• 전기학회논문지P
• /
• 제62권2호
• /
• pp.90-94
• /
• 2013

In this paper, we propose a new algorithm to improve the contrast ratio, to preserve information of bright regions and to maintain the color of backlight image that appears with a great relative contrast. Backlight images of the natural environment have characteristics for difference of local brightness; the overall image contrast improvement is not easy. To improve the contrast of the backlight images, MSR (Multi-Scale Retinex) algorithm using the existing multi-scale Gaussian filter is applied. However, existing multi-scale Gaussian filter involves color distortion and information loss of bright regions due to excessive contrast enhancement and noise because of the brightness improvement of dark regions. Moreover, it also increases computational complexity due to the use of multi-scale Gaussian filter. In order to solve these problems, a linear MSR is performed that reduces the amount of computation from the HSV color space preventing the color distortion and information loss due to excessive contrast enhancement. It can also remove the noise of the dark regions which is occurred due to the improved contrast through edge preserving filter. Through experimental evaluation of the average color difference comparison of CIELAB color space and the visual assessment, we have confirmed excellent performance of the proposed algorithm compared to conventional MSR algorithm.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2002년도 추계학술대회 논문집
• /
• pp.111-116
• /
• 2002

In this study, a vision system with image processing method have been introduced to find the deflection of brush filaments. Several preprocessing methods including Scale-space filter with various threshold levels have been applied. In order to evaluate the deflection of the filaments, deformed filaments have been assessed using the processed profile

• 대한의용생체공학회:의공학회지
• /
• 제36권1호
• /
• pp.22-30
• /
• 2015

Melanoma is originated from the melanocyte producing the melanin which determines the complexion, and it has the highest mortality among skin cancers. Acral lentiginous melanoma(ALM) arises from extremities such as hands, feet or fingernails. Since the appearance of ALM is different from melanoma on the body, conventional auto diagnosis systems for melanoma is inappropriate to detect ALM. Therefore, ALM is typically difficult to distinguish from general nevus, resulting in delayed diagnosis and bad prognosis. In this paper, we firstly introduce a determination method for ALM by dermatologists and propose a method to rotate dermoscopic images automatically as a pre-processing for facilitating the easy determination of ALM and to select the optimal value of the Gaussian differentiation filter parameter which is significant for precise pattern extraction using the scale space analysis. From experimental results, it is shown that there exists the consistency between empirical values of the Gaussian differential filter parameter and optimal values derived from the scale space analysis to distinguish nevus and ALM.

• 한국정보전자통신기술학회논문지
• /
• 제2권3호
• /
• pp.31-38
• /
• 2009

A process of identifying moving objects from data is typical task in many computer vision applications. In this paper, we propose a motion segmentation method that generally consists from background subtraction and foreground pixel segmentation. The Approximated Median Filter (AMF) was chosen to perform background modelling. To demonstrate the effectiveness of proposed approach, we tested it gray-scale video data as well as RGB color space.

• Journal of Positioning, Navigation, and Timing
• /
• 제11권2호
• /
• pp.71-81
• /
• 2022

In order for electro-optical tracking system (EOTS) to have accurate target coordinate, accurate navigation results are required. If an integrated navigation system is configured using an inertial measurement unit (IMU) of EOTS and the vehicle's navigation results, navigation results with high rate can be obtained. Due to the time-delay of the navigation results of the vehicle in the EOTS and scale factor errors of the EOTS IMU in high-speed and high dynamic operation of the vehicle, it is much more difficult to have accurate navigation results. In this paper, an integrated navigation system of EOTS which compensates time-delay and scale factor error is proposed. The proposed integrated navigation system consists of vehicle's navigation system which provides time-delayed navigation results, an EOTS IMU, an inertial navigation system (INS), an augmented Kalman filter and integration Kalman filter. The augmented Kalman filter outputs navigation results, in which the time-delay of the vehicle's navigation results is compensated. The integration Kalman filter estimates position, velocity, attitude error of the EOTS INS and accelerometer bias, accelerometer scale factor error, gyro bias and gyro scale factor error from the difference between the output of the augmented Kalman filter and the navigation result of the EOTS INS. In order to check performance of the proposed integrated navigation system, simulations for output data of a measurement generator and land vehicle experiments were performed. The performance evaluation results show that the proposed integrated navigation system provides more accurate navigation results.

• 한국통신학회논문지
• /
• 제29권1C호
• /
• pp.50-58
• /
• 2004

본 논문은 수정된 이방성 확산 펄터를 이용한 영상 개선 방법을 제안하였다. 이를 위하여 최소 신뢰 스케일을 기반으로 하는 센서 잡음 추정과 스케일 스페이스 방법을 도입하였다. 이때 이방성 필터는 구해진 임계값 함수와 국부 기울기에 의해 수정되었다. 모의 실험을 통해 제안한 방법이 평탄 영역에서의 잡음을 거의 증폭시키지 않으면서도 뛰어난 에지 향상을 보임을 증명할 수 있었다.

• 대한전자공학회논문지
• /
• 제25권12호
• /
• pp.1548-1558
• /
• 1988

In this paper, a segmentation algorithm for color images based on the scale-space filter and the Fuzzy c-means (FCM) techniques is proposed. The methodology uses a coarse-fine concept to reduce the computational burden required for the FCM. The coarse segmentation attempts to segment coarsely using a thresholding technique, while a fine segmentation assigns the unclassified pixels by a coarse segmentation to the closest class using the FCM. Attempts also have been made to compare the performance of the proposed algorithm with other algorithms such as Ohlander's, Rosenfeld's, and Bezdek's. Intensive computer simulations has been done and the results are discussed in the paper. The simulation results indicate that the proposed algorithm produces the most accurate segmentation on the O-K-S color coordinate while requiring a reasonable amount of computational effort.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2014년도 추계학술발표대회
• /
• pp.520-522
• /
• 2014

Due to the availability of easy-to-use and powerful image editing tools, the authentication of digital images cannot be taken for granted and it gives rise to non-intrusive forgery detection problem because all imaging devices do not embed watermark. Forgery detection plays an important role in this case. In this paper, an effective framework for passive-blind method for copy-move image forgery detection is proposed, based on Gabor filter which is robust to illumination, rotation invariant, robust to scale. For the detection, the suspicious image is selected and Gabor wavelet is applied from whole scale space and whole direction space. We will extract the mean and the standard deviation as the texture features and feature vectors. Finally, a distance is calculated between two textures feature vectors to determine the forgery, and the decision will be made based on that result.

• Nuclear Engineering and Technology
• /
• 제50권5호
• /
• pp.698-708
• /
• 2018

This article introduces a methodology of designing a wavelet operator suitable for multiscale modeling. The operator matrix transforms states of a multivariable system onto projection space. In addition, it imposes a specific structure on the system matrix in a multiscale environment. To be specific, the article deals with a diagonalizing transform that is useful for decoupled control of a system. It establishes that there exists a definite relationship between the model in the measurement space and that in the projection space. Methodology for deriving the multirate perfect reconstruction filter bank, associated with the wavelet operator, is presented. The efficacy of the proposed technique is demonstrated by modeling the point kinetics nuclear reactor. The outcome of the multiscale modeling approach is compared with that in the single-scale approach to bring out the advantage of the proposed method.

• 한국항공우주학회지
• /
• 제44권5호
• /
• pp.407-415
• /
• 2016

본 논문에서는 최적의 항공 영상 융합을 위하여 적응 가이디드 필터 기반 알고리즘을 제안하였다. 제안한 적응 가이디드 필터는 가이디드 필터 설계 요소 중에서 정규화 파라미터 값을 입력된 영상 특성에 따라서 조절하고 PSNR (peak signal to noise ratio)을 미리 정해둔 값으로 유지한다. 제안한 방법은 입력 영상의 특성에 관계없이 미리 정한 PSNR을 유지하는 범위 내에서 잡음을 제거하므로 최적의 영상 융합 성능의 결과를 가져올 수 있다. 필터 성능은 시뮬레이션을 통해 검증하였고, 기존에 많이 사용되고 있는 영상융합 품질 파라미터를 이용하여 분석하였다.