Image registration using Markov random coefficient and geometric transformation fields

Arce-Santana, Edgar R.; Alba, Alfonso

doi:10.1016/j.patcog.2008.11.033

Cited by 25 publications

(18 citation statements)

References 25 publications

(10 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image geometrical deformation has many different ways of description [6,[22][23]. Combination of rotation, scaling and translation is the most common one and it has five parameters:…”

Section: Transformation Parameters Estimationmentioning

confidence: 99%

Rigid Point Feature Registration for MRI Brain Images based on Fuzzy Transform

Al-Azzawi¹

2013

IJCA

View full text Add to dashboard Cite

Radiological images are gradually more being used in healthcare and medical research. There is, accordingly, widespread interest in accurately relating information in the different images for diagnosis, treatment and basic science. In this paper we formulate feature registration problems by using F-transform (Fuzzy-Transform) to extract the salient edges and extracted control points (CP) of medical Images. The MRI brain Images were first decomposed using F-transform, then Edge and CP were extracted from F-transform error function, and some proposed rules. After edge and CP extraction, mutual information (MI) was adopted for the registration of feature points, and translation parameters are calculated by using particle swarm optimization (PSO). We implement experiments to evaluate the performance of the FTransform and MI similarity measures for 2-D/3-D rigid point feature registration. The experimental results showed that the proposed method produces totally accurate performance for rigid point feature registration for MRI brain images.

show abstract

“…Image geometrical deformation has many different ways of description [6,[22][23]. Combination of rotation, scaling and translation is the most common one and it has five parameters:…”

Section: Transformation Parameters Estimationmentioning

confidence: 99%

Rigid Point Feature Registration for MRI Brain Images based on Fuzzy Transform

Al-Azzawi¹

2013

IJCA

View full text Add to dashboard Cite

show abstract

“…The iterations in an optimization are 200 times for Hessian matrix in an inner loop. The parameters for equation (16) are: ı 1 =ı 2 =ı=1 and Ȝ=1 in the first two experiments. This process is repeated for four times in an outer loop.…”

Section: Implementationsmentioning

confidence: 99%

“…Moreover, this method is less robust due to that the gradient of MI is sensitive to noise. The MRF model theory has been applied in the field of image analysis such as image segmentation, image restoration in recent decades and become very popular recently in the field of image registration [15], [16], [17]. This method models a deformation field with an energy function to be ___________________________________ 978-1-4673-2197-6/12/$31.00 ©2012 IEEE ICSP2012 Proceedings minimized.…”

Section: Introductionmentioning

confidence: 99%

“…The multiresolution method is often taken account for large deformations and produce better results on a higher resolution level. Santana et al [16] proposed a method to achieve a global/local image registration by constructing an energy function combined with intensity deformation field and geometric deformation field. A probabilistic framework is determined to perform the registration process.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Markov Random Field model based multimodal medical image registration

Shi

Yuan

Zhang

et al. 2012

2012 IEEE 11th International Conference on Signal Processing

View full text Add to dashboard Cite

A new method based on Markov Random Field (MRF) model to register multimodal medical image is proposed. First, a multimodality intensity transformation or mapping function, which is estimated from the marginal peaks in a joint histogram of two images, is introduced. The transformation function is applied to one image to create a virtual image that hat has similar intensity correspondence characteristics to the other one, of a different modality. Then, using the original two image matrices and the transferred two image matrices, we formulate a new MRF energy function comprising a data term which is similar to a distance function and a smoothness term that penalizes local deviations. In optimization step, a quasi-Newton optimization algorithm is used to find the minimal value of the MRF energy function. The test results show that the proposed algorithm has better performance in both accuracy and robustness to noise, on a series of 2D MRI and CT images.

show abstract

“…Image registration is a well studied problem [20][21][22][23][24]. This problem can be described as finding an optimal spatial transformation T Ã for matching the transformed reference image to the target image.…”

Section: Intensity Based Non-rigid Registrationmentioning

confidence: 99%