• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권10호
• /
• pp.5015-5038
• /
• 2018

In this paper, a novel spectral-spatial joint sparse representation algorithm for hyperspectral image classification is proposed based on multi-layer superpixels in various scales. Superpixels of various scales can provide complete yet redundant correlated information of the class attribute for test pixels. Therefore, we design a joint sparse model for a test pixel by sampling similar pixels from its corresponding superpixels combinations. Firstly, multi-layer superpixels are extracted on the false color image of the HSI data by principal components analysis model. Secondly, a group of discriminative sampling pixels are exploited as reconstruction matrix of test pixel which can be jointly represented by the structured dictionary and recovered sparse coefficients. Thirdly, the orthogonal matching pursuit strategy is employed for estimating sparse vector for the test pixel. In each iteration, the approximation can be computed from the dictionary and corresponding sparse vector. Finally, the class label of test pixel can be directly determined with minimum reconstruction error between the reconstruction matrix and its approximation. The advantages of this algorithm lie in the development of complete neighborhood and homogeneous pixels to share a common sparsity pattern, and it is able to achieve more flexible joint sparse coding of spectral-spatial information. Experimental results on three real hyperspectral datasets show that the proposed joint sparse model can achieve better performance than a series of excellent sparse classification methods and superpixels-based classification methods.

• Tribology and Lubricants
• /
• 제23권6호
• /
• pp.301-305
• /
• 2007

The wear particle analysis has been known as very effective method to foreknow and decide a moving situation and a damage of machine parts by using the digital computer image processing. But it was not laid down and trusted to calculate shape parameters of wear particle and wear volume. In order to apply image processing method in the foreknowledge and decision of lubricated condition, it needs to verify the reliability of the calculated data by the image processing and to lay down the number of images and the amount of wear particle in one image. In this study, the lubricated friction experiment was carried out in order to establish the optimum image capture with the SM45C specimen under experiment condition. The wear particle data were calculated differently according to the number of image and the amount of wear particle in one image.

• 한국항공우주학회지
• /
• 제34권6호
• /
• pp.67-74
• /
• 2006

본 논문에서는 저가의 클러스터 컴퓨터 시스템과 저해상도 영상장비들을 이용하여 초대형 해석 데이터를 정밀하게 분석할 수 있는 고해상도 타일 가시화 시스템을 개발하였다. 타일 가시화 하드웨어 구축 시 유의점을 고찰하고, 화면왜곡 현상을 제거할 수 있는 빔프로젝터 위치조절장치를 설계/제작하였다. 타일 가시화 소프트웨어 개발에서 그래픽 사용자 인터페이스와 렌더링을 위해서는 Qt와 OpenGL 라이브러리를 이용하였다. 또한 LAM-MPI 라이브러리를 통해 각각의 클러스터 컴퓨터 노드로부터 얻게 되는 조각적인 화면들을 전체의 한 화면으로 동기화시켜 왜곡 없는 전체 타일 영상을 만들도록 하였다.

• 전자공학회논문지CI
• /
• 제49권3호
• /
• pp.8-14
• /
• 2012

최근 3D TV나 영화, 증강현실과 같은 대용량 고화질의 영상 응용분야가 확산됨에 따라 빠른속도로 영상을 처리하는 것이 요구되고 있다. 여러개의 프로세서로 구성되어 병렬처리 성능을 극대화 시킬 수 있는 SIMD구조의 컴퓨터는 다양하고 많은 양의 데이터들을 처리하는 것을 가속화한다. 다중접근기억장치인 MAMS는 여러개의 PE와 고성능 SIMD 구조에 최적화된 시스템으로 MAMS는 메모리 모듈을 $M{\times}N$의 2-D array 개념을 적용하여 X, Y 좌표 및 임의의 간격으로 pq개의 데이터 각각에 수평, 수직, 대각선, 역대각선, 블록의 다양한 방식으로 충돌없이 접근하며, 이 메모리모듈(MM)의 개수 m은 pq 개수보다 큰 소수이다. MAMS-PP4는 4개의 PE와 5개의 MM로 구성되어 기존에 구현된 바 있다. 이 논문에서는 MAMS-PP4의 확장으로 16개의 PE와 17개의 MM으로 구성된 MAMS-PP16에 대한 영상처리 알고리즘의 구현과 그에 따른 성능평가에 대해 소개한다. MAMS-PP16의 인스트럭션 포맷은 64비트로 확장되어 새로 설계 되었으며 특정 어플리케이션의 추가와 새로운 인스트럭션이 포함되어 있다. 본 논문에서는 구현된 알고리즘이 수행될 수 있도록 MAMS-PP16의 시뮬레이터를 개발하였다. 이 시뮬레이터를 통해 구현된 영상처리 알고리즘을 수행함으로서 MAMS-PP16의 성능이 향상되었음을 확인하였다. 영상처리 알고리즘 중 피라미드 기법을 적용하여 수행한 결과, 캐시를 사용하는 Serial processor에서는 랜덤한 응답인 반면, 캐시를 사용하지 않는 MAMS-PP16에서 일정한 응답을 확인하였다.

• International Journal of Automotive Technology
• /
• 제6권1호
• /
• pp.53-63
• /
• 2005

We propose a fuzzy neural network (FNN) theory capable of deciding the quality of a road image prior to extracting lane-related information. The accuracy of lane-related information obtained by image processing depends on the quality of the raw images, which can be classified as good or bad according to how visible the lane marks on the images are. Enhancing the accuracy of the information by an image-processing algorithm is limited due to noise corruption which makes image processing difficult. The FNN, on the other hand, decides whether road images are good or bad with respect to the degree of noise corruption. A cumulative distribution function (CDF), a function of edge histogram, is utilized to extract input parameters from the FNN according to the fact that the shape of the CDF is deeply correlated to the road image quality. A suitability analysis shows that this deep correlation exists between the parameters and the image quality. The input pattern vector of the FNN consists of nine parameters in which eight parameters are from the CDF and one is from the intensity distribution of raw images. Experimental results showed that the proposed FNN system was quite successful. We carried out simulations with real images taken in various lighting and weather conditions, and obtained successful decision-making about $99\%$ of the time.

• International journal of advanced smart convergence
• /
• 제13권1호
• /
• pp.99-107
• /
• 2024

In AI image generation tools, most general users must use an effective prompt to craft queries or statements to elicit the desired response (image, result) from the AI model. But we are software engineers who focus on software processes. At the process's early stage, we use informal and formal requirement specifications. At this time, we adapt the natural language approach into requirement engineering and toon engineering. Most Generative AI tools do not produce the same image in the same query. The reason is that the same data asset is not used for the same query. To solve this problem, we intend to use informal requirement engineering and linguistics to create a toon. Therefore, we propose a sequence diagram and image generation mechanism by analyzing and applying key objects and attributes as an informal natural language requirement analysis. Identify morpheme and semantic roles by analyzing natural language through linguistic methods. Based on the analysis results, a sequence diagram and an image are generated through the diagram. We expect consistent image generation using the same image element asset through the proposed mechanism.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 1998년도 가을 학술발표대회 논문집(III)
• /
• pp.791-796
• /
• 1998

Air voids existed in hardened concrete have an important influence on concrete deterioration such as carbonation, freezing and thawing, and corrosion of embedded steel in concrete. Therefore it is very significant to investigate the pore structure of system(size, number and continuity of air voids) to solve the reason caused concrete deterioration. The purpose of this study is to develop the standard method of measuring air voids which affect properties in hardened concrete using image analyzing system. This paper presents the settlement of rapid and exact experimental method which extracts fine bubbles, calculates the number of air voids, and determines air-void distribution using image analyzing system with computer.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.831-832
• /
• 2008

This paper proposes the experimental results and analysis of face recognition on an conventional UMPC(Ultra Mobile Personal Computer). With face images acquired by the embedded camera of UMPC, we detected the facial region by using Adaboost face detector. The detected image was normalized into a $32{\times}32$ pixel sized image for face recognition. We performed face recognition based on PCA (Principal Component Analysis). As experimental results, the TER (Total Error Rate) of face recognition was 19.77%.

• 한국컴퓨터정보학회논문지
• /
• 제21권12호
• /
• pp.11-18
• /
• 2016

Magnetic resonance image (MRI) is widely used in brain research field and medical image. Especially, non-invasive brain activation acquired image technique, which is functional magnetic resonance image (fMRI) is used in brain study. In this study, we investigate brain activation occurred by LED light stimulation. For investigate of brain activation in experimental small animal, we used high magnetic field 9.4T MRI. Experimental small animal is Balb/c mouse, method of fMRI is using echo planar image (EPI). EPI method spend more less time than any other MRI method. For this reason, however, EPI data has low contrast. Due to the low contrast, image pre-processing is very hard and inaccuracy. In this study, we planned the study protocol, which is called block design in fMRI research field. The block designed has 8 LED light stimulation session and 8 rest session. All block is consist of 6 EPI images and acquired 1 slice of EPI image is 16 second. During the light session, we occurred LED light stimulation for 1 minutes 36 seconds. During the rest session, we do not occurred light stimulation and remain the light off state for 1 minutes 36 seconds. This session repeat the all over the EPI scan time, so the total spend time of EPI scan has almost 26 minutes. After acquired EPI data, we performed the analysis of this image data. In this study, we analysis of EPI data using statistical parametric map (SPM) software and performed image pre-processing such as realignment, co-registration, normalization, smoothing of EPI data. The pre-processing of fMRI data have to segmented using this software. However this method has 3 different method which is Gaussian nonparametric, warped modulate, and tissue probability map. In this study we performed the this 3 different method and compared how they can change the result of fMRI analysis results. The result of this study show that LED light stimulation was activate superior colliculus region in mouse brain. And the most higher activated value of segmentation method was using tissue probability map. this study may help to improve brain activation study using EPI and SPM analysis.

• 한국컴퓨터정보학회논문지
• /
• 제13권1호
• /
• pp.193-202
• /
• 2008

본 논문에서는 이미지(image) 합성을 하되 일반적인 환경이 아닌 바다. 호수 등을 포함하고 있는 영상에 다른 하나의 객체를 합성시키기 위한 물결 영상 기반 디지털 이미지 합성 프로세스를 제안한다. 즉 타겟(target) 이미지가 일반적 환경이 아닌 물결을 묘사한 영상인 경우 다른 객체 이미지를 합성시켜 타겟 이미지의 물결에 비춰진 객체의 모습이나 물 안에 있는 객체의 모습을 묘사하며 이를 위한 합성 알고리즘을 제안한다. 물결 부분에 이미지를 합성하기 위해 먼저 Shape-from-shading 기법을 사용하여 2차원 물결영상으로부터 3차원 정보를 추출하여 그 형상을 복원한다. 그리고 추출된 노말 정보를 적용하여 물결에 합성 될 영역을 알맞게 변형시킨다. 마지막으로 합성할 영역을 타겟 이미지의 물결에 옮겨놓는 합성과정을 수행한다.