• 한국멀티미디어학회논문지
• /
• 제20권10호
• /
• pp.1671-1677
• /
• 2017

In this paper, we propose a machine learning method for random noise removal in image deblurring. The proposed method uses a logistic regression to select reliable data to use them, and, at the same time, to exclude data, which seem to be corrupted by random noise, in the deblurring process. The proposed method uses commonly available images as training data. Simulation results show an improved performance of the proposed method, as compared with the median filtering based reliable data selection method.

• 한국정보처리학회논문지
• /
• 제7권2호
• /
• pp.529-535
• /
• 2000

본 논문에서는 웨이브렛 변환을 이용한 영상 부호화에서 입력 영상의 통계적 성질에 영향을 받지 않고 부호화 결과에 범용성을 갖는 새로운 벡터 양자화기 설계법을 제안한다. 기존의 벡터 양자화기의 가장 큰 문제점은 양자화대상 영상과 대표 벡터를 생성하기 위한 학습계열간의 통계적 성질의 불일치에 의한 부호화 성능의 열화이다. 그리하여, 본 논문에서는 벡터 양자화기의 대표벡터를 생성하기 위한 학습계열로 독립 난수에 영상의 상관과 에지 성분을 첨가한 모사 영상을 사용하여 종래 방식의 문제점을 해결하는 방법에 대하여 검토하였다. 제안방식에 의해 설계된 벡터양자화기와 대표 벡터 생성에 이용하는 학습계열에 부호화 대상이 되는 영상과 같은 실제의 영상을 사용한 종래 방식에 의해 설계된 벡터 양자화기와 부호화 성능을 컴퓨터 시뮬레이션을 통하여 비교하여 종래 방식의 문제점을 명확하게 밝힘과 동시에 제안 방식으로 설계된 벡터 양자화기가 부호화 성능이 뛰어남을 보인다.

• 대한원격탐사학회지
• /
• 제19권2호
• /
• pp.170-179
• /
• 2003

다중분광 영상의 정확한 지형지물 분류를 수행할 때 고려해야 할 중요한 요소중에 적절한 분류 클래스의 선정과 선정된 클래스의 분리도가 높아지도록 트레이닝 지역(training fields)을 잡는 것은 특히 중요하다. 최근에 이용되고 있는 위성탑재 하이퍼스펙트럴(hyperspectral) 영상은 많은 밴드를 포함하고 있기 때문에 데이터 처리가 어렵고, 잡음(noise)으로 인하여 다중분광 영상보다 분류 결과가 나쁜 경우도 나타난다. 특히 대상지역의 클래스에 따른 트레이닝 지역의 선정시 일부 클래스에서 하이퍼스펙트럴 밴드수에 비해 상대적으로 적은 수의 트레이닝 샘플로 인하여 공분산 행렬의 계산에 어려움이 따른다. 따라서 본 연구에서는 Hyperion 데이터를 이용한 분류를 수행하기 위하여 밴드 추출 방식을 알아보고, 분류영상의 정확도 평가를 통하여 밴드 추출의 효용성을 시험하였다. 밴드를 줄이는 또 다른 방법인 클래스간 분리도에 따른 최적 밴드를 추출하여 분류정확도를 평가하였다. 실험 결과, 밴드 추출이나 클래스 분리도에 따라 선택된 영상의 분류 정확도는 분류자(classifier)에 상관없이 전체 밴드를 사용한 원영상과 유사하게 나타났지만, 사용된 밴드수와 계산 시간은 단축되었다. 분류자는 MLC, SAM, ECHO의 3종류가 사용되었다.

• 대한원격탐사학회지
• /
• 제38권6_4호
• /
• pp.1911-1923
• /
• 2022

The availability of high-resolution satellite images provides precise information without direct observation of the research target. Korea Multi-Purpose Satellite (KOMPSAT), also known as the Arirang satellite, has been developed and utilized for earth observation. The machine learning model was continuously proven as a good classifier in classifying remotely sensed images. This study aimed to compare the performance of the support vector machine (SVM) model in classifying the land cover of the Delaware River port area on high and medium-resolution images. Three optical images, which are KOMPSAT-2, KOMPSAT-3A, and Sentinel-2B, were classified into six land cover classes, including water, road, vegetation, building, vacant, and shadow. The KOMPSAT images are provided by Korea Aerospace Research Institute (KARI), and the Sentinel-2B image was provided by the European Space Agency (ESA). The training samples were manually digitized for each land cover class and considered the reference image. The predicted images were compared to the actual data to obtain the accuracy assessment using a confusion matrix analysis. In addition, the time-consuming training and classifying were recorded to evaluate the model performance. The results showed that the KOMPSAT-3A image has the highest overall accuracy and followed by KOMPSAT-2 and Sentinel-2B results. On the contrary, the model took a long time to classify the higher-resolution image compared to the lower resolution. For that reason, we can conclude that the SVM model performed better in the higher resolution image with the consequence of the longer time-consuming training and classifying data. Thus, this finding might provide consideration for related researchers when selecting satellite imagery for effective and accurate image classification.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.185-189
• /
• 2004

For face recognition system, a face detector which can find exact face region from complex image is needed. Many face detection algorithms have been developed under the assumption that background of the source image is quite simple . this means that face region occupy more than a quarter of the area of the source image or the background is one-colored. Color-based face detection is fast but can't be applicable to the images of which the background color is similar to face color. And the algorithm using neural network needs so many non-face data for training and doesn't guarantee general performance. In this paper, A multi-scale, multi-face detection algorithm using PCA is suggested. This algorithm can find most multi-scaled faces contained in static images with small number of training data in reasonable time.

• International Journal of Advanced Culture Technology
• /
• 제4권4호
• /
• pp.23-29
• /
• 2016

In this paper, the learning technique for CNN processor on vehicle is proposed. In the case of conventional CNN processors, weighted values learned through training are stored for use, but when there is distortion in the image due to the weather conditions, the accuracy is decreased. Therefore, the method of enhancing the input image for classification is general, but it has the weakness of increasing the processor size. To solve this problem, the CNN performance was improved in this paper through the learning method of the distorted image. As a result, the proposed method showed improvement of approximately 38% better accuracy than the conventional method.

• 로봇학회논문지
• /
• 제14권1호
• /
• pp.8-13
• /
• 2019

Visual place recognition is widely researched area in robotics, as it is one of the elemental requirements for autonomous navigation, simultaneous localization and mapping for mobile robots. However, place recognition in changing environment is a challenging problem since a same place look different according to the time, weather, and seasons. This paper presents a feature extraction method using a deep convolutional auto-encoder to recognize places under severe appearance changes. Given database and query image sequences from different environments, the convolutional auto-encoder is trained to predict the images of the desired environment. The training process is performed by minimizing the loss function between the predicted image and the desired image. After finishing the training process, the encoding part of the structure transforms an input image to a low dimensional latent representation, and it can be used as a condition-invariant feature for recognizing places in changing environment. Experiments were conducted to prove the effective of the proposed method, and the results showed that our method outperformed than existing methods.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2023년도 제68차 하계학술대회논문집 31권2호
• /
• pp.697-698
• /
• 2023

최근 딥 러닝 분야의 기술이 발달하면서 Chat GPT, Google Bard와 같은 자연어 처리 기술이 확대되고 있고 이미지 객체를 분석하는 CLIP, BLIP와 같은 기술도 발전되고 있다. 그러나 전시회와 같은 예술 분야는 딥 러닝 기술 기반의 이미지 데이터 활용이 제한적이다. 본 논문은 전시회장에서의 그림 내부의 객체 데이터를 분석하기 위해 이미지 객체 분석 기술을 사용하고 자연어 처리 기반으로 관람객이 특정 그림에 대한 질문을 입력하면 해당 그림을 식별하는 방법을 제시한다. 이를 통해 관람객이 원하는 그림을 선별하여 관람할 수 있도록 한다.

• 전자통신동향분석
• /
• 제35권4호
• /
• pp.91-102
• /
• 2020

Recently, generative adversarial networks (GANs) is a field of research that has rapidly emerged wherein many studies conducted shows overwhelming results. Initially, this was at the level of imitating the training dataset. However, the GAN is currently useful in many fields, such as transformation of data categories, restoration of erased parts of images, copying facial expressions of humans, and creation of artworks depicting a dead painter's style. Although many outstanding research achievements have been attracting attention recently, GANs have encountered many challenges. First, they require a large memory facility for research. Second, there are still technical limitations in processing high-resolution images over 4K. Third, many GAN learning methods have a problem of instability in the training stage. However, recent research results show images that are difficult to distinguish whether they are real or fake, even with the naked eye, and the resolution of 4K and above is being developed. With the increase in image quality and resolution, many applications in the field of design and image and video editing are now available, including those that draw a photorealistic image as a simple sketch or easily modify unnecessary parts of an image or a video. In this paper, we discuss how GANs started, including the base architecture and latest technologies of GANs used in high-resolution, high-quality image creation, image and video editing, style translation, content transfer, and technology.

• International journal of advanced smart convergence
• /
• 제12권4호
• /
• pp.306-313
• /
• 2023

Having pet is one of the activities people living in modern society do to relieve stress and find peace of mind. Currently, the object of companion animals has moved beyond being a real 'living entity' and has developed to a stage where the animal's upbringing process can be enjoyed in a virtual space by being programmed in digital content. This paper studies detailed elements such as character design, interaction, and realism of 'Tamagotchi (1996)', which can be said to be the beginning of digital training content, and 'Peridot (2023)', a recently introduced augmented reality-based training content. The point was that it was training content using portable electronic devices. However, while the environment in the electronic device in which Tamagotchi's character exists was a simple black and white screen, the environment in which Peridot's character operates has been changed to the real world projected on the screen based on augmented reality. Mutual communication with characters in Tamagotchi remained a response to pressing buttons, but in Peridot, it has advanced to the point where you can pet the characters by touching the smartphone screen. In addition, through object and step recognition, it was confirmed that the sense of reality had become more realistic, with toys thrown by users on the screen bouncing off real objects. We hope that this research material will serve as a useful reference for the development of digital training content to be developed in the near future.