• Journal of applied mathematics & informatics
• /
• 제38권5_6호
• /
• pp.519-532
• /
• 2020

In this paper, we first propose a new total variation-based regularization model for image restoration. We next propose a fixed-point-like method for solving the new image restoration model, and then we provide convergence analysis for the fixed-point-like method. To evaluate the feasibility and efficiency of the fixed-point-like method for the new proposed total variation-based regularization model, we provide numerical experiments for several test problems.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권4호
• /
• pp.185-195
• /
• 2020

The study aims to assess the impact of destination image, satisfaction and loyalty of tourists at mountain destinations in Thanh Hoa province, Vietnam. The study involves questionnaire surveys and multivariate data analysis methods (Cronbach Alpha test, EFA, CFA, SEM). Research results from 500 tourists in the mountain destinations of Thanh Hoa province demonstrate that all factors have imposed a positive impact on tourist satisfaction, specifically: The most influential factor is Natural features, followed by Human factors while the least influential factor is Infrastructure; On the other hand, research results also demonstrate that satisfaction has a substantial impact on tourist loyalty. Based on the research results, we also proposed some key solutions to enhance the destination image, thereby contributing to increased satisfaction and loyalty of tourists, including: (i) Promoting Natural Tourism Resources. (ii) Raising Awareness of Environmental Protection. (iii) Building Local Cultural Identity. (iv) Building Exclusive Tourist Products. (5) Strengthening the Support of Local Authorities for Tourism Activities. (vi) Developing a Price Policy.

• 한국산업융합학회 논문집
• /
• 제13권4호
• /
• pp.227-233
• /
• 2010

This study analyzes the images of city residents on the landscape elements of the rural theme villages. The results of analysis bring the following conclusions. 1) Important factor of rural landscape with worth preserving is natural landscape such as dense forests, trees and creek. 2) Natural landscape such as forests and trees is evaluated high in image-assessment as well. However, it is evaluated low in the image of "Diversity", therefore, various species of trees need to be preserved. 3) In the future, people who spent their life only in the city would be the main stream of Green-tourism, and their structure of image-assessment needs to be reorganized.

• 자연과학논문집
• /
• 제8권2호
• /
• pp.77-82
• /
• 1996

영상을 텍스처와 같은 성질의 영역으로 세그멘트 함으로써 새로운 very low bit rate 세그멘테이션 영상코딩 기술을 제안한다. 영역은 Human Visual System(HVS) 과 프락탈 특성을 이용하여 3 가지의 다른 텍스처 크래스(인간이 인지한 상 인텐셔티 (크라스 I), 부드러운 텍스처 (크라스 II) 및 거칠은 텍스처 (크리스 III) 중 1 가지로 구분한다. Very low bit rate 영상코더를 설계하기 위해 각각의 텍스처 크라스에 대해 nonoverlap과 overlap 세그멘테이션 방법을 결정하는 것이 중요하다. 좋은 화질을 갖는 재생영상은 여러 종류의 영상에 대해서 약 0.10에서 0.21비트/피셀에서 얻는다.

• 전자통신동향분석
• /
• 제39권1호
• /
• pp.95-105
• /
• 2024

In natural language processing, large language models such as GPT-4 have recently been in the spotlight. The performance of natural language processing has advanced dramatically driven by an increase in the number of model parameters related to the number of acceptable input tokens and model size. Research on multimodal models that can simultaneously process natural language and image data is being actively conducted. Moreover, natural-language and image-based reasoning capabilities of large language models is being explored in robot artificial intelligence technology. We discuss research and related patent trends in robot task planning and code generation for robot control using large language models.

• 한국방사선학회논문지
• /
• 제13권4호
• /
• pp.623-628
• /
• 2019

본 연구의 목적은 시간 분해능이 향상된 비지역적 평균 (fast non local means, FNLM) 노이즈 제거 알고리즘을 모델링하여 광학 현미경 영상에서의 적용 가능성을 확인하는 것이다. 이를 위해 실제 흰쥐 (mouse)의 첫째어금니 치아를 사용하여 영상을 획득한 후 기존에 널리 사용되고 있는 노이즈 제거 알고리즘과 제안하는 FNLM 알고리즘을 각각 적용하여 비교하였다. 정량적 평가는 대조도 대 잡음비 (contrast to noise ratio, CNR), 변동계수 (coefficient of variation, COV), 그리고 최근에 개발된 no reference 기반의 방법인 natural image quality evaluator (NIQE)와 Blind/referenceless image spatial quality evaluator (BRISQUE)를 사용하였다. 결과적으로 모든 정량적 평가 인자에서 제안하는 FNLM 노이즈 제거 알고리즘이 가장 우수한 값을 나타내었다. 특히나 치아의 전체적인 형태학적 영상을 분석할 수 있는 NIQE와 BRISQUE 인자는 원본영상에 비하여 각각 1.14와 1.12배 향상됨을 확인할 수 있었다. 결론적으로 소동물 치아 광학 현미경 영상에서의 FNLM 노이즈 제거 알고리즘의 유용성 및 가능성을 증명하였다.

• 스마트미디어저널
• /
• 제10권1호
• /
• pp.63-69
• /
• 2021

사람이 어떤 문장을 보고 그 문장에 대해 이해하는 것은 문장 안에서 주요한 단어를 이미지로 연상시켜 그 문장에 대해 이해한다. 이러한 연상과정을 컴퓨터가 할 수 있도록 하는 것을 text-to-image라고 한다. 기존 딥 러닝 기반 text-to-image 모델은 Convolutional Neural Network(CNN)-Long Short Term Memory(LSTM), bi-directional LSTM을 사용하여 텍스트의 특징을 추출하고, GAN에 입력으로 하여 이미지를 생성한다. 기존 text-to-image 모델은 텍스트 특징 추출에서 기본적인 임베딩을 사용하였으며, 여러 모듈을 사용하여 이미지를 생성하므로 학습 시간이 오래 걸린다. 따라서 본 연구에서는 자연어 처리분야에서 성능 향상을 보인 어텐션 메커니즘(Attention Mechanism)을 문장 임베딩에 사용하여 특징을 추출하고, 추출된 특징을 GAN에 입력하여 이미지를 생성하는 방법을 제안한다. 실험 결과 기존 연구에서 사용되는 모델보다 inception score가 높았으며 육안으로 판단하였을 때 입력된 문장에서 특징을 잘 표현하는 이미지를 생성하였다. 또한, 긴 문장이 입력되었을 때에도 문장을 잘 표현하는 이미지를 생성하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 신호처리소사이어티 추계학술대회 논문집
• /
• pp.553-556
• /
• 2003

In the field of content-based image retrieval, various mathematical low-level features have been proposed to describe the perceptual content of images. Since most of the features are assumed to be independent of each other, one feature is extracted from images without any consideration of the other features. Recently proposed CCE and SCFT taking advantage of the correlation between color and texture have shown relatively good performance. In this paper, the performance of CCE, SCFT, and the traditional regular weighted comparison method are evaluated. Simulation results with natural images have shown that CCE outperforms the other methods.

• IEIE Transactions on Smart Processing and Computing
• /
• 제1권3호
• /
• pp.125-132
• /
• 2012

This paper proposes an automatic object segmentation and background composition method for video communication over consumer mobile phones. The object regions were extracted based on the motion and color variance of the first two frames. To combine the motion and variance information, the Euclidean distance between the motion boundary pixel and the neighboring color variance edge pixels was calculated, and the nearest edge pixel was labeled to the object boundary. The labeling results were refined using the morphology for a more accurate and natural-looking boundary. The grow-cut segmentation algorithm begins in the expanded label map, where the inner and outer boundary belongs to the foreground and background, respectively. The segmented object region and a new background image stored a priori in the mobile phone was then composed. In the background composition process, the background motion was measured using the optical-flow, and the final result was synthesized by accurately locating the object region according to the motion information. This study can be considered an extended, improved version of the existing background composition algorithm by considering motion information in a video. The proposed segmentation algorithm reduces the computational complexity significantly by choosing the minimum resolution at each segmentation step. The experimental results showed that the proposed algorithm can generate a fast, accurate and natural-looking background composition.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.875-878
• /
• 2004

Researching in text detection and segmentation has been done for a long period in the OCR area. However, there is some other area that the text detection and segmentation from images can be very useful. In this report, we first propose the design of a mobile translator system which helps non-native speakers to understand the foreign language using ubiquitous mobile network and camera mobile phones. The main focus of the paper will be the algorithm in detecting and segmenting texts embedded in the natural scenes from taken images. The image, which is captured by a camera mobile phone, is transmitted to a translator server. It is initially passed through some preprocessing processes to smooth the image as well as suppress noises. A threshold is applied to binarize the image. Afterward, an edge detection algorithm and connected component analysis are performed on the filtered image to find edges and segment the components in the image. Finally, the pre-defined layout relation constraints are utilized in order to decide which components likely to be texts in the image. A preliminary experiment was done and the system yielded a recognition rate of 94.44% on a set of 36 various natural scene images that contain texts.