0.052 개선된 결과를 나타내었으며, 주관적 화질 비교에서도 우위에 있음을 실험을 통해서 알 수 있었다. 알고리즘의 동작속도 비교를 통해서 기존의 방법들보다 최소 3배 이상 빠르게 동작하는 것을 알 수 있었다. 제안하는 방법은 영상 해상도 개선을 위한 응용 환경에서 유용하게 사용될 수 있다.

디지털 이미지의 컬러 매니지먼트 적용에 관한 연구 (A study on Color Management Application in Digital Image)

  • 조영권;구철회;조가람
    • 한국인쇄학회지
    • /
    • 제22권2호
    • /
    • pp.163-178
    • /
    • 2004
  • In this study, the CIE RGB color space which was one of the most popular device-dependent application program in digital image processing was adopted to make the profile with the device information. The profile was applied to the digital image of a JPEG file format. The result was compared with the color reproduction of another digital image of a JPEG file format, which was made in the e-sRGB color space that had the color spaces allocated to each reproduced color of an image and device-independent colors. In this way it was investigated which color space was more appropriate for digital image processing for web printing and if the e-sRGB color space was good as a color management tool that didn't depend on a device in processing a digital image for web printing.

  • PDF

Analysis of Homomorphic Filtered Remotely Sensed Imagery and Multiple Geophysical Images

  • Ryu Hee-Young;Lee Kiwon;Kwon Byung-Doo
    • 대한원격탐사학회:학술대회논문집
    • /
    • 대한원격탐사학회 2004년도 Proceedings of ISRS 2004
    • /
    • pp.237-240
    • /
    • 2004
  • In this study, the digital image processing with image enhancement based on homomorphic filtering was performed using geophysical imaging data such as gravity, magnetic data and sub-scenes of satellite images such as LANDSAT, IKONOS, and KOMPSAT. Windows application program for executing homomorphic filtering was designed and newly implemented. In general, homomorphic filtering is technique that is based on Fourier transform, which enhances the contrast of image by removing the low frequencies and amplifying the high frequencies in frequency domain. We can enhance the image selectively using homomorphic filtering as compared with the existing method, which enhance the image totally. Through several experiment using remotely sensed imagery and geophysical image with this program, it is concluded that homomorphic filtering is more effective to reveal distinct characteristics for some complicated and multi-associated features on image data.

  • PDF

Effective Marketing Proposals Enhancing Customer Loyalty

  • Chen, Tser-Yieth;Hsu, Hsin-Swai
    • 유통과학연구
    • /
    • 제12권5호
    • /
    • pp.5-13
    • /
    • 2014
  • Purpose - We seek feasible strategies to draw customers into a state of attitudinal/behavioral loyalty through perceived quality and perceived risk in the experienced food industry. Research design, data, and methodology - We utilize the LISREL model to examine the cause and effect relationships between customer loyalty, perceived quality, perceived risk, and three marketing proposals (brand image, store image, and promotion). We employed the quota sampling method to conduct the survey questionnaires, collecting365 effective customer samples in coffee shops/stores in Taipei City. Results - We find that store image substantially benefits consumer loyalty through perceived quality. Marketing managers can enhance store environment and atmosphere to elicit both attitudinal and behavioral aspects of customer-perceived quality and loyalty. Conclusions - This is the first paper to investigate simultaneously customer loyalty across brand image, store image, and promotion/marketing proposals in the food industry. Managers can promote brand image and store image at the same time to enhance customer-perceived quality.