• Proceedings of the Korean Society of Computer Information Conference
• /
• 2011.06a
• /
• pp.31-34
• /
• 2011

영상처리 기법을 이용한 이미지 인식에 관한 컨텐츠들은 아주 다양한 알고리즘을 사용하였다. 영상처리 기법에서 이미지 인식기법 중에서 일반적인 것으로는 PCA(Principal Component Analysis) 알고리즘이 있다. 이 알고리즘이 적용된 대표적인 컨텐츠로는 얼굴 문자인식이 있다. 이 알고리즘은 정확성을 위하여 학습을 통한 영상의 저장과 인식을 통한 복잡한 알고리즘을 사용한다. 간단한 이미지 인식 컨텐츠의 경우에 복잡한 알고리즘을 사용함으로써, 시스템 처리속도에 영향을 줄 수 있다. 따라서 이 논문에서는 비교연산을 수행하는 히스토그램 매칭을 두 가지 실험 방법을 통하여, 간단한 이미지인식 시스템을 위한 알고리즘을 설계한 것이다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.370-373
• /
• 2022

Recently, various deep learning framework models such as Tensorflow, Pytorch, Keras, etc. have appeared. In addition, CNN (Convolutional Neural Network) is applied to image recognition using frameworks such as Tensorflow, Pytorch, and Keras, and the optimization model in image classification is mainly used. In this paper, based on the results of training the CNN model with the Paitotchi and tensor flow frameworks most often used in the field of deep learning image recognition, the two frameworks are compared and analyzed for image analysis. Derived an optimized framework.

• Convergence Security Journal
• /
• v.22 no.4
• /
• pp.129-133
• /
• 2022

Deep learning frameworks are still evolving, and there are various frameworks. Typical deep learning frameworks include TensorFlow, PyTorch, and Keras. The Deepram framework utilizes optimization models in image classification through image learning. In this paper, we use the TensorFlow and PyTorch frameworks, which are most widely used in the deep learning image recognition field, to proceed with image learning, and compare and analyze the results derived in this process to know the optimized framework. was made.

• Journal of the Korea Convergence Society
• /
• v.8 no.9
• /
• pp.85-91
• /
• 2017

The purpose of this study was conducted to identify differences of nursing professionalism and nurse's image before and after convergence-based nursing history and culture program. Study subjects were 29 juniors in B nursing college. The convergence-based nursing history and culture programs had been provided 6 times. In this study, the score of nursing professionalism and nurses' image were significantly increased after program. Among the sub-items of nursing professionalism, the self-concept of professionalism, the social awareness, the professionalism of nursing showed significant improvement, and among the sub-items of nurse's image, the role of nurse, the interpersonal relationship of nurse were statistically significant improvement after program. Nursing professionalism and Nurse's image had significant positive relationship with each other. Therefore this program could be a good extra-curriculum and it is necessary to develop more variable contents.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.2
• /
• pp.20-25
• /
• 2019

Most multimedia signals contain image data, so the problem of efficient processing and transmitting the image data is an important task of the information society. This paper proposes a compression algorithm that reduces the color bits according to importance using YUV color space among the various methods of compressing image data. 4: 2: 2 subsampling is the standard in the field of video. Using the color information and the characteristics of the human retina, YUV color data was reduced by 4: 2: 2 subsampling. The YUV images and RGB images can be interconverted using the transformation matrix. The image data was converted into color space by YUV, and the relatively low U and V bits were subjected to a downscaling operation. The data was then compressed through 4: 2: 2 subsampling. The performance of the proposed algorithm was compared and analyzed by a comparison with existing methods. As a result of the analysis, it was possible to compress the image without reducing the information of the low importance color element and without significant deterioration in the quality compared to the original.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.3
• /
• pp.75-82
• /
• 2009

The comparison of images uses PSNR generally. In the case that PSNR value is above 35, it is hard to distinguish the quality of images. In 2006 Lee has proposed the protocol to be able to prove ownership of image using publishing MSB bit strings of original image instead of original images and used the new function to measure correlation of MSB bit strings of two images. In the view of measuring the quality of images, correlation is a bit different from PSNR. That is, if an object image to gene ate from an original image has lower quality, PSNR has very low value, but though the quality is bad, correlation of the images is very high in the view of similarity. In this paper, we modify MSB comparison function that LEE suggested and propose the ICOR function, then analyze the possibility to decide correlation of two images.

• Science of Emotion and Sensibility
• /
• v.13 no.3
• /
• pp.493-500
• /
• 2010

The development of new technology and diversity in user needs lead mobile phone manufacturers to establish new strategies different from the existing for user attraction. Product identity, and brand image are major strategies for differentiation and adding new values to a product. This research starts with stating emotional brand image as the brand image made by the actual usage and the emotion built from the experience while using the product. This research will compare emotional brand image of the three major mobile phone manufactures in Korea (Brand A, C, and S) using evaluation of six representative emotions from users while using the product. The result of evaluating actual mobile phone users and the emotion built while actually using the product showed the brand image, and especially the emotional side of Korean mobile phone manufacturers. The result of this research itself would not be sufficient to simply state the emotional brand image of Korean mobile phone manufactures, but with further research including age, profession, gender and other demographic factors the result of this research would surely be able to abstract a clearer view of emotional brand image of Korean mobile phone manufactures.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.12C
• /
• pp.1216-1223
• /
• 2006

In many imaging devices, a single image sensor is used, which is covered by a color filter array to filter out the specific color components from light. Since an image acquired from this image sensors have a color components at each pixel, it is needed to be reconstructed to a perfect image. In this paper, a new color interpolation method for the imaging devices having a single image sensor is proposed. The proposed method improves a edge sensing function to obtain satisfactory results in edges of an image, md presents a new inter-channel correlation for improving interpolation performance in smooth region. We have compared our method with several exiting methods, and our experimental results have proved better interpolation performance in comparing with the other results.

• Journal of Applied Tourism Food and Beverage Management and Research
• /
• v.13 no.2
• /
• pp.27-44
• /
• 2002

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.628-630
• /
• 2002

본 논문은 현재까지 제안된 여러 가지의 움직임 적응형 알고리즘을 비교 분석하였다. 비교 분석은 C++를 이용한 시뮬레이션을 하였고 여러 가지 이미지에 대잔 PSNR 값을 추출하였으며 에지 특성을 확인하고 그리고 시뮬레이션된 이미지를 원본과 비교 평가하였다. 그 결과 PSNR 값과 알고리즘의 성능과는 크게 낙관이 없었고, 에지 특성과 이미지간에 비교가 평가에 더 확실한 방법이었다. 알고리즘 성능은 어떤 이미지론 사용함에 따라 성능이 달라졌다. 전체적으로 볼 때 동영상에서는 $\Delta$- 형이 가장 좋은 결과가 확인되었으며 준동영상에서는 미디언 필터와 Adaptive형이 비슷한 성능을 보여 주었다.