Robust Huber similarity measure for image registration in the presence of spatially-varying intensity distortion

Ghaffari, Aboozar; Fatemizadeh, Emad

doi:10.1016/j.sigpro.2014.10.022

Cited by 16 publications

(4 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In regard to the nature of the spatially-varying noise, our simulation of the noise in the MR images is based on additive Gaussian noise. This model follows a strong body of previous studies [23][24][25][26]. However, the intensity non-uniformity in MRI could be also modeled via multiplication by a non-uniform distribution.…”

Section: Discussion and Future Workmentioning

confidence: 99%

See 1 more Smart Citation

Robust Registration of Medical Images in the Presence of Spatially-Varying Noise

2022

Self Cite

View full text Add to dashboard Cite

Spatially-varying intensity noise is a common source of distortion in medical images and is often associated with reduced accuracy in medical image registration. In this paper, we propose two multi-resolution image registration algorithms based on Empirical Mode Decomposition (EMD) that are robust against additive spatially-varying noise. EMD is a multi-resolution tool that decomposes a signal into several principle patterns and residual components. Our first proposed algorithm (LR-EMD) is based on the registration of EMD feature maps from both floating and reference images in various resolutions. In the second algorithm (AFR-EMD), we first extract a single average feature map based on EMD and then use a simple hierarchical multi-resolution algorithm to register the average feature maps. We then showcase the superior performance of both algorithms in the registration of brain MRIs as well as retina images. For the registration of brain MR images, using mutual information as the similarity measure, both AFR-EMD and LR-EMD achieve a lower error rate in intensity (42% and 32%, respectively) and lower error rate in transformation (52% and 41%, respectively) compared to intensity-based hierarchical registration. Our results suggest that the two proposed algorithms offer robust registration solutions in the presence of spatially-varying noise.

show abstract

Section: Discussion and Future Workmentioning

confidence: 99%

“…One type is focused on defining robust similarity measures. Residual complexity (RC) [22], rank-induced [23,24] and sparsity-based [25,26] similarity measures are some examples. The second type of algorithms is based on simply reducing the noise effect and then registration of the denoised images [27,28].…”

Section: Introductionmentioning

confidence: 99%

Robust Registration of Medical Images in the Presence of Spatially-Varying Noise

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…An important core of signal processing is signal decomposition representing a signal vector using a linear combination of some basis functions , that is , where , and . Recently, the sparsity assumption on signal and image representation ( ) has been used for various applications such as image denoising 47 , blind source separation 48 , compressed sensing 24 , pattern recognition 49 , and image registration 50 , 51 . It is assumed that the signal is k-sparse, which means it has at most k non-zero entries in a learned dictionary or a transform domain such as discrete cosine transform or wavelet.…”

Section: Preliminariesmentioning

confidence: 99%

Image compression-encryption method based on two-dimensional sparse recovery and chaotic system

Ghaffari

2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

In this paper, we propose an image compression-encryption method based on two-dimensional (2D) sparse representation and chaotic system. In the first step of this method, the input image is extended in a transform domain to obtain a sparse representation. To achieve better performance of image compression by 2D sparse recovery, the sparse representation is scrambled via a chaotic confusion. This step helps the satisfaction of the uniqueness conditions for sparse recovery, and the security level of encryption is increased. Then, two orthogonal measurement matrices are generated using the chaotic time series. The singular value decomposition is used to compress the sparse scrambled representation in two dimensions. Finally, to reduce the correlation between adjacent pixels in the compressed matrix, and obtain a uniform distribution in the encrypted image, a compressed scrambling matrix based on chaotic confusion is used. Then, XOR operation is applied for final encryption. In the decryption process, to improve the compression efficiency, the total variation constraint is added to the 2D sparse recovery problem based on the smoothed norm. The simulation results demonstrate the satisfying performance of the proposed method for different compression ratios. Security analysis describes the effectiveness of the proposed encryption approach.

show abstract

“…Reviewing pattern recognition techniques shows that similarity measure can be used as a tool for comparing different objects and identifying similar ones [17]. This technique has been applied in different areas such as image guided surgery [18], computer vision [19] and remote sensing [20].…”

Section: Introductionmentioning

confidence: 99%

Application of Huber-similarity measure on PD detection

Parvin¹

2019

Serb J Electr Eng

View full text Add to dashboard Cite

Extraction of Partial Discharges (PD) is a key step in diagnosis and evaluation of the power system equipment condition. In field testing, besides high frequency noise and disturbance, Power Frequency (P.F.) harmonics also couple with PD measurement sensors. In order to deal with both types of noises and disturbances, in this paper, a new PD signal extraction algorithm is presented, which is based on a combination of Huber Function, Discrete Cosine Transform (DCT), 1  and 2  norms. This new method, which is introduced as Huber Similarity Measure for Partial Discharge (HSMPD), was evaluated through experimental laboratory constructed PD models. Results show this proposed algorithm successfully extracted PD signals in the presence of baseline and high frequency noises and disturbances. HSMPD can be employed as a backbone in intelligent diagnosis systems for improving the accuracy of PD condition monitoring equipment.

show abstract

Robust Huber similarity measure for image registration in the presence of spatially-varying intensity distortion

Cited by 16 publications

References 36 publications

Robust Registration of Medical Images in the Presence of Spatially-Varying Noise

Robust Registration of Medical Images in the Presence of Spatially-Varying Noise

Image compression-encryption method based on two-dimensional sparse recovery and chaotic system

Application of Huber-similarity measure on PD detection

Contact Info

Product

Resources

About