• 스마트미디어저널
• /
• 제1권2호
• /
• pp.34-39
• /
• 2012

본 연구에서는 노이즈를 제거하고 자연 영상에서 자동으로 꽃을 분할하는 후처리방법을 제시한다. 레벨 셋 알고리즘을 이용한 자연영상 꽃 분할에서는 레벨 셋이 에지 정보에만 의존하기 때문에 기대하지 않았던 분리된 노이즈들이 발생한다. 실험 결과는 제안 방법이 꽃 영역과 배경 영역의 많은 노이즈를 성공적으로 제거하였음을 보여준다.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2009년도 9th International Meeting on Information Display
• /
• pp.1022-1024
• /
• 2009

Stereoscopic Images provide depth information with the relative distances between the objects in the images. There are many different ways to extract disparity maps from the visible spectral images. For the infrared spectral range, the same approach cannot be utilized for the innate low resolution and colorless features because typical methods require corresponding features between the images. The authors suggest a new approach that makes use of image segmentation to obtain depth information for stereoscopic millimeter-wave images. For image segmentation a selective visual attention model based on the theory of a feature-integration of attention is used. Experimental results show the proposed method provides reasonable depth information for object shape recognition and display.

• 제어로봇시스템학회논문지
• /
• 제10권8호
• /
• pp.726-733
• /
• 2004

This paper presents a method to segment object ID(identification) marks on poor quality images under uncontrolled lighting conditions of automated inspection process. The method is based on dynamic programming using multiple templates and normalized gray-level correlation (NGC) method. If the lighting condition is not good and hence, we can not control the image quality, target image to be inspected presents poor quality ID marks and it is not easy to identify and recognize the ID characters. Conventional several methods to segment the interesting ID mark regions fail on the bad quality images. In this paper, we propose a multiple template method, which uses combinational relation of multiple templates from model templates to match several characters of the inspection images. To increase the computation speed to segment the ID mark regions, we introduce the dynamic programming based algorithm. Experimental results using images from real factory automation(FA) environment are presented.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2002년도 제14회 한글 및 한국어 정보처리 학술대회
• /
• pp.33-39
• /
• 2002

중국어의 품사 태깅(part-of-speech tagging)을 위해서는 중국어 문장들은 내부 단어간의 명확한 분리가 없기 때문에 단어 분할(word segmentation)과 품사 태깅을 동시에 처리해야 한다. 본 논문은 규칙 기반(rule base)과 사전 기반(dictionary base) 기법을 혼합하여 구현한 단어 분할 시스템을 사용하여 입력 문장을 단어 단위로 분할하고, HMM(hidden Markov model) 기반 통계적 품사 태깅 기법을 사용한다. 특히, 본 논문에서는 주어진 말뭉치(corpus)로부터 자동 학습(automatic training)을 통해 품사 사전을 구축하여 구현된 시스템과 말뭉치간의 독립성을 유지한다. 말뭉치는 중국어 간체와 번체 모두를 대상으로 하고, 각 말뭉치로부터 자동 학습을 통해 얻어진 품사 사전으로 단어 분할과 품사 태깅을 한다. 실험결과들은 간체, 번체 각각의 단어 분할 성능과 품사 태깅 성능을 보여준다.

• 반도체디스플레이기술학회지
• /
• 제18권4호
• /
• pp.110-115
• /
• 2019

Blur detection and segmentation play vital role in many computer vision applications. Among various methods, local binary pattern based methods provide reasonable blur detection results. However, in conventional local binary pattern based methods, the blur map is computed by using a fixed threshold irrespective of the type and level of blur. It may not be suitable for images with variations in imaging conditions and blur. In this paper we propose an effective method based on local binary pattern with adaptive threshold for blur detection. The adaptive threshold is computed based on the model learned through the multinomial logistic regression. The performance of the proposed method is evaluated using different datasets. The comparative analysis not only demonstrates the effectiveness of the proposed method but also exhibits it superiority over the existing methods.

• 한국정보기술학회 영문논문지
• /
• 제8권2호
• /
• pp.89-99
• /
• 2018

Due to global warming, various natural disasters such as floods and droughts are increasing. If we can detect the possibility of natural disasters in advance, we can prevent massive damages caused by natural disasters. Recent advances in visual sensor technologies have enabled remote monitoring of a variety of natural environments, including lakes, rivers, and shores. In this paper, we propose a method to segment an image obtained from video sensor networks into regions in order to monitor the environment effectively. In the proposed method, we first partition the image into superpixels and model the connections between superpixels as a graph. Then, initial seeds for each region are set by using the prior information, and the initial seeds are expanded to form regions using agglomerative clustering. Experimental results show that the proposed method extracts the regions from natural environment images easily and accurately.

• 한국컴퓨터정보학회논문지
• /
• 제23권12호
• /
• pp.35-41
• /
• 2018

In this paper, we propose a swarm-based possibilistic c-means(PCM) algorithm in order to overcome the problems of PCM, which are sensitiveness of clustering performance due to initial cluster center's values and producing coincident or close clusters. To settle the former problem of PCM, we adopt a swam-based global optimization method which can be provided the optimal initial cluster centers. Furthermore, to settle the latter problem of PCM, we design an adaptive thresholding model based on the optimized cluster centers that yields preliminary clustered and un-clustered dataset. The preliminary clustered dataset plays a role of preventing coincident or close clusters and the un-clustered dataset is lastly clustered by PCM. From the experiment, the proposed method obtains a better performance than other PCM algorithms on a simulated magnetic resonance(MR) brain image dataset which is corrupted by various noises and bias-fields.

• International Journal of Advanced Culture Technology
• /
• 제9권4호
• /
• pp.385-391
• /
• 2021

3D modeling of the human body is an integral part of computer graphics. Among them, several studies have been conducted on hair modeling, but there are generally few studies that effectively implement hair and face modeling simultaneously. This study has the originality of providing users with customized face modeling and hair modeling that is different from previous studies. For realistic hair styling, We design and realize hair segmentation using FCN, and we select the most appropriate model through comparing PSPNet, DeepLab V3+, and MobileNet. In this study, we use the open dataset named Figaro1k. Through the analysis of iteration and epoch parameters, we reach the optimized values of them. In addition, we experiment external parameters about the location of the camera, the color of the lighting, and the presence or absence of accessories. And the environmental analysis factors of the avatar maker were set and solutions to problems derived during the analysis process were presented.

• 한국산업융합학회 논문집
• /
• 제25권4_2호
• /
• pp.573-586
• /
• 2022

Corrosion can cause dangerous and expensive damage and failures of ship hulls and equipment. Therefore, it is necessary to maintain the vessel by periodic corrosion inspections. During visual inspection, many corrosion locations are inaccessible for many reasons, especially safety's point of view. Including subjective decisions of inspectors is one of the issues of visual inspection. Automation of visual inspection is tried by many pieces of research. In this study, we propose image preprocessing methods by image patch segmentation and thresholding. YOLOv5 was used as an object detection model after the image preprocessing. Finally, it was evaluated that corrosion detection performance using the proposed method was improved in terms of mean average precision.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.11-13
• /
• 2023

의미론적 분할(Semantic Segmentation)은 이미지 내의 객체 및 배경을 픽셀 단위로 분류하는 작업으로 정밀한 탐지가 요구되는 분야에서 활발히 연구되고 있다. 기존 어텐션 기법은 의미론적 분할의 다운샘플링(Downsampling) 과정에서 발생하는 정보손실을 완화하기 위해 널리 사용됐지만 고정된 Convolution 필터의 형태 때문에 객체의 형태에 따라 유동적으로 대응하지 못했다. 본 논문에서는 이를 보완하고자 Deformable Convolution과 셀프어텐션(Self-attention) 구조기반 어텐션 모듈을 사용한 의미론적 분할 모델을 제안한다.