• 대한원격탐사학회지
• /
• 제25권3호
• /
• pp.295-309
• /
• 2009

In this study, an iterative maximum a posteriori (MAP) approach using a Bayesian model of Markovrandom field (MRF) was proposed for despeckling images that contains speckle. Image process is assumed to combine the random fields associated with the observed intensity process and the image texture process respectively. The objective measure for determining the optimal restoration of this "double compound stochastic" image process is based on Bayes' theorem, and the MAP estimation employs the Point-Jacobian iteration to obtain the optimal solution. In the proposed algorithm, MRF is used to quantify the spatial interaction probabilistically, that is, to provide a type of prior information on the image texture and the neighbor window of any size is defined for contextual information on a local region. However, the window of a certain size would result in using wrong information for the estimation from adjacent regions with different characteristics at the pixels close to or on boundary. To overcome this problem, the new method is designed to use less information from more distant neighbors as the pixel is closer to boundary. It can reduce the possibility to involve the pixel values of adjacent region with different characteristics. The proximity to boundary is estimated using a non-uniformity measurement based on standard deviation of local region. The new scheme has been extensively evaluated using simulation data, and the experimental results show a considerable improvement in despeckling the images that contain speckle.

• 대한원격탐사학회지
• /
• 제25권5호
• /
• pp.455-464
• /
• 2009

Lee(2009)에서 영상 강도를 위해서 lognormal 확률 모형과 영상 texture를 위해서 Markov random field(MRF)에 기반하는 Bayesian 모형을 사용하는 boundary-adaptive despeckling 방법을 제안하였다. 이 방법은 speckle 제거 영상의 최대 사후(maximum a posteriori: MAP) 추정치를 구하기 위해서 Point-Jacobian iteration을 이용한다 인접하고 있는 다른 특성의 지역에 위치한 화소의 값을 사용하는 가능성을 줄이기 위해 Boundary-adaptive algorithm은 경계에 가까울 수록 멀리 떨어진 이웃 화소로부터 정보를 덜 수집하도록 고안된다. 이러한 boundary-adaptive 방법은 전반적으로 simulation 자료를 사용하여 Lee(2009)에서 평가되었고 그리고 제안된 방법의 효험을 증명하였다. 본 연구는 Lee(2009)의 확장 연구로 MAP 추정치를 구하기 반복 algorithm의 계산 효율성을 증가 시키고 noise 제거와 함께 분류를 수행하는 수정 algorithm을 제안한다. Simulation 자료를 사용한 실험을 통해서 boundary-adaption이 분류 오류를 줄여줄 뿐 아니라 더욱 명확한 경계선을 보여준다는 것을 알 수 있다. 또한 영종도 서해안에서 관측된 고해상도 Terra-SAR data에 적용한 결과는 boundary-adaption은 SAR 활용에서 분석의 정확성을 개선 시킬 수 있다는 것을 암시한다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 Proceedings of ISRS 2007
• /
• pp.270-273
• /
• 2007

In this paper, a SAR-despeck1ing approach of adaptive iteration based a Bayesian model using the lognormal distribution for image intensity and a Gibbs random field (GRF) for image texture is proposed for noise removal of the images that are corrupted by multiplicative speckle noise. When the image intensity is logarithmically transformed, the speckle noise is approximately Gaussian additive noise, and it tends to a normal probability much faster than the intensity distribution. The MRF is incorporated into digital image analysis by viewing pixel types as states of molecules in a lattice-like physical system. The iterative approach based on MRF is very effective for the inner areas of regions in the observed scene, but may result in yielding false reconstruction around the boundaries due to using wrong information of adjacent regions with different characteristics. The proposed method suggests an adaptive approach using variable parameters depending on the location of reconstructed area, that is, how near to the boundary. The proximity of boundary is estimated by the statistics based on edge value, standard deviation, entropy, and the 4th moment of intensity distribution.

• 대한원격탐사학회지
• /
• 제23권1호
• /
• pp.33-42
• /
• 2007

In this paper, an iterative MAP approach using a Bayesian model based on the lognormal distribution for image intensity and a GRF for image texture is proposed for despeckling the SAR images that are corrupted by multiplicative speckle noise. When the image intensity is logarithmically transformed, the speckle noise is approximately Gaussian additive noise, and it tends to a normal probability much faster than the intensity distribution. MRFs have been used to model spatially correlated and signal-dependent phenomena for SAR speckled images. The MRF is incorporated into digital image analysis by viewing pixel types as slates of molecules in a lattice-like physical system defined on a GRF Because of the MRF-SRF equivalence, the assignment of an energy function to the physical system determines its Gibbs measure, which is used to model molecular interactions. The proposed Point-Jacobian Iterative MAP estimation method was first evaluated using simulation data generated by the Monte Carlo method. The methodology was then applied to data acquired by the ESA's ERS satellite on Nonsan area of Korean Peninsula. In the extensive experiments of this study, The proposed method demonstrated the capability to relax speckle noise and estimate noise-free intensity.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2010년도 춘계학술발표대회
• /
• pp.447-450
• /
• 2010

하모닉 초음파 영상은 일반 초음파 영상에 비해 조직 간의 영상 대조도와 해상도를 향상 시키고, 경계가 보다 명확하기 때문에 초음파 영상 진단 분야에서 각광받고 있다. 하지만 초음파 영상이 포함하고 있는 스펙클 잡음 (speckle noise)에 의한 화질 저하는 하모닉 초음파 영상에서도 여전히 문제가 되고 있다. 이러한 스펙클 잡음을 제거하기 위해 많은 스펙클 제거 (despeckling) 방법들이 연구되었으며, 대부분의 방법들이 영상의 시각적 개선에 초점을 두고 있다. 이러한 접근 방법은 잡음개선정도와 영상의 정보 손실의 상반 관계 (trade off)를 갖는다. 한편 병변 분할은 이런 잡음 제거 방법에 따라 다른 분할 성능을 보이게 된다. 따라서 정확한 병변 분할을 위해서는, 스펙클 제거 방법에 따른 병변 분할 성능을 비교하고, 그 결과를 토대로 병변 분할에 효과적인 스펙클 제거 방법에 대한 연구가 필요하다. 본 논문에서는 유방 하모닉 초음파 영상에서 다양한 스펙클 제거 방법을 사용하여 각각의 필터가 병변 분할 성능에 미치는 영향을 비교해 보았으며, 실험 결과를 바탕으로 유방 병변 분할에 효과적인 전처리 역할을 수행하는 필터에 대해 분석해 보았다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 춘계학술대회 논문집
• /
• pp.126-129
• /
• 2007

In this paper, an iterative MAP approach using a Bayesian model based on the lognormal distribution for image intensity and a GRF for image texture is proposed for despeckling the SAR images that are corrupted by multiplicative speckle noise. When the image intensity is logarithmically transformed, the speckle noise is approximately Gaussian additive noise, and it tends to a normal probability much faster than the intensity distribution. The MRF is incorporated into digital image analysis by viewing pixel type s as states of molecules in a lattice-like physical system defined on a GRF. Because of the MRFGRF equivalence, the assignment of an energy function to the physical system determines its Gibbs measure, which is used to model molecular mteractions. The proposed adaptive iterative method was evaluated using simulation data generated by the Monte Carlo method. In the extensive experiments of this study, the proposed method demonstrated the capability to relax speckle noise and estimate noise-free intensity.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2017년도 추계학술대회
• /
• pp.66-69
• /
• 2017

본 논문에서는 깊은 합성 곱 신경망 (Deep Convolutional Neural Network) 를 이용해서 SAR (Synthetic Aperture Radar) 영상의 반전 잡음 (speckle noise) 성분을 제거하는 기법을 제안하고자 한다. Deep Convolutional Neural Network는 이미지의 데이터 특성에 적합한 딥 러닝 방법이고, 이는 SAR 위성영상의 반전 잡음 제거에 사용해도 효과적이다. 반전 잡음 필터 모델 추정을 위한 학습은 임의로 반전 잡음을 합성한 트레이닝 이미지들과 원본 트레이닝 이미지들을 이용한 회귀모델을 통해 진행된다. 학습을 통해 얻은 반전 잡음 필터는 기존 알고리즘에 비해 우수한 외곽선 보존 성능을 나타냄을 확인하였다.

• 대한원격탐사학회지
• /
• 제23권5호
• /
• pp.455-464
• /
• 2007

Lee(2007) suggested the Point-Jacobian iteration MAP estimation(PJIMAP) for noise removal of the images that are corrupted by multiplicative speckle noise. It is to find a MAP estimation of noisy-free imagery based on a Bayesian model using the lognormal distribution for image intensity and an MRF for image texture. When the image intensity is logarithmically transformed, the speckle noise is approximately Gaussian additive noise, and it tends to a normal probability much faster than the intensity distribution. The MRF is incorporated into digital image analysis by viewing pixel types as states of molecules in a lattice-like physical system. In this study, the MAP estimation is computed by the Point-Jacobian iteration using adaptive parameters. At each iteration, the parameters related to the Bayesian model are adaptively estimated using the updated information. The results of the proposed scheme were compared to them of PJIMAP with SAR simulation data generated by the Monte Carlo method. The experiments demonstrated an improvement in relaxing speckle noise and estimating noise-free intensity by using the adaptive parameters for the Ponit-Jacobian iteration.