• 융합신호처리학회 학술대회논문집
• /
• 한국신호처리시스템학회 2006년도 하계 학술대회 논문집
• /
• pp.53-56
• /
• 2006

이 논문에서 제시된 알고리즘은, 원 이미지에서 저주파를 성분을 덜어내어 얻은 성분과 원 이미지의 컴비네이션을 통해 대상 이미지를 좀 더 선명하게 하는 역할을 하도록 고안되었다. 여기에서 이미지의 저주파를 선택하기 위해 가우시안 스무딩 방법이 선택되었다. 또한 이미지의 전체적인 밝기를 유지하기 위하여 제시될 필터의 이득의 크기도 고려하였다. MATLAB으로 검증된 알고리즘을 바탕으로, 제안한 알고리즘을 통해 이전 보다 더 상세하고 선명한 이미지를 확인 할 수 있었다.

• 한국통신학회논문지
• /
• 제38A권3호
• /
• pp.240-248
• /
• 2013

본 논문에서는 이산 웨이블릿 변환(Discrete Wavelet Transform: DWT)과 적응적 가중치 보간법을 이용한 효율적인 초해상도 기법을 제안한다. 기존의 단일 영상에 적용되는 초해상도 기법들의 경우, 영상에서의 고주파 대역을 찾기 위하여 확률 기반의 방법들을 많이 사용하였다. 따라서 연산의 복잡도가 증가하고 처리시간 증가라는 문제점을 발생시킨다. 제안된 기법에서는 고주파 대역을 찾기 위한 방법으로 DWT와 적응적 가중치 보간법을 이용한다. 먼저 주어진 영상에 대하여 DWT를 수행하고, 생성된 고주파 부대역(sub-band)들을 적응적 가중치 보간법을 이용하여 입력 받은 영상과 동일한 크기의 고주파 부대역을 생성한다. 이 부대역들과 입력 받은 영상을 조합하여 이산 웨이블릿 역변환(Inverse DWT : IDWT)을 수행함으로써 고해상도의 영상을 획득하게 된다. 실험을 위하여 원본 영상($512{\times}512$)을 다운 샘플링하여 실험 영상($256{\times}256$)을 획득한다. 실험을 통하여 제안된 기법이 기존의 보간법에 비해 향상된 효율을 보이며, 확률 기반의 기법들과 비슷한 성능을 갖지만 처리시간에서 많은 이득을 보이는 것을 확인할 수 있었다.

• 한국치위생학회지
• /
• 제7권2호
• /
• pp.197-211
• /
• 2007

The purpose of this study was to examine the image of dental hygienists. The subjects in the study were 396 patients and their caregivers who visited 14 dental hospitals and dentists' offices in and around Seoul. After a survey was conducted, the following findings were given: 1. The people investigated gave a mean of 4.0 to the image of dental hygienists. Dental hygienists rated highest in terms of looking neat and tidy(4.33), and were given the lowest marks in arbitrary job performance(3.46). 2. There appeared four different types of dental hygienist images, which made a 59.824 prediction of the image of dental hygienists in general. A typical image(4.11) was most dominant, followed by professional one(4.07), personal one(4.01) and social one(3.73). 3. The relations between the general characteristics of the respondents and their image of dental hygienists could be described as below: 1) By age, those who were in their 60s(4.12) had the best image of dental hygienists, and the teenagers(3.90) had the worst image of them. 2) By gender, the men(4.05) looked at dental hygienists more positively than the women(3.96). They had a significantly different opinion on the social image of dental hygienists according to gender(pE0.05). 3) By marital status, the married people(4.00) had a better image of dental hygienists than the unmarried ones(3.95). 4) As for the influence of the type of dental institutions, they had a more favorable image of dental hygienists in dentists' offices(4.13) than in dental hospitals(3.88). There was a broad significant difference in the way they looked at the professional and personal images of dental hygienists according to the type of dental institutions(pE0.001). 5) As to the impact of educational level, those who received community-college or higher education(4.01) had the best image of dental hygienists, and those who received middle-school or lower education(3.91) had the worst image of them. 6) By occupation, the government workers and students(4.07) had the best image of dental hygienists, and the company employees(3.90) had the worst image of them. They took a significantly different view of the social image of dental hygienists according to occupation(pE0.05). 7) Concerning the impact of the frequency of receiving dental treatment, the respondents who had received it seven times or more(4.16) had the best image of dental hygienists, and those who hadn't(3.79) the worst image of them. There was a wide significant gap according to that frequency. The way they looked at the typical, social and professional images of dental hygienists was quite different significantly according to that frequency as well(pE0.001). 8) As for the influence of whether they were accompanied by caregivers or not, the people who weren't accompanied by caregivers(3.99) had a better image of dental hygienists than those who were(3.97).

• 한국소음진동공학회논문집
• /
• 제16권4호
• /
• pp.414-419
• /
• 2006

In this research, the test how the evaluation of the spacial image influenced by the environmental friendly elements included in the visual information, and how the selection of the sound changed depending on the characteristics of spacial image were carried out by the 40 subjects. Vast tracts of green land and the waterfront were highly preferred and impressive than the other spaces. The green music, signal with water sound and bird chirping sound were highly scored. In the frequency characteristics of the factors, the first factor was artificial sound (high at the low frequency band), the second was natural sound(uniform at all frequency band) and the third was water sound (high at the middle and high frequency band over 500 Hz) . This shows that the proposal of the sound which has the frequency characteristics fit to the spacial image should be selected for the soundscape of the target space.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2009년도 정보 및 제어 심포지움 논문집
• /
• pp.237-239
• /
• 2009

The purpose of this research is to propose a system to detect a strip defect on a iron plate using an image processing, one way of finding defects on an iron plate. An existing way of image processing is using a light source which release a light energy in a certain frequency and a light absorbing display which responds to the light source. This research attempts to detect defects by using the image processing which handles an illumination, without depending on characteristics of light frequency. One of the advantages of this method is that it makes up for the weakness of the existing method which was too difficult for users to notice a defect. Also this method makes it possible to realize a real-time monitoring on a plate of iron.

• 한국멀티미디어학회논문지
• /
• 제16권4호
• /
• pp.411-417
• /
• 2013

In this paper, we proposed a fast detection method of copy-move forgery image based on low frequency coefficients of the DCT coefficients. We proposed a new matching criterion of copy-moved forgery image detection (MCD) using discrete cosine transform. For each $8{\times}8$ pixel block, the DCT transform is calculated. Our algorithm uses low frequency four (DC, 3 AC coefficient) and six coefficients (DC, 5 AC coefficients) of DCT per $8{\times}8$ pixel block. Our algorithm worked block matching for DCT coefficients of the $8{\times}8$ pixel block is slid by one pixel along the image from the upper left corner to the lower right corner. Our algorithm can reduce computational complexity more than conventional copy moved forgery detection algorithms.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.648-650
• /
• 2003

Efficient multi-resolution image fusion aims to take advantage of the high spectral resolution of Landsat TM images and high spatial resolution of SPOT panchromatic images simultaneously. This paper presents a multi-resolution data fusion scheme, based on multirate image representation. Motivated by analytical results obtained from high-resolution multispectral image data analysis: the energy packing the spectral features are distributed in the lower frequency bands, and the spatial features, edges, are distributed in the higher frequency bands. This allows to spatially enhancing the multispectral images, by adding the high-resolution spatial features to them, by a multirate filtering procedure. The proposed method is compared with some conventional methods. Results show it preserves more spectral features with less spatial distortion.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.401-403
• /
• 2019

In this paper, we propose a generative adversarial networks (GAN) based text-to-image generating method. In many natural language processing tasks, which word expressions are determined by their term frequency -inverse document frequency scores. Word2Vec is a type of neural network model that, in the case of an unlabeled corpus, produces a vector that expresses semantics for words in the corpus and an image is generated by GAN training according to the obtained vector. Thanks to the understanding of the word we can generate higher and more realistic images. Our GAN structure is based on deep convolution neural networks and pixel recurrent neural networks. Comparing the generated image with the real image, we get about 88% similarity on the Oxford-102 flowers dataset.

• Journal of Information Processing Systems
• /
• 제15권1호
• /
• pp.34-46
• /
• 2019

A method for detecting foreign substances in mould based on scatter grams was presented to protect moulds automatically during moulding production. This paper proposes a wavelet transform foreign detection method based on Monte Carlo analysis mechanism to identify foreign objects in the tube. We use the Monte Carlo method to evaluate the image, and obtain the width of the confidence interval by the deviation statistical gray histogram to divide the image type. In order to stabilize the performance of the algorithm, the high-frequency image and the low-frequency image are respectively drawn. By analyzing the position distribution of the pixel gray in the two images, the suspected foreign object region is obtained. The experiments demonstrate the effectiveness of our approach by evaluating the labeled data.

• Journal of Information Technology Applications and Management
• /
• 제30권1호
• /
• pp.11-19
• /
• 2023

To remove unnecessary background from tooth X-ray images and enhance the sharpness of tooth and gum images, image processing techniques including contrast adjustment and histogram equalization are used. The introduction of two methods for detecting the boundary of the tooth and gum region and separating the tooth and gum from the background. In both cases, the background of the tooth X-ray images could be removed as a result, improving the quality of the images. The proposed method improves MTF (Modulation Transfer Function), an image performance indicator, as a result of measuring MTF. The original image's spatial frequency ranged from 4.73 to 11.40 lp/mm at the 10% response, whereas the proposed image's spatial frequency ranged from 10.90 to 11.85 lp/mm, giving uniformly enhanced results. In contrast, tooth and gums could not be completely separated from the background using Apple's Lift subject from background function.