Feature Similarity Index Research Articles

A novel adaptive image zooming scheme via weighted least-squares estimation

A critical issue in image interpolation is preserving edge detail and texture information in images when zooming. In this paper, we propose a novel adaptive image zooming algorithm using weighted least-square estimation that can achieve arbitrary integer-ratio zoom (WLS-AIZ) For a given zooming ratio n, every pixel in a low-resolution (LR) image is associated with an n × n block of high-resolution (HR) pixels in the HR image. In WLS-AIZ, the LR image is interpolated using the bilinear method in advance. Model parameters of every n×n block are worked out through weighted least-square estimation. Subsequently, each pixel in the n × n block is substituted by a combination of its eight neighboring HR pixels using estimated parameters. Finally, a refinement strategy is adopted to obtain the ultimate HR pixel values. The proposed algorithm has significant adaptability to local image structure. Extensive experiments comparing WLS-AIZ with other state of the art image zooming methods demonstrate the superiority of WLS-AIZ. In terms of peak signal to noise ratio (PSNR), structural similarity index (SSIM) and feature similarity index (FSIM), WLS-AIZ produces better results than all other image integer-ratio zoom algorithms.

A novel Zohair filter for deblurring computed tomography medical images

Deblurring computed tomography (CT) images has been an active research topic in recent years because of the wide variety of challenges it offers. Hence, a novel filter is proposed in this article unveiling a simple, efficient, and fast deblurring process that involves few parameters, low calculations and does not utilize the undesirable iterative property or introduce the common deblurring problems. The newly proposed filter is validated on both real and synthetic blurred CT images to provide a sufficient understanding about its performance. Moreover, proper comparisons are made with high-profile deblurring methods, in which the results are evaluated using three reliable quality metrics of feature similarity index (FSIM), structural similarity (SSIM), and visual information fidelity in pixel domain (VIFP). The intensive experiments and performance evaluations exhibited the efficiency of the proposed filter, in that it outperformed all the comparative methods.

FSITM: A Feature Similarity Index For Tone-Mapped Images

In this work, based on the local phase information of images, an objective index, called the feature similarity index for tone-mapped images (FSITM), is proposed. To evaluate a tone mapping operator (TMO), the proposed index compares the locally weighted mean phase angle map of an original high dynamic range (HDR) to that of its associated tone-mapped image calculated using the output of the TMO method. In experiments on two standard databases, it is shown that the proposed FSITM method outperforms the state-of-the-art index, the tone mapped quality index (TMQI). In addition, a higher performance is obtained by combining the FSITM and TMQI indices. The MATLAB source code of the proposed metric(s) is available at https://www.mathworks.com/matlabcentral/fileexchange/59814.

Deblurring Computed Tomography Medical Images Using a Novel Amended Landweber Algorithm.

In computed tomography (CT), blurring occurs due to different hardware or software errors and hides certain medical details that are present in an image. Image blur is difficult to avoid in many circumstances and can frequently ruin an image. For this, many methods have been developed to reduce the blurring artifact from CT images. The problems with these methods are the high implementation time, noise amplification and boundary artifacts. Hence, this article presents an amended version of the iterative Landweber algorithm to attain artifact-free boundaries and less noise amplification in a faster application time. In this study, both synthetic and real blurred CT images are used to validate the proposed method properly. Similarly, the quality of the processed synthetic images is measured using the feature similarity index, structural similarity and visual information fidelity in pixel domain metrics. Finally, the results obtained from intensive experiments and performance evaluations show the efficiency of the proposed algorithm, which has potential as a new approach in medical image processing.

Quality Assessment of Images Projected Using Multiple Projectors

Multiple projectors with partially overlapping regions can be used to project a seamless image on a large projection surface. With the advent of high-resolution photography, such systems are gaining popularity. Experts set up such projection systems by subjectively identifying the types of errors induced by the system in the projected images and rectifying them by optimizing (correcting) the parameters associated with the system. This requires substantial time and effort, thus making it difficult to set up such systems. Moreover, comparing the performance of different multi-projector display (MPD) systems becomes difficult because of the subjective nature of evaluation. In this work, we present a framework to quantitatively determine the quality of an MPD system and any image projected using such a system. We have divided the quality assessment into geometric and photometric qualities. For geometric quality assessment, we use Feature Similarity Index (FSIM) and distance-based Scale Invariant Feature Transform (SIFT). For photometric quality assessment, we propose to use a measure incorporating Spectral Angle Mapper (SAM), Intensity Magnitude Ratio (IMR) and Perceptual Color Difference (ΔE). We have tested the proposed framework and demonstrated that it provides an acceptable method for both quantitative evaluation of MPD systems and estimation of the perceptual quality of any image projected by them.

Enhancement of Underwater Images UsingWavelength Compensation Method

Most important source of distortion in underwater environs are Haze and Hue alteration. Haze is produced because of the effect of light scattering by particle present in the underwater environment. Hue alterations occur when light enter deeper in underwater. These two issues make the picture look darker and low luminosity.Haze removal and Hue altered enhancement is important for this kind of low visibility and low contrast underwater images. The existing Dark Channel Prior method effectively removes Haze but color change is not processed. In this paper underwater image enhancement is carried out in two steps. In the first step Haze in the underwater image is removed using dark channel prior. In the second step Hue alterations handled by wavelength compensation. Once depth map is derived, luminance of foreground and background inside the image can be separated and compared. To regulate the Hue alteration wavelength can be compensated using average RGB channels in the image. After computing the scale value of each RGB component, wavelength is compensated together with the average RGB and scale value of each channel in the image. Performance of the proposed method of wavelength compensated image is evaluated using the PSNR, Focus Measurement, Contrast Improvement Index, and Feature Similarity Index. Performance measurement of the wavelength compensation produces better enhancement results than existing method.

SU-E-J-98: Assessment of Deformable Image Registration Algorithms by Using Different Similarity Measures for the Registration Evaluation

Purpose: To evaluate deformable image registration algorithms used for 4DCT data sets registration. Furthermore, to validate several similarity measures applied on clinical 4DCT images as part of the evaluation. Methods: The capabilities of the registration algorithms — Deformable Multi Pass (DMP), Extended Deformable Multi Pass (EXDMP), structure guided deformable (SGD), and rigid — applied in the commercial software Velocity (Medical Solutions, Atlanta, GA) were evaluated by several different similarity measures applied on 4DCT images. Measures included the cross correlation (CC), root mean squared error (RMSE), relative dimensionless global error in synthesis (Erreur Relative Globale Adimensionelle de Synthese — ERGAS), image quality index (Q), structural similarity index (SSIM), feature similarity index (FSIM), gradient magnitude similarity deviation (GMSD), mutual information (MI), dice similarity coefficient (DSC), Tanimoto coefficient (TC), and specificity (S). Results: The analysis showed that for two of the registration methods (DMP and SGD), in 3 out of the 4 cases, the same registration results (the two deformed data sets were exactly the same) were obrained regardless of the phase that was used for registration. For the four cases done so far, only two similarity measures (RMSE, ERGAS) ranked rigid registration in the last place compared to the other methods. Another measure that indicated an inferior performance for the rigid registration was the MI, which ranked it in the 3rd place in front of EXDMP in only one of the cases studied. The EXDMP was ranked as the best performing algorithm by the different measures combined in 43%, DMP in 22%, SGD in 20% and RIGID in 15% of the cases considered. Conclusion: Root mean squared error, relative dimensionless global error in synthesis and mutual information appear to have an advantage over other similarity measures that are considered in the evaluation of the accuracy of deformable image registration.

Full-reference quality assessment of stereoscopic images by learning binocular receptive field properties.

Quality assessment of 3D images encounters more challenges than its 2D counterparts. Directly applying 2D image quality metrics is not the solution. In this paper, we propose a new full-reference quality assessment for stereoscopic images by learning binocular receptive field properties to be more in line with human visual perception. To be more specific, in the training phase, we learn a multiscale dictionary from the training database, so that the latent structure of images can be represented as a set of basis vectors. In the quality estimation phase, we compute sparse feature similarity index based on the estimated sparse coefficient vectors by considering their phase difference and amplitude difference, and compute global luminance similarity index by considering luminance changes. The final quality score is obtained by incorporating binocular combination based on sparse energy and sparse complexity. Experimental results on five public 3D image quality assessment databases demonstrate that in comparison with the most related existing methods, the devised algorithm achieves high consistency with subjective assessment.

An innovative technique for contrast enhancement of computed tomography images using normalized gamma-corrected contrast-limited adaptive histogram equalization

Abstract Image contrast is an essential visual feature that determines whether an image is of good quality. In computed tomography (CT), captured images tend to be low contrast, which is a prevalent artifact that reduces the image quality and hampers the process of extracting its useful information. A common tactic to process such artifact is by using histogram-based techniques. However, although these techniques may improve the contrast for different grayscale imaging applications, the results are mostly unacceptable for CT images due to the presentation of various faults, noise amplification, excess brightness, and imperfect contrast. Therefore, an ameliorated version of the contrast-limited adaptive histogram equalization (CLAHE) is introduced in this article to provide a good brightness with decent contrast for CT images. The novel modification to the aforesaid technique is done by adding an initial phase of a normalized gamma correction function that helps in adjusting the gamma of the processed image to avoid the common errors of the basic CLAHE of the excess brightness and imperfect contrast it produces. The newly developed technique is tested with synthetic and real-degraded low-contrast CT images, in which it highly contributed in producing better quality results. Moreover, a low intricacy technique for contrast enhancement is proposed, and its performance is also exhibited against various versions of histogram-based enhancement technique using three advanced image quality assessment metrics of Universal Image Quality Index (UIQI), Structural Similarity Index (SSIM), and Feature Similarity Index (FSIM). Finally, the proposed technique provided acceptable results with no visible artifacts and outperformed all the comparable techniques.

Deblurring computed tomography medical images using a novel amended Landweber algorithm.

In computed tomography (CT), blurring occurs due to different hardware or software errors, and hides certain medical details that are present in an image. Image blur is difficult to avoid in many circumstances and can frequently ruin an image. For this, many methods have been developed to reduce the blurring artifact from CT images. The problems with these methods are the high implementation time, noise amplification and boundary artifacts. Hence, this article presents an amended version of the iterative Landweber algorithm to attain artifact-free boundaries and less noise amplification in a faster application time. In this study, both synthetic and real blurred CT images are used to validate the proposed method properly. Similarly, the quality of the processed synthetic images is measured using the Feature Similarity Index (FSIM), Structural Similarity (SSIM) and Visual Information Fidelity in Pixel Domain (VIFP) metrics. Finally, the results obtained from intensive experiments and performance evaluations show the efficiency of the proposed algorithm, which has potential as a new approach in medical image processing.

Single‐frame image super‐resolution inspired by perceptual criteria

In this study, the authors consider the problem of image super-resolution (SR) in terms of the perceptual criteria. Existing SR methods treat the traditional mean-squared error (MSE) as an irreplaceable objective function. However, MSE has been widely criticised since it is inconsistent with visual perception of human beings. The perceptual criteria, including the structural similarity (SSIM) index and feature similarity (FSIM) index, have been reported to be more effective in assessing image quality. Therefore SSIM and FSIM are included for the SR task in this study. Specifically, the authors first propose to reform principal component analysis (PCA), which is named as visual perceptual PCA (VP-PCA), by adopting SSIM as the object function. Subsequently, to accomplish the SR task, the authors cluster the training data and perform VP-PCA on each cluster to calculate the coefficients. Finally, based on the principle of FSIM, the traditional SR results and the SR results using VP-PCA are combined to form our fused results. Experimental results are provided to show the superiority of the proposed method over several state-of-the-art methods in both quantitative and visual comparisons.

Natural image statistics based 3D reduced reference image quality assessment in contourlet domain

Designing a reliable and generic perceptual quality metric is a challenging issue in three-dimensional (3D) visual signal processing. In many practical 3D application scenarios, the original stereoscopic images (i.e., the reference image) cannot be fully accessed, leaving difficulties to quality assessment. To handle this problem, 3D reduced-reference image quality assessment (RRIQA) metrics have been investigated, which only extract small amount of information from the original stereoscopic images. In this paper, we propose a novel 3D RRIQA metric based on 3D natural image statistics in contourlet domain. In this metric, the Gaussian scale mixtures (GSM) model is employed to normalize the coefficients in the contourlet subband of luminance image and disparity map of the 3D images. After divisive normalization transform, we find that the marginal distribution of the coefficients is approximately Gaussian distributed. Based on these investigations, the standard derivations of the fitted Gaussian distribution are determined as the feature parameters in our metric for each contourlet subband. Then, the feature similarity index is employed to measure the 3D visual quality at the receiver side without accessing the reference stereoscopic images. Experimental results demonstrate that the proposed metric has good consistency with 3D subjective perception of human, and can be implemented in many end-to-end 3D video systems.

Perceptual image quality assessment by independent feature detector

The development of image processing technology has triggered the increasing demand for accurate methods of image quality assessment (IQA). Thus, creating reliable and accurate image quality metrics (IQMs) that are consistent with subjective human evaluation is an intense focus of research. Because the human visual system (HVS) is the ultimate receiver of images, modeling of the HVS has been regarded as the most suitable way to achieve perceptual quality predictions. In fact, independent component analysis (ICA) can provide a very good description for the receptive fields of neurons in the primary visual cortex which is the most important part of the HVS. Inspired by this fact, a novel independent feature similarity (IFS) index is proposed for full-reference IQA. Moreover, ICA can simulate the color-opponent mechanism of the HVS. Thus IFS can effectively predict the quality of an image with color distortion. Because IFS uses only a part of the reference image information, it can also be considered as a reduced-reference IQM. The proposed method is based on independent features that are acquired from a feature detector which is trained on samples of natural images by ICA. The computation of IFS consists of two components: feature component and luminance component. The feature component measures the structure and texture differences between two images, while the luminance component evaluates brightness distortions. Experimental results show that IFS has relatively low computational complexity and high correlation with subjective quality evaluation.

Uniformity analysis in nanocrystalline silver thin films using fuzzy inference system

An automatic and efficient technique to analyze the uniformity of nanoscale images using wavelets, feature similarity index measure (FSIM) and fuzzy inference system is reported. It has been successfully tested on scanning electron micrographs of nanocrystalline silver thin films. Thin films are prepared using on-axis and off-axis pulse laser deposition (PLD) technique. It is found that the film prepared using on-axis PLD is more uniformly distributed and has smoother texture compared with that of the off-axis technique. In order to analyze the images quantitatively, they are transformed to the wavelet domain to extract the localized frequency variations and a uniformity measure is derived using a fuzzy inference system for quantitatively analyzing the uniformity of each image. The surface plot of the FSIM values of the image is found to be an efficient tool for nanoscientists to evaluate the smoothness of the thin film surfaces. This study is expected to help the nanoscientists to understand these nanostructures in detail. Copyright © 2014 John Wiley & Sons, Ltd.

Monogenic signal theory based feature similarity index for image quality assessment

Image quality assessment (IQA) aims to establish generic metrics consistently with subjective evaluations using computational models. Recent phase congruency, which is a dimensionless, normalized feature of a local structure, is used as the structure similarity feature. This paper proposes a novel feature similarity index that is Riesz transform based monogenic phase congruency feature similarity index (RMFSIM). RMFSIM is based on monogenic signal theory for full reference IQA. Monogenic phase congruency (MPC) map, instead of phase congruency map, is constructed utilizing the local phase, the local orientation and the local energy information of the 2D monogenic signal. The corresponding 1st-order and 2nd-order coefficients of the MPC map are obtained by Riesz transform. The local feature coefficients similarities are computed by the similarity measure, and then a final single quality score is derived from weighting feature coefficients similarities. Experimental results demonstrate that the proposed similarity index is highly consistent with human subjective evaluations and achieves good performance with the existing state-of-the-art methods in terms of prediction monotonicity and accuracy.

WE‐D‐9A‐02: Automated Landmark‐Guided CT to Cone‐Beam CT Deformable Image Registration

Purpose:The anatomical changes that occur between the simulation CT and daily cone‐beam CT (CBCT) are investigated using an automated landmark‐guided deformable image registration (LDIR) algorithm with simultaneous intensity correction. LDIR was designed to be accurate in the presence of tissue intensity mismatch and heavy noise contamination.Method:An auto‐landmark generation algorithm was used in conjunction with a local small volume (LSV) gradient matching search engine to map corresponding landmarks between the CBCT and planning CT. The LSVs offsets were used to perform an initial deformation, generate landmarks, and correct local intensity mismatch. The landmarks act as stabilizing controlpoints in the Demons objective function. The accuracy of the LDIR algorithm was evaluated on one synthetic case with ground truth and data of ten head and neck cancer patients. The deformation vector field (DVF) accuracy was accessed using a synthetic case. The Root mean square error of the 3D canny edge (RMSECE), mutual information (MI), and feature similarity index metric (FSIM) were used to access the accuracy of LDIR on the patient data. The quality of the corresponding deformed contours was verified by an attending physician.Results:The resulting 90 percentile DVF error for the synthetic case was within 5.63mm for the original demons algorithm, 2.84mm for intensity correction alone, 2.45mm using controlpoints without intensity correction, and 1.48 mm for the LDIR algorithm. For the five patients the mean RMSECE of the original CT, Demons deformed CT, intensity corrected Demons CT, control‐point stabilized deformed CT, and LDIR CT was 0.24, 0.26, 0.20, 0.20, and 0.16 respectively.Conclusion:LDIR is accurate in the presence of multimodal intensity mismatch and CBCT noise contamination. Since LDIR is GPU based it can be implemented with minimal additional strain on clinical resources.This project has been supported by a CPRIT individual investigator award RP11032.

Multi-scale structural image quality assessment based on two-stage low-level features

Objective image quality assessment has been widely used in image processing for decades. Many researchers have been studying the objective quality assessment method based on human visual system. Recently, the single-scale feature-similarity index metric has been proposed to provide a good approximation to perceived image quality. However, this metric does not take into account the fact that features in a certain scale cannot reflect various distorted details in the image. To address this issue, this paper proposes a multi-scale structural image quality assessment based on two-stage low-level features, which supplies more flexible than previous single-scale method by incorporating the variations of viewing conditions and resolution. In this multi-scale framework, different weights are assigned to various scales with different levels of importance. Extensive experiments on the five public benchmark databases indicate that the proposed metric is more consistent with the subjective evaluations than all the other competing methods evaluated.

Enhancement of positron emission tomography-computed tomography image quality using the principle of stochastic resonance.

Purpose:Acquisition of higher counts improves visual perception of positron emission tomography-computed tomography (PET-CT) image. Larger radiopharmaceutical doses (implies more radiation dose) are administered to acquire this count in a short time period. However, diagnostic information does not increase after a certain threshold of counts. This study was conducted to develop a post processing method based on principle of “stochastic resonance” to improve visual perception of the PET-CT image having a required threshold counts.Materials and Methods:PET-CT images (JPEG file format) with low, medium, and high counts in the image were included in this study. The image was corrupted with the addition of Poisson noise. The amplitude of the Poisson noise was adjusted by dividing each pixel by a constant 1, 2, 4, 8, 16, and 32. The best amplitude of the noise that gave best images quality was selected based on high value of entropy of the output image, high value of structural similarity index and feature similarity index. Visual perception of the image was evaluated by two nuclear medicine physicians.Results:The variation in structural and feature similarity of the image was not appreciable visually, but statistically images deteriorated as the noise amplitude increases although maintaining structural (above 70%) and feature (above 80%) similarity of input images in all cases. We obtained the best image quality at noise amplitude “4” in which 88% structural and 95% feature similarity of the input images was retained.Conclusion:This method of stochastic resonance can be used to improve the visual perception of the PET-CT image. This can indirectly lead to reduction of radiation dose.

An edge-directed interpolation method for fetal spine MR images

BackgroundFetal spinal magnetic resonance imaging (MRI) is a prenatal routine for proper assessment of fetus development, especially when suspected spinal malformations occur while ultrasound fails to provide details. Limited by hardware, fetal spine MR images suffer from its low resolution.High-resolution MR images can directly enhance readability and improve diagnosis accuracy. Image interpolation for higher resolution is required in clinical situations, while many methods fail to preserve edge structures. Edge carries heavy structural messages of objects in visual scenes for doctors to detect suspicions, classify malformations and make correct diagnosis. Effective interpolation with well-preserved edge structures is still challenging.MethodIn this paper, we propose an edge-directed interpolation (EDI) method and apply it on a group of fetal spine MR images to evaluate its feasibility and performance. This method takes edge messages from Canny edge detector to guide further pixel modification. First, low-resolution (LR) images of fetal spine are interpolated into high-resolution (HR) images with targeted factor by bi-linear method. Then edge information from LR and HR images is put into a twofold strategy to sharpen or soften edge structures. Finally a HR image with well-preserved edge structures is generated. The HR images obtained from proposed method are validated and compared with that from other four EDI methods. Performances are evaluated from six metrics, and subjective analysis of visual quality is based on regions of interest (ROI).ResultsAll these five EDI methods are able to generate HR images with enriched details. From quantitative analysis of six metrics, the proposed method outperforms the other four from signal-to-noise ratio (SNR), peak signal-to-noise ratio (PSNR), structure similarity index (SSIM), feature similarity index (FSIM) and mutual information (MI) with seconds-level time consumptions (TC). Visual analysis of ROI shows that the proposed method maintains better consistency in edge structures with the original images.ConclusionsThe proposed method classifies edge orientations into four categories and well preserves structures. It generates convincing HR images with fine details and is suitable in real-time situations. Iterative curvature-based interpolation (ICBI) method may result in crisper edges, while the other three methods are sensitive to noise and artifacts.

Feature-Based Image Fusion with a Uniform Discrete Curvelet Transform

Abstract The uniform discrete curvelet transform (UDCT) is a novel tool for multiscale representations with several desirable properties compared to previous representation methods. A novel algorithm based on UDCT is proposed for the fusion of multi-source images. A novel fusion rule for different subband coefficients obtained by UDCT decomposition is discussed in detail. Low-pass subband coefficients are merged to develop a fusion rule based on a feature similarity (FSIM) index. High-pass directional subband coefficients are merged for a fusion rule based on a complex coefficients feature similarity (CCFSIM) index. Experimental results demonstrate that the proposed algorithm fuses all of the useful information from source images without introducing artefacts. Compared with several state-of-the-art fusion methods, it yields a better performance and achieves higher efficiency.