A Maximum Likelihood Approach for Image Registration Using Control Point And Intensity

Li, W.; Leung, Henry

doi:10.1109/tip.2004.828435

Cited by 63 publications

(26 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To augment the performance, Maximum Likelihood (ML) approaches evolved in the research works. Li et al [19] combined Control Point (CP) with intensity measures for enhanced ML registration method. The EML registration method maximized the likelihood function for registration parameters estimation.…”

Section: Related Workmentioning

confidence: 99%

A Hybrid Particle Swarm Optimization with Affine Transformation Approach for Cloud Free Multi-Temporal Image Registration

Prabu

V.S

2016

ELCVIA

View full text Add to dashboard Cite

Image Registration (IR) is the process of transformation of different data into the coordinate system and provides the geometric alignment of two images used in the computer vision, medical imaging and remote sensing applications. An image registration is an important stage in multi-temporal image processing since, the recovery of information from cloud shadow is difficult. Traditionally, the Demons, Combined Registration and Segmentation (CRS) approach, Markov Random Field (MRF) and Mutual Information (MI) based approaches offers more computational complexity, minimum edge preservation measure (QAB/F) during image registration process. To maximize the quality of edge preservation measure and MI with minimum computational time, this paper proposes hybrid Particle Swarm Optimization (PSO)-Affine Transformation (AT) technique for an image registration. An enhanced registration process and the cloud removal technique are proposed for quality improvement of an image. Initially, Gaussian filtering in the preprocessing stage removes the noises present in an image. The proposed PSO extracts the matching points between the reference image and target image in the multitemporal image dataset. Then, the AT on extracted matching points provides the specific feature points from main features. Finally, the Relevance Vector Machine (RVM) classification forms the cluster of specific feature points. The extracted feature points from PSO-AT maximize the quality of edge preservation and MI with efficient cloud removal. The comparative analysis with the traditional methods of Control Point -Least Square (CP-LS), MultiFocus Image Fusion (MFIF) and Discrete Wavelet Transform (DWT) on the parameters of QAB/F and MI shows the effectiveness of proposed PSO-AT.

show abstract

Section: Related Workmentioning

confidence: 99%

A Hybrid Particle Swarm Optimization with Affine Transformation Approach for Cloud Free Multi-Temporal Image Registration

Prabu

V.S

2016

ELCVIA

View full text Add to dashboard Cite

show abstract

“…Methods based on pixel intensities [1]- [6]: In these methods, the similarity between pixel intensities is used to determine the alignment between two images. Similarity measures used in these algorithms include maximum likelihood [1] and mutual information [2].…”

Section: )mentioning

confidence: 99%

“…Similarity measures used in these algorithms include maximum likelihood [1] and mutual information [2]. 2) Methods based on frequency-domain characteristics [7]- [9]: Such algorithms attempt to find an optimal alignment match between two images based on characteristics in the frequency domain.…”

Section: )mentioning

confidence: 99%

ARRSI: Automatic Registration of Remote-Sensing Images

Wong

Clausi

2007

IEEE Trans. Geosci. Remote Sensing

213

129

View full text Add to dashboard Cite

Abstract-This paper presents the Automatic Registration of Remote-Sensing Images (ARRSI); an automatic registration system built to register satellite and aerial remotely sensed images. The system is designed specifically to address the problems associated with the registration of remotely sensed images obtained at different times and/or from different sensors. The ARRSI system is capable of handling remotely sensed images geometrically distorted by various transformations such as translation, rotation, and shear. Global and local contrast issues associated with remotely sensed images are addressed in ARRSI using control-point detection and matching processes based on a phasecongruency model. Intensity-difference issues associated with multimodal registration of remotely sensed images are addressed in ARRSI through the use of features that are invariant to intensity mappings during the control-point matching process. An adaptive control-point matching scheme is employed in ARRSI to reduce the performance issues associated with the registration of large remotely sensed images. Finally, a variation on the Random Sample and Consensus algorithm called Maximum Distance Sample Consensus is introduced in ARRSI to improve the accuracy of the transformation model between two remotely sensed images while minimizing computational overhead. The ARRSI system has been tested using various satellite and aerial remotely sensed images and evaluated based on its accuracy and computational performance. The results indicate that the registration accuracy of ARRSI is comparable to that produced by a human expert and improvement over the baseline and multimodal sum of squared differences registration techniques tested.

show abstract

“…Intensity-based registration methods don't require extracting features in images and attempt to find directly pixel correspondences between two images by determining the similarity between two pixel points according to feature information from neighboring pixel points. Some common similarity metrics used in intensity-based methods include maximum likelihood [4], correlation [5,6], and mutual information (MI) [7][8][9]. Of particular interest in recent years are techniques based on mutual information, which attempt to match data points by finding the mutual dependence between the images.…”

Section: Introductionmentioning

confidence: 99%

A robust feature-based registration method of multimodal image using phase congruency and coherent point drift

Xia

Zhao

Liu

2013

MIPPR 2013: Pattern Recognition and Computer Vision

View full text Add to dashboard Cite

This paper presents a new feature matching algorithm for nonrigid multimodal image registration. The proposed algorithm first constructs phase congruency representations (PCR) of images to be registered. Then scale invariant feature transform (SIFT) method is applied to capture significant feature points from PCR. Subsequently, the putative matching is obtained by the nearest neighbour matching in the SIFT descriptor space. The SIFT descriptor is then integrated into Coherent Point Drift (CPD) method so that the appropriate matching of two point sets is solved by combining appearance with distance properties between putative match candidates. Finally, the transformation estimated by matching the point sets is applied to registration of original images. The results show that the proposed algorithm increases the correct rate of matching and is well suited for multi-modal image registration.

show abstract

A Maximum Likelihood Approach for Image Registration Using Control Point And Intensity

Cited by 63 publications

References 20 publications

A Hybrid Particle Swarm Optimization with Affine Transformation Approach for Cloud Free Multi-Temporal Image Registration

A Hybrid Particle Swarm Optimization with Affine Transformation Approach for Cloud Free Multi-Temporal Image Registration

ARRSI: Automatic Registration of Remote-Sensing Images

A robust feature-based registration method of multimodal image using phase congruency and coherent point drift

Contact Info

Product

Resources

About