High Frequency Sub-images Research Articles

An efficient image defogging algorithm based on dragonfly optimized gamma correction and stationary wavelet decomposition

Image dehazing is a revolutionary technique for restoring images with hazy or foggy landscapes, that has gotten a lot of focus in recent years since it gained importance in a surveillance system. However, the image processing by the traditional defogging algorithm has difficulties in integrating the depth of image detail and the color of the image. Therefore, in this paper, a novel framework based on wavelet decomposition and optimized gamma correction is proposed for efficaciously retrieving the fog-free image. The foggy image is first divided into low and high frequency sub-images using SWT (Stationary Wavelet Transform), which has the advantages of preserving temporal features so that information loss can be stopped. Then the low frequency and high frequency images are processed with defogging and denoising modules to remove fog and noise respectively. The DOGC (Dragonfly optimal Gamma Correction) algorithm in dehazing module dynamically enhanced the color detail information without human intervention so that observed scene contrast and visibility are well preserved. Lastly, fog-free image is reconstructed from sub-enhanced images. The experimental findings show that the proposed framework outperforms state-of-the-art methods in terms of both quantitative and qualitative assessment criteria using the established dataset. Furthermore, the proposed method efficiently removes fog while preserving the naturalness of fog images.

Medical Image Fusion Using SKWGF and SWF in Framelet Transform Domain

Accurately localizing and describing patients’ lesions has long been considered a crucial aspect of clinical diagnosis. The fusion of multimodal medical images provides a feasible solution to the above problem. Unfortunately, the trade-off between the fusion performance and heavy computation overhead remains a challenge. In this paper, a novel and effective fusion method for multimodal medical images is proposed. Firstly, framelet transform (FT) is introduced to decompose the source images into a series of low and high frequency sub-images. Next, we utilize the benefits of both steering kernel weighted guided filtering and side window filtering to successfully fuse sub-images. Finally, the inverse FT is employed to reconstruct the final fused image. To verify the effectiveness of the proposed fusion method, we fused several pairs of medical images covering different modalities in simulation experiments. The experimental results demonstrate that the proposed method yields better performance than current representative ones in terms of both visual quality and quantitative evaluation.

A Lightweight Multimode Medical Image Fusion Method Using Similarity Measure Between Intuitionistic Fuzzy Sets Joint Laplacian Pyramid

Medical image fusion combines the multiple features of human tissue from different source images, which will be conducive to clinical diagnosis. Because of the human visual perception and mechanisms of medical imaging, abundant fuzzy features exist in medical image fusion with remarkable influence. To address this issue, we introduce the similarity measure of fuzzy set theory into medical image fusion to abstract and measure these fuzzy features. In this study, we present a new similarity measure of intuitionistic fuzzy set theory to represent image features and present a lightweight medical image fusion technique on the basis of this new measure. First, the new similarity measure is proposed according to geometric modeling technique and verified by mathematical justification. Second, a set of high frequency sub-images and a low frequency sub-image are produced by Laplacian pyramid decomposition to separate different image features. Third, our proposed similarity measure is utilized to describe and extract the detailed image features. Finally, two fusion rules and inverse Laplacian pyramid decomposition are sequentially used to get the fused image. This research shows that the similarity measure of fuzzy set theory can get excellent performance in medical image fusion. Experiments reveal that our similarity measure and medical image fusion method both have the superior performance to most of the existing methods.

Translation-invariant context-retentive wavelet reflection removal network.

It has been widely investigated for images taken through glass to remove unwanted reflections in deep learning. However, none of these methods have bad effects, but they all remove reflections in specific situations, and validate the results with their own datasets, e.g., several local places with strong reflections. These limitations will result in situations where real reflections in the world cannot be effectively eliminated. In this study, a novel Translation-invariant Context-retentive Wavelet Reflection Removal Network is proposed to address this issue. In addition to context and background, low-frequency sub-images still have a small amount of reflections. To enable background context retention and reflection removal, the low-frequency sub-images at each level are performed on the Context Retention Subnetwork (CRSn) after wavelet transform. Novel context level blending and inverse wavelet transform are proposed to remove reflections in low frequencies and retain background context recursively, which is of great help in restoring clean images. High-frequency sub-images with reflections are performed on the Detail-enhanced Reflection layer removal Subnetwork to complete reflection removal. In addition, in order to further separate the reflection layer and the transmission layer better, we also propose Detail-enhanced Reflection Information Transmission, through which the extracted features of reflection layer in high-frequency images can help the CRSn effectively separate the transmission layer and the reflection layer, so as to achieve the effects of removing reflection. The quantitative and visual experimental results on benchmark datasets demonstrate that the proposed method performs better than the state-of-the-art approaches.

Enhancing Variational Generation Through Self-Decomposition

In this article we introduce the notion of Split Variational Autoencoder (SVAE), whose output $\hat{x}$ is obtained as a weighted sum $\sigma \odot \hat{x_1} + (1-\sigma) \odot \hat{x_2}$ of two generated images $\hat{x_1},\hat{x_2}$, and $\sigma$ is a {\em learned} compositional map. The composing images $\hat{x_1},\hat{x_2}$, as well as the $\sigma$-map are automatically synthesized by the model. The network is trained as a usual Variational Autoencoder with a negative loglikelihood loss between training and reconstructed images. No additional loss is required for $\hat{x_1},\hat{x_2}$ or $\sigma$, neither any form of human tuning. The decomposition is nondeterministic, but follows two main schemes, that we may roughly categorize as either \say{syntactic} or \say{semantic}. In the first case, the map tends to exploit the strong correlation between adjacent pixels, splitting the image in two complementary high frequency sub-images. In the second case, the map typically focuses on the contours of objects, splitting the image in interesting variations of its content, with more marked and distinctive features. In this case, according to empirical observations, the Fr\'echet Inception Distance (FID) of $\hat{x_1}$ and $\hat{x_2}$ is usually lower (hence better) than that of $\hat{x}$, that clearly suffers from being the average of the former. In a sense, a SVAE forces the Variational Autoencoder to make choices, in contrast with its intrinsic tendency to {\em average} between alternatives with the aim to minimize the reconstruction loss towards a specific sample. According to the FID metric, our technique, tested on typical datasets such as Mnist, Cifar10 and CelebA, allows us to outperform all previous purely variational architectures (not relying on normalization flows).

Glioma classification via MR images radiomics analysis

Accurate glioma classification before surgery is of the utmost important in clinical decision making and prognosis prediction. In this paper, we investigate the impact of multi-modal MR image fusion for the differentiation of low-grade gliomas (LGG) versus high-grade gliomas (HGG) via integrative analyses of radiomic features and machine learning approaches. A set of 80 histologically confirmed gliomas patients (40 HGG and 40 LGG) obtained from the MICCAI BraTS 2019 data were involved in this study. To achieve this work, we propose to combine T1 with T2 or FLAIR modality in the non-subsampled shearlet domain. Firstly, the pre-processed source MR images are decomposed into low-frequency (LF) and several high-frequency (HF) sub-images. LF sub-images are fused using the proposed weight local features fusion rule while HF sub-images are combined based on the novel sum-modified-laplacian technique. Experimental results demonstrate that the proposed fusion approach outperformed the recent state-of-the-art approaches in terms of entropy and feature mutual information. Subsequently, a key radiomics signature was retrieved by the least absolute shrinkage and selection operator regression algorithm. Five machine learning classifiers were established and evaluated with the retrieved dataset, then with the fused dataset using tenfold cross-validation scheme. As a result, the random forest had the highest accuracy of 96.5% with 21 features selected from the raw data and 96.1% with 16 features selected from the fused data. Finally, the experimental findings confirm that the proposed aided diagnosis framework represents a promising tool to aid radiologists in differentiating HGG and LGG.

Research on Image Fusion Algorithm Based on NSST Frequency Division and Improved LSCN

Single modal medical images provide limited information and cannot reflect all the details of the relevant tissues, which may lead to misdiagnosis in clinical medicine. Therefore, a medical image fusion algorithm based on non-down-sampling shear wave transform (NSST) is proposed. This algorithm fuses multi-modal medical images, enriches the information of fused images, improves the image quality, and provides a basis for clinical diagnosis. Firstly, the low-frequency sub-band and several high-frequency directional sub-bands are obtained by NSST transformation of the source image, and the structural similarity between sub-bands is evaluated. Then, according to the characteristics of low-frequency sub-band images, for sub-images with high similarity, the regional features are obtained by region energy and variance, and the fusion method is based on region feature weighting. For sub-images with low similarity, two images to be fused are input into the LSCN model respectively by fusing the connection items of the improved LSCN model. The improved L-term replaces the ignition frequency in the traditional PCNN as the output. According to the characteristics of high frequency sub-images, the fusion rule of combining visual sensitivity coefficient and regional energy is adopted for sub-images with high similarity. For sub-images with low similarity, an improved guided filter is used to fuse the sub-images in order to maintain the clear edges of the images. Finally, the image is reconstructed by inverse NSST transform. The experimental results show that the proposed algorithm can obtain better fusion effects in both objective and subjective evaluation. The obtained fusion image has rich information, excellent edge retention characteristics, subjectively clear texture and high contrast and good visual effect.

Infrared small target detection based on non-subsampled shearlet transform and phase spectrum of quaternion Fourier transform

Infrared small target detection is a crucial part of infrared search and track system, and it has been a significant research topic in the past decades. Inspired by previous studies showing that phase spectrum of quaternion Fourier transform (PQFT) great superiority in salient region extraction and the desirable characteristics of multi-scale, multi-direction and shift-invariant with non-subsampled shearlet transform (NSST), a new target detection method is proposed based on NSST and PQFT in this paper. The original image is first subjected to NSST decomposition to obtain a low frequency component and four high frequency components by NSP. Next, directional localization is achieved by shearing filters which provides multi-directional decomposition. Then, four direction high frequency sub-images decomposed by NSST are introduced as four data channels of PQFT. The reconstruction map that highlights the salient region in the time domain is computed using the inverse PQFT. Lastly, the real target is directly segmented by an adaptive threshold. The proposed method is validated by five test sequences. The experimental results show that our method is superior to other traditional methods in terms of robustness and effectiveness in complex background.

An IHS-Based Pan-Sharpening Method for Spectral Fidelity Improvement Using Ripplet Transform and Compressed Sensing.

Pan-sharpening aims at integrating spectral information from a multi-spectral (MS) image and spatial information from a panchromatic (PAN) image in a fused image with both high spectral and spatial resolutions. Numerous pan-sharpening methods are based on intensity-hue-saturation (IHS) transform, which may cause evident spectral distortion. To address this problem, an IHS-based pan-sharpening method using ripplet transform and compressed sensing is proposed. Firstly, the IHS transform is applied to the MS image to separate intensity components. Secondly, discrete ripplet transform (DRT) is implemented on the intensity component and the PAN image to obtain multi-scale sub-images. High-frequency sub-images are fused by a local variance algorithm and, for low-frequency sub-images, compressed sensing is introduced for the reconstruction of the intensity component so as to integrate the local information from both the intensity component and the PAN image. The specific fusion rule is defined by local difference. Finally, the inverse ripplet transform and inverse IHS transform are coupled to generate the pan-sharpened image. The proposed method is compared with five state-of-the-art pan-sharpening methods and also the Gram-Schmidt (GS) method through visual and quantitative analysis of WorldView-2, Pleiades and Triplesat datasets. The experimental results reveal that the proposed method achieves relatively higher spatial resolution and more desirable spectral fidelity.

Multi-Sensor Image Fusion Based on Interval Type-2 Fuzzy Sets and Regional Features in Nonsubsampled Shearlet Transform Domain

Multi-scale geometric analysis, one of the most often-used multi-sensor image fusion (MSIF) techniques, can offer outstanding performance during extracting the features of source image. Interval type-2 fuzzy sets (Type-2 FS) have a good prospect in image fusion field, because it can effectively address the uncertain and fuzzy problem in image fusion for selecting the high-quality pixels or coefficients of source images. We try to extend the application fields of Type-2 FS and improve the performance of MSIF; therefore, this paper presents a hybrid method by combining the local spatial frequency (LSF) with interval Type-2 FS in nonsubsampled shearlet transform (NSST) domain. NSST is used to decompose source images, and interval Type-2 FS and LSF is employed to extract the regional features of source images; so it can extract and fuse the detailed features of different source images accurately. First, NSST is performed to decompose the source images into low frequency and high frequency sub-images. Second, LSF-based fusion rule is applied to fuse low frequency sub-images. Thirdly, a novel fusion process based on interval Type-2 FS is designed to fuse high frequency sub-images. At last, inverse NSST2 (INSST) is implemented to reconstruct the fused images. The experimental and contrastive results of different image sets show that the proposed method is an effective MSIF scheme, which can achieve better fusion effect than the existing representative methods.

Nonsubsampled shearlet domain fusion techniques for CT–MR neurological images using improved biological inspired neural model

The fusion of multimodality medical images performs a very crucial role in the clinical diagnosis, analysis and the treatment of especially in critical diseases. It is considered as an assisted approach for the radiologist by providing the composite images having significant diagnostic information acquired from the source images. The main purpose of this work is to develop an efficient framework for fusing the multimodal medical images. Three different fusion techniques are proposed in this paper that presents the CT and MR medical image fusion in nonsubsampled shearlet transform (NSST) domain using the adaptive spiking neural model. The NSST having different features and a competent depiction of the image coefficients provides several directional decomposition coefficients. Maximum selection approach and regional energy are utilized for low frequency coefficients fusion. Spatial frequency, novel modified spatial frequency and novel sum modified Laplacian motivated spiking model are used for every high frequency subimage component. Finally, fused images are reconstructed by applying inverse NSST. The performance of proposed fusion techniques is validated by extensive simulations performed on different CT-MR image datasets using proposed and other thirty seven existing fusion approaches in terms of both the subjective and objective manner. The results revealed that the proposed techniques provide better visualization of resultant images and higher quantitative measures compared to several existing fusion approaches.

Colour Image Enhancement Method Combined PCNN and PCA Based on NSCT

A new colour image enhancement method based on NSCT and PCNN is proposed by using HSV model, in order to decrease the influence non-uniform luminance on true colour images. First, a colour image is transformed from RGB colour space to HSV colour space. Second, intensity channel is decomposed by NSCT, and we can obtain the low frequency sub-image and a series high frequency sub-images. Third, PCNN and PCA are applied on the low frequency sub-image, and nonlinear translation is employed on high-frequency sub-images. Then, the intensity component image is obtained by inverse NSCT. Finally, the colour image is obtained by transforming from HSV colour space to RGB colour space. Experiments illustrate that our algorithm can not only corrected non-uniform illumination in images, but also well maintain the colour and local details of images.

적응적 비선형 히스트그램 스트레칭을 이용한 의료영상의 화질향상

In the production of medical images, noise reduction and contrast enhancement are important methods to increase qualities of processing results. By using the edge-based denoising and adaptive nonlinear histogram stretching, a novel medical image enhancement algorithm is proposed. First, a medical image is decomposed by wavelet transform, and then all high frequency sub-images are decomposed by Haar transform. At the same time, edge detection with Sobel operator is performed. Second, noises in all high frequency sub-images are reduced by edge-based soft-threshold method. Third, high frequency coefficients are further enhanced by adaptive weight values in different sub-images. Finally, an adaptive nonlinear histogram stretching method is applied to increase the contrast of resultant image. Experimental results show that the proposed algorithm can enhance a low contrast medical image while preserving edges effectively without blurring the details.

Medical Image Enhancement Algorithm Using Edge-Based Denoising and Adaptive Histogram Stretching

In the production of medical images, noise reduction and contrast enhancement are important methods to increase qualities of processing results. Wavelet transforms have shown promising results for localization in both time and frequency, and hence have been used for image processing applications including noise removal. By using the edge-based denoising and adaptive nonlinear histogram stretching, a novel medical image enhancement algorithm is proposed. First, a medical image is decomposed by wavelet transform, and then all high frequency sub-images are decomposed by Haar transform. At the same time, edge detection with Sobel operator is performed. Second, noises in all high frequency sub-images are reduced by edge-based soft-threshold method. Third, high frequency coefficients are further enhanced by adaptive weight values in different sub-images. Through the inverse Haar transform and the inverse wavelet transform, the enhanced image is obtained. Finally, the proposed adaptive nonlinear histogram stretching method is applied to increase the contrast of resultant image. Experimental results show that the proposed algorithm can enhance a low contrast medical image while preserving edges effectively without blurring the details.

Feature and Contrast Enhancement of Mammographic Image Based on Multiscale Analysis and Morphology

A new algorithm for feature and contrast enhancement of mammographic images is proposed in this paper. The approach bases on multiscale transform and mathematical morphology. First of all, the Laplacian Gaussian pyramid operator is applied to transform the mammography into different scale subband images. In addition, the detail or high frequency subimages are equalized by contrast limited adaptive histogram equalization (CLAHE) and low-pass subimages are processed by mathematical morphology. Finally, the enhanced image of feature and contrast is reconstructed from the Laplacian Gaussian pyramid coefficients modified at one or more levels by contrast limited adaptive histogram equalization and mathematical morphology, respectively. The enhanced image is processed by global nonlinear operator. The experimental results show that the presented algorithm is effective for feature and contrast enhancement of mammogram. The performance evaluation of the proposed algorithm is measured by contrast evaluation criterion for image, signal-noise-ratio (SNR), and contrast improvement index (CII).

Research of Image Compression Based on Fractal Coding

The EZW and Fractal Coding were researched and simulated in this paper. And two drawbacks were discovered in these algorithm:the coding time is too long and the effect of reconstructed image is not ideal. Therefore, The paper studied the wavelet transformation in the fractal coding application, The wavelet coefficients of an image present two characteristics when the image is processed by wavelet transform: first characteristic is that the energy of an image is strongly concentrated in low frequency sub-image, second characteristic is that there is a similarity between the same direction in high frequency sub-images.but the fractal coding essence was precisely uses the similarity of wavelet transform image. The paper designed one kind of new Image Compression based on Fractal Coding in wavelet domain. The theoretical analysis and the simulation experiment indicated that, to some extent the method can reduce the coding time and reduce the MSE and enhance compression ratio of the reconstructed image and improve PSNR of the reconstructed image..

An integrated method in wavelet-based image compression

In this paper, we propose an integrated image compression method, which contains the discrete wavelet transform, scalar quantization and some lossless codings, to gain higher compression ratios while maintaining the image fidelity. The discrete wavelet transform has the properties of entropy reduction and energy concentration in high frequency subimages. An innovative approach, called revised run-length coding, is proposed to improve the compression performance. The idea of this approach is to represent the appearance of symbols of the run-length code in exponential expression for saving the storage in bits. The differential pulse code modulation is used to reduce the entropy of the lowest frequency subimage of the discrete wavelet transform and to achieve high compression effects losslessly.

Pyramidal piecewise uniform lattice quantization in the wavelet transform domain for image coding

The wavelet transform, which provides a multiresolution representation of images, has been widely used in image compression. A new image coding scheme using the wavelet transform and lattice vector quantization is presented. The input image is first decomposed into a hierarchy of three layers containing 10 subimages by discrete wavelet transform. The lowest resolution low-frequency subimage is scalar quantized with 8 bits/pixel. High-frequency subimages are encoded by lattice vector quantization. A pyramidal piecewise uniform companding approach is used to design the lattice quantizer according to a piecewise constant approximation to the probability density function of the input source. Due to the fast algorithm of lattice quantization, computational complexity is greatly reduced as compared to the vector quantizers based on the Linde-Buzo-Gray (LBG) algorithm. Computer simulations show that the proposed coding scheme can achieve a high compression ratio while maintaining good reconstruction image quality (both objectively and subjectively).

Image coding using wavelet transform and classified vector quantisation

The wavelet transform, which provides a multiresolution representation of images, has been widely used in image compression. A new image coding scheme using the wavelet transform and classified vector quantisation is presented. The input image is first decomposed into a hierarchy of three layers containing ten subimages by the discrete wavelet transform. The lowest resolution low frequency subimage is scalar quantised with 8 bits/pixel. The high frequency subimages are compressed by classified vector quantisation to utilise the crosscorrelation among different resolutions while reducing the edge distortion and computational complexity. Vectors are constructed by combining the corresponding wavelet coefficients of different resolutions in the same orientation and classified according to the magnitude and the position of wavelet transform coefficients. Simulation results show that the proposed scheme has a better performance than those utilising current scalar or vector quantisation schemes.