• 한국통신학회논문지
• /
• 제19권1호
• /
• pp.111-119
• /
• 1994

본 논문에서는 차분변화에 이은 Run-length 부호화와 RDH(Run-length Dynamic Huffman Codding)에 의한 가역 부호화 방식을 제안하였다. 단계적 전송 기능을 부가하기 위하여 비트 플랜을 사용하였으며, 시스템 구성의 간결성을 위해야 단일 주사 방식의 Run-length 부호에 기초한 부호와 방식을 적용하였다. 특히, 하위 비트열에 대한 압축률을 개선하기 위해 가변형의 RDHC가 유효함을 보였으며, 컴퓨터 시뮬레이션에 의해 그 성능을 비교.분석 하였다. 그 결과 2차 차분변환후 VFRL(Variable to Fixed Run-Length) 부호화가 무변환, 그레이변환 및 1차 차분변환 방법에 비해 평균 1.271, 0.77 및 0.629 [bit/pixel]씩 향상되었다. 또한, 2차 차분변환에 이은 RDHC의 결과는 VFRL, Dynamic Huffman, Arthmetic 및 LZE부호화 보다 0.76, 0.37, 0.22 및 0.68[bit/pixel]씩 향상되어 비교적 간단한 시스템의 구성으로 각종 유니버샬 부호에 비해 높은 압축 효과를 얻었다.

• International Journal of Computer Science & Network Security
• /
• 제23권8호
• /
• pp.49-62
• /
• 2023

There has been a rapid increase in the creation and alteration of new malware samples which is a huge financial risk for many organizations. There is a huge demand for improvement in classification and detection mechanisms available today, as some of the old strategies like classification using mac learning algorithms were proved to be useful but cannot perform well in the scalable auto feature extraction scenario. To overcome this there must be a mechanism to automatically analyze malware based on the automatic feature extraction process. For this purpose, the dynamic analysis of real malware executable files has been done to extract useful features like API call sequence and opcode sequence. The use of different hashing techniques has been analyzed to further generate images and convert them into image representable form which will allow us to use more advanced classification approaches to classify huge amounts of images using deep learning approaches. The use of deep learning algorithms like convolutional neural networks enables the classification of malware by converting it into images. These images when fed into the CNN after being converted into the grayscale image will perform comparatively well in case of dynamic changes in malware code as image samples will be changed by few pixels when classified based on a greyscale image. In this work, we used VGG-16 architecture of CNN for experimentation.

• 대한핵의학회지
• /
• 제35권1호
• /
• pp.43-51
• /
• 2001

목적: 이번 연구는 임상적으로 구내 건조증을 호소하는 환자에서 Tc-99m pertechnetate를 사용하여 역동적 타액선 신티그라피를 얻어 기능적 변수를 정량화 하고자 하였으며 그 결과를 정적 타액선 신티그라피와 비교하여 그 유용성을 비교하고자 하였다. 대상 및 방법: 임상적으로 구내 건조증을 호소하는 환자 26명의 52개의 이하선과 52개의 악하선을 대상으로 하였다. 각각의 환자에서 역동적 타액선 신티그라피와 정적 타액선 신티그라피를 얻었다. 비교를 위하여 10명의 정상 대조군에서 같은 방법으로 타액선 신티그라피를 획득하였다. 370 MBq Tc-99m pertechnetate를 정주한 다음 10분 후에 자극 전 정적영상을 획득하였고 이어서 20분간 역동적 영상을 획득하였는데 이때 최타 자극을 위해 레몬 주스를 사용하였다. 역동적 영상을 획득한 후에 정적영상을 다시 획득하여 재섭취 영상으로 하였다. 역동적 영상에서는 섭취율, 분비율 및 재섭취율과 같은 기능적 변수를 획득하여 정상과 비정상을 판별하였다. 마지막으로 정적영상과 동적영상의 결과를 비교하였다. 결과: 모든 증례에서 역동적 타액선 신티그라피에서 섭취율, 분비율 및 재섭취율을 성공적으로 획득할 수 있었다. 역동적 신티그라피에서 각각 52개의 이하선과 악하선 중 22개의 이하선과 22개의 악하선이 비정상으로 판독되었다. 정적 신티그라피에서는 다른 결과가 초래 되었는데 역동적 타액선 신티그라피의 결과를 참조하여 그 원인을 추정할 수 있었다. 결론: Tc-99m perechnetate를 사용한 역동적 타액선 신티그라피는 정적 신티그라피보다 타액선의 기능적인 평가에 더 유리하다고 생각되며 임상적으로 구강건조증이 있는 환자에서 타액선의 기능적인 변화를 평가하는데 유용하다고 생각된다.

• Journal of information and communication convergence engineering
• /
• 제7권3호
• /
• pp.323-329
• /
• 2009

In this paper, we propose the improvement method of the camera images regardless of exposure environments. By using a double-exposure method, we could improve camera images with clear recognition. We applied the improvement method on the mobile phone. For the feasibility of the proposed algorithm, we compared simulated camera images with the proposed method to conventional images by using auto-exposure image. Experimental results are also shown in this paper.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권4호
• /
• pp.1846-1863
• /
• 2016

High dynamic range (HDR) images can present the perfect real scene and rich color information. A commonly encountered problem in practical applications is how to well visualize HDR images on standard display devices. In this paper, we propose a multi-scale decomposition method using guided filtering for HDR image tone mapping. In our algorithm, HDR images are directly decomposed into three layers：base layer, coarse scale detail layer and fine detail layer. We propose an effective function to compress the base layer and the coarse scale detail layer. An adaptive function is also proposed for detail adjustment. Experimental results show that the proposed algorithm effectively accomplishes dynamic range compression and maintains good global contrast as well as local contrast. It also presents more image details and keeps high color saturation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권11호
• /
• pp.5419-5435
• /
• 2017

The construction of panoramic images on smartphones and low-powered devices is a challenging task. In this paper, we propose a new approach for smoothly stitching images on mobile phones in the presence of moving objects in the scene. Our main contributions include handling moving object problems, reducing processing time, and generating rectangular panoramic images. First, unique and robust feature points are extracted using fast ORB method and a feature matching technique is applied to match the extracted feature points. After obtaining good matched feature points, we employ the non-deterministic RANSAC algorithm to discard wrong matches, and the hommography transformation matrix parameters are estimated with the algorithm. Afterward, we determine precise overlap regions of neighboring images and calculate their absolute differences. Then, thresholding operation and noise removal filtering are applied to create a mask of possible moving object regions. Sequentially, an optimal seam is estimated using dynamic programming algorithm, and a combination of linear blending with the mask information is applied to avoid seam transition and ghosting artifacts. Finally, image-cropping operation is utilized to obtain a rectangular boundary image from the stitched image. Experiments demonstrate that our method is able to produce panoramic images quickly despite the existence of moving objects.

• 방송공학회논문지
• /
• 제14권4호
• /
• pp.428-437
• /
• 2009

A high dynamic range (HDR) image can represent real world scenes that have a wide range of luminance intensity. However, compared with the range of real world luminance, conventional display devices have a low dynamic range (LDR). To display HDR images onto conventional displayable devices such as monitors and printers, we propose the logarithmic based global reproduction algorithm that considers the features of the image using reproduction parameters. Based on the characteristics of the image, we first modify the input luminance values for reproducing perceptually tuned images and then obtain the displayable output values directly. The experimental results show that the proposed algorithm achieves good subjective results while preserving details of the image; furthermore, the proposed algorithm has a fast, simple and practical structure for implementation.

• 한국멀티미디어학회논문지
• /
• 제22권1호
• /
• pp.10-17
• /
• 2019

In High Dynamic Range (HDR) image processing, tone mapping is the process to compress an input image into a Low Dynamic Range (LDR) image. In most cases, the reason that detail preservation is prior to take over tone mapping is that the dynamic range is significantly different between input and output images. In the case of iCAM06, details are separated by using a bilateral filter, however, it causes noise amplification at the dim surround region. Thus, we suggest that the detail signal, which is separated from the bilateral filter, is combined with the base signal after an adaptive Kalman filter is applied according to the local standard deviation. We confirmed that the proposed method enhances the HDR images quality by checking the noise reduction in a dim surround region.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.555-556
• /
• 2021

우리는 패션 의류 이미지의 빠르고 정확한 분류를 달성하기 위해 최적화된 동적 붕괴 학습률과 개선된 모델 구조를 가진 딥 러닝 모델을 기반으로 하는 새로운 방법을 제안한다.

• 한국의류산업학회지
• /
• 제14권5호
• /
• pp.713-719
• /
• 2012

The purpose of this study is to analyze the style of the windsurfing suits and to extract main expressional words for the development of semantic differential scales of visual images according to the change in the style of windsurfing suits. The results of this study are as follows: 1) By a period of activity and its functions of windsurfing suits, they were classified into dry suit, wet suit, semi-dry suit and warm water. 2) Windsurfing suits were assorted into 4 kinds of designs: the design #1 on a suit with long sleeves and long pants, the design #2 on a suit with half sleeves and long pants, the design #3 on a suit with half sleeves and half pants, and the design #4 on sleeveless and half pants. 3) Main expressional words of visual images for windsurfing suits differ greatly depending on the design of windsurfing suits. The visual images for the design #1 are ranked in the order of 'sporty', 'looking like arms that are slim', 'looking like thighs that are slim', 'looking slim', 'neatbbb, 'practical', 'difficult to wear'. The visual images for the design #2 are placed in the order of 'sporty', 'dynamic', 'practical', 'cheerful', 'light'. The visual images for the design #3 are ranked in the order of 'sporty', 'dynamic', 'light', 'cheerful', 'masculine', 'practical'. The visual images for the design #4 are placed in the order of 'sporty', 'dynamic', 'simple', 'light', 'uncomfortable', 'easy to wear', 'looking like arms that are fat'.