Low Frequency Sub-band Research Articles

Image enhancement method for paint defects based on polarization fusion technique

The highly reflective nature of paint surfaces poses a challenge for defect detection. In this paper, a polarization fusion based image enhancement algorithm for paint defects is proposed to improve the image quality and complement the masked defect details. Firstly, the linearly polarized photometric (DOLP) image is initially fused with the angle of polarization (AOP) image. The light intensity images and polarization feature images were enhanced using a single scale Retinex algorithm and these images were decomposed and reconstructed using wavelet transform to integrate the low and high frequency subbands based on saliency maps and regional energy features. Experiments were performed on defects at different locations and compared with other classical methods. The results show that the proposed fusion algorithm improves the contrast while providing more complete defect information, clearer texture details and significant advantages over other algorithms.

BGFlow: Brightness-guided normalizing flow for low-light image enhancement

Low-light image enhancement poses significant challenges due to its ill-posed nature. Recently, deep learning-based methods have attempted to establish a unified mapping relationship between normal-light images and their low-light versions but frequently struggle to capture the intricate variations in brightness conditions. As a result, these methods often suffer from overexposure, underexposure, amplified noise, and distorted colors. To tackle these issues, we propose a brightness-guided normalizing flow framework, dubbed BGFlow, for low-light image enhancement. Specifically, we recognize that low-frequency sub-bands in the wavelet domain carry significant brightness information. To effectively capture the intricate variations in brightness within an image, we design a transformer-based multi-scale wavelet-domain encoder to extract brightness information from the multi-scale features of the low-frequency sub-bands. The extracted brightness feature maps, at different scales, are then injected into the brightness-guided affine coupling layer to guide the training of the conditional normalizing flow module. Extensive experimental evaluations demonstrate the superiority of BGFlow over existing deep learning-based approaches in both qualitative and quantitative assessments. Moreover, we also showcase the exceptional performance of BGFlow on the underwater image enhancement task.

A Transformer-based invertible neural network for robust image watermarking

For the existing encoder-noise-decoder (END) based watermarking models, since the coupling between the encoder and the decoder is weak, the encoder generally embeds certain redundant features into the cover image to enable the decoder to extract watermark completely, which will affect watermarking invisibility. To address this problem, this paper proposes a Transformer-based invertible neural network (INN) for robust image watermarking (IWFormer). In order to effectively reduce redundant features, the INN framework is utilized for the watermark embedding and extracting processes, so that the encoded features are highly consistent with the features required for decoding. For enhancing watermarking robustness, an affine Transformer module is designed by mining the global correlation of the cover image. In addition, considering that the human visual system is sensitive to low-frequency variations, the wavelet low-frequency sub-band loss is deployed to guide watermark to be embedded in middle- and high-frequency components, thus further increasing the quality of the encoded images. Experimental results demonstrate that compared with the existing state-of-the-art watermarking models, the proposed IWFormer owns remarkable advantages in terms of both watermarking invisibility and robustness.

Research on fractional wavelet transform combined with parameter adaptive PCNN for infrared and visible image fusion algorithm

Infrared and visible image fusion holds significant value across various fields due to its ability to provide complementary information. However, existing fusion algorithms often suffer from susceptibility to external physical conditions of source images, leading to inconsistent fusion quality and limited adaptive capability. In this paper, we propose a fractional wavelet transform fusion algorithm for infrared and visible images. This algorithm uses fractional wavelet domain image decomposition to more accurately locate the image structures of different scales. Initially, we perform image decomposition using a non-subsampled shearlet transform (NSST) with multi-scale and multi-directional decomposition. Subsequently, to effectively fuse detailed information, we employ discrete fractional wavelet transform (DFRWT) to decompose low-frequency subbands while selecting an appropriate p-value. High-frequency subbands are fused using a parameterized adaptive pulse-coupled neural network (PCNN) model. To validate the superiority of our algorithm, we conduct visual and quantitative comparative analyses against several existing algorithms. The results confirm that our proposed algorithm exhibits robustness against external physical conditions and surpasses these existing algorithms, making it highly applicable for infrared–visible fusion tasks.

New oscillatory features of electrodermal activity signals evaluated in automated mental workload monitoring

Oscillatory components are discriminative features of mental workload monitoring in electrodermal activity (EDA) signals. Currently, most feature extraction techniques mainly focus on time domain or linear techniques but rarely consider the non-stationary nature, individual differences, and recording noise. This study has proposed a new time–frequency feature extraction method based on Tunable Q-factor Wavelet Transform providing an effective quantification of oscillatory behavior of a single transient. The extracted features have been classified using a recurrent neural network with the advantage of dynamic mapping procedure. The proposed method has been evaluated using EDA data acquired during an arithmetic task of five workload levels with both subtle and distinct differences. In a comparative study, the effects of several decomposition parameters and cognitive factors have been explored. Experimental results have shown that it achieves an average accuracy rate of 98.52% for three workload levels discrimination by optimizing the number of features to 3 (features extracted from a low frequency sub-band) from 15 (features extracted from five frequency sub-bands), i.e., 80% feature reduction. The greatest contribution coming fromthe smallest frequency sub-bands has also been obtained. This method is superior to other existing methods in separating 3 to 5 workload levels with both distinct and subtle differences extracting effective oscillatory characteristics. Considering the merits of a simple feature extraction procedure and cost-effectiveness of a single lead EDA signal as well as high discriminability between several workload levels, it provides a trade-off between performance and computational complexity, thus demonstrating its potential for online human-error prevention systems.

DCFNet: Infrared and Visible Image Fusion Network Based on Discrete Wavelet Transform and Convolutional Neural Network.

Aiming to address the issues of missing detailed information, the blurring of significant target information, and poor visual effects in current image fusion algorithms, this paper proposes an infrared and visible-light image fusion algorithm based on discrete wavelet transform and convolutional neural networks. Our backbone network is an autoencoder. A DWT layer is embedded in the encoder to optimize frequency-domain feature extraction and prevent information loss, and a bottleneck residual block and a coordinate attention mechanism are introduced to enhance the ability to capture and characterize the low- and high-frequency feature information; an IDWT layer is embedded in the decoder to achieve the feature reconstruction of the fused frequencies; the fusion strategy adopts the l1-norm fusion strategy to integrate the encoder's output frequency mapping features; a weighted loss containing pixel loss, gradient loss, and structural loss is constructed for optimizing network training. DWT decomposes the image into sub-bands at different scales, including low-frequency sub-bands and high-frequency sub-bands. The low-frequency sub-bands contain the structural information of the image, which corresponds to the important target information, while the high-frequency sub-bands contain the detail information, such as edge and texture information. Through IDWT, the low-frequency sub-bands that contain important target information are synthesized with the high-frequency sub-bands that enhance the details, ensuring that the important target information and texture details are clearly visible in the reconstructed image. The whole process is able to reconstruct the information of different frequency sub-bands back into the image non-destructively, so that the fused image appears natural and harmonious visually. Experimental results on public datasets show that the fusion algorithm performs well according to both subjective and objective evaluation criteria and that the fused image is clearer and contains more scene information, which verifies the effectiveness of the algorithm, and the results of the generalization experiments also show that our network has good generalization ability.

Edge-preserving image deraining network using cumulative feature aggregation

This study proposes an edge-preserving image deraining network using a wavelet feature aggregation method. Wavelet subbands re correlated with each other, and the high-frequency subband in the horizontal direction is the least affected by rain streak contamination. On this basis, we introduce a single image deraining network that cumulatively aggregates wavelet subband features according to their importance. The network architecture primarily comprises a wavelet feature aggregation block and a residue channel guide block. The aggregation of features with the cumulative wavelet feature aggregation block moves downward and upward, and a long short-term memory-based multiscale attentive rain streak removal block is developed to serve as the backbone for rain streak removal. We use a residual channel map based on the low-frequency subband to construct guide features that assist in rain streak removal. A repetitive image restoration framework that incorporates two proposed blocks is used to iteratively improve rainy images. We test the proposed network on various image datasets and compare the deraining performance with those of existing methods The experimental results demonstrate that the performance of the proposed scheme is superior to that of other tested deraining methods. https://github.com/SYChoi98/CWFANet/

Robust zero-watermarking algorithm for multi-medical images based on FFST-Schur and Tent mapping

Aiming at issues such as the difficulty of centralized protection of multiple medical images and the high storage cost caused by repetitive operations, we proposed a robust zero-watermarking algorithm for multiple medical images based on fast finite Shearlet transform (FFST)-Schur and Tent mapping. First, multiple medical images were normalized, and the processed images were fused using a gray-weighted average fusion method for image fusion. Second, an FFST is applied to the fused image to divide the low-frequency sub-bands into blocks of the same size and perform Schur decomposition, which generates a feature image using the magnitude between the largest eigenvalue of each block and the overall average value. Finally, an image encryption algorithm based on Tent mapping is proposed to encrypt the logo image, and the encrypted image and feature image are then subjected to an exclusive OR operation to produce a zero-watermarking image. Experimental results demonstrate that the proposed approach effectively safeguards against standard image processing and geometric and combinatorial attacks. The average performance of the anti-attack algorithm was improved by approximately 3.2 % compared to similar algorithms, indicating the superior robustness of the proposed algorithm.

A Multi-Scale Fusion Strategy for Side Scan Sonar Image Correction to Improve Low Contrast and Noise Interference

Side scan sonar images have great application prospects in underwater surveys, target detection, and engineering activities. However, the acquired sonar images exhibit low illumination, scattered noise, distorted outlines, and unclear edge textures due to the complicated undersea environment and intrinsic device flaws. Hence, this paper proposes a multi-scale fusion strategy for side scan sonar (SSS) image correction to improve the low contrast and noise interference. Initially, an SSS image was decomposed into low and high frequency sub-bands via the non-subsampled shearlet transform (NSST). Then, modified multi-scale retinex (MMSR) was employed to enhance the contrast of the low frequency sub-band. Next, sparse dictionary learning (SDL) was utilized to eliminate high frequency noise. Finally, the process of NSST reconstruction was completed by fusing the emerging low and high frequency sub-band images to generate a new sonar image. The experimental results demonstrate that the target features, underwater terrain, and edge contours could be clearly displayed in the image corrected by the multi-scale fusion strategy when compared to eight correction techniques: BPDHE, MSRCR, NPE, ALTM, LIME, FE, WT, and TVRLRA. Effective control was achieved over the speckle noise of the sonar image. Furthermore, the AG, STD, and E values illustrated the delicacy and contrast of the corrected images processed by the proposed strategy. The PSNR value revealed that the proposed strategy outperformed the advanced TVRLRA technology in terms of filtering performance by at least 8.8%. It can provide sonar imagery that is appropriate for various circumstances.

Enhancement of X-Ray Images by Gradient Domain Guided Filtering and Non Sub Sampled Shearlet Transform

Abstract: In order to address the issues of low resolution, noise amplification, missing details, and weak edge gradient retention in the X-ray image improvement process, we propose in this study an image enhancement technique that combines nonSubsampled Shearlet transform with gradient-domain guided filtering. We start by breaking down the non Subsampled Shearlet transform and histogram equalization into the original image. We receive multiple high-frequency sub-bands as well as a lowfrequency sub-band. To enhance the overall contrast of the image and bring out the contour information in the low-frequency sub-band, adaptive gamma correction with weighting distribution is applied. To reduce image noise and emphasize edge information and detail, gradient-domain guided filtering is applied to the high-frequency sub-bands. In order to generate the final enhanced image, we use the inverse non-Subsampled Shearlet transform to reconstruct all of the sub-bands that were successfully processed. The experimental findings demonstrate the effectiveness of the suggested algorithm in improving X-ray images, as well as the clear advantages its objective index provides over certain conventional algorithms.

Medical Image Fusion for Brain Tumor Diagnosis Using Effective Discrete Wavelet Transform Methods

Background: The field of clinical or medical imaging is beginning to experience significant advancements in recent years. Various medical imaging methods such as computed tomography (CT), X-radiation (X-ray), and magnetic resonance imaging (MRI) produce images with distinct resolution differences, goals, and noise levels, making it challenging for medical experts to diagnose diseases. Objective: The limitations of a single medical image modality have increased the necessity for medical image fusion. The proposed solution is to create a fusion method of merging two types of medical images, such as MRI and CT. Therefore, this study aimed to develop a software solution that swiftly identifies the precise region of a brain tumor, speeding up the diagnosis and treatment planning. Methods: The proposed methodology combined clinical images by using discrete wavelet transform (DWT) and inverse discrete wavelet transform (IDWT). This strategy depended on a multi-goal decay of the image information using DWT, and high-frequency sub-bands of the disintegrated images were combined using a weighted averaging method. Meanwhile, the low-frequency sub-bands were straight-forwardly replicated in the resulting image. The combined high-quality image was recreated using the IDWT. This method can handle images with various modalities and resolutions without the need for previous data. Results: The results showed that the outcomes of the proposed method were assessed by different metrics such as accuracy, recall, F1-score, and visual quality. The method showed a high accuracy of 98% over the familiar neural network techniques. Conclusion: The proposed method was found to be computationally effective and produced high-quality medical images to assist professionals. Furthermore, the method can be stretched out to other image modalities and exercised by hybrid techniques of wavelet transform and neural networks and used for different clinical image analysis tasks. Keywords: CT and MRI, Image fusion, brain tumor, wavelet transform methods, medical images, machine learning, CNN

Analysis of DWT-DCT watermarking algorithm on digital medical imaging.

Over the past decade, the diagnostic information of the patients are digitally recorded and transferred. During the transmission of patients data, the security and authenticity of the information has to be ensured. Medical image watermarking technology has recently advanced because it can be used to conceal patient information while ensuring the authenticity. We propose a multiple watermarking method for securing clinical medical images. In this watermarking method, the quality feature property and private label property information are embedded as watermarks in the original image. Initially, medical images are divided into the region of interest (ROI) and non-interest region (NIR). Second, a two-level discrete wavelet transform (DWT) is applied to the ROI and the coefficients LL1 (LL2, LH2, HL2, HH2), LH1, HL1, and HH1 are generated. Watermarks are embedded using the DWT low-frequency sub-band (LL2) by quantizing the low-frequency coefficients. Next, the NIR is separated into non-overlapping blocks, and a discrete cosine transform (DCT) is applied for each block. The DCT coefficients of each block are sorted using the zigzag transform. For embedding, eight intermediate frequency coefficients are used. Finally, the feature information is embedded in the ROI, and the tag information is embedded in the NIR. The performance of the DWT-DCT watermarking method is calculated using the metrics of peak signal-to-noise ratio (PSNR), structural similarity index measure, and mean square error. The proposed method obtained the better PSNR value of 45.76dB. The proposed model works well for clinical medical images when compared with the existing techniques.

A Dual-Tree–Complex Wavelet Transform-Based Infrared and Visible Image Fusion Technique and Its Application in Tunnel Crack Detection

Computer vision methods have been widely used in recent years for the detection of structural cracks. To address the issues of poor image quality and the inadequate performance of semantic segmentation networks under low-light conditions in tunnels, in this paper, infrared images are used, and a preprocessing method based on image fusion technology is developed. First, the DAISY descriptor and the perspective transform are applied for image alignment. Then, the source image is decomposed into high- and low-frequency components of different scales and directions using DT-CWT, and high- and low-frequency subband fusion rules are designed according to the characteristics of infrared and visible images. Finally, a fused image is reconstructed from the processed coefficients, and the fusion results are evaluated using the improved semantic segmentation network. The results show that using the proposed fusion method to preprocess images leads to a low false alarm rate and low missed detection rate in comparison to those using the source image directly or using the classical fusion algorithm.

Multimodality medical image fusion analysis with multi-plane features of PET and MRI images using ONSCT

ABSTRACT The Multimodal Medical Image Fusion (MMIF) is affected by poor image quality, which leads to the extraction of inefficient features. The main intent of this work is to fuse various planes in the PET and MRI medical images efficiently using the MMIF approach. Initially, the sample images containing the axial plane of PET and MRI images are aggregated from standard datasets. Then, the collected images are employed for the decomposition process, which is accomplished via Optimal Non-Subsampled Contourlet Transform (ONSCT). The parameters in the NSCT are optimized using the Modified Water Strider Algorithm (MWSA. Once the images are decomposed, it is segmented into two sub-bands as high frequency and low-frequency sub-bands. Consequently, the high-frequency sub-bands of both PET and MRI images are fused by using the optimal weighted average fusion, in which the weight factor is obtained optimally by the MWSA algorithm. Similarly, the low-frequency sub-bands of both medical images are combined by sparse fusion technique. Finally, both the resultant fused images are subjected to Inverse Non-Subsampled Contourlet Transform (INSCT) to get desired fused images. The experimental findings suggest that the proposed model has effectively fused the images, and it also enhances the similarity score with axial planes.

A time-efficient and noise-resistant cryptosystem based on discrete wavelet transform and chaos theory: An application in image encryption

Due to the exponential rise of multimedia technologies, digital information privacy is now more crucial than ever. The process of transmitting data across a channel such as the internet has become a challenging task. In recent years, a variety of techniques for encrypting digital data have been proposed. However, due to shortcomings such as a high computational cost and weak security, it is important to build an encryption scheme that can provide a suitable level of security while also being time-effective. This research introduces a Discrete Wavelet Transform (DWT), chaotic map, and substitution box-based encryption scheme that is both time efficient and provides high levels of security for digital images. DWT is utilized to reduce the computation complexity of the encryption scheme proposed in this research. This is done by transforming the input image into its four frequency sub-bands (ΓΓ, Γħ, ħΓ, and ħħ) and selecting only the low-frequency sub-band (ΓΓ) for encryption, while the substitution boxes (S-boxes) and a chaotic map are used to increase the level of security. Using chaotic maps, random sequences are also generated to introduce confusion and diffusion. The final encrypted image is created by combining all of the non-modified and encrypted frequency bands. Finally, the results show that proposed encryption system nears the optimum values with a key-space of 2265 to avoid a brute-force attack.

Multi-Focus Image Fusion via PAPCNN and Fractal Dimension in NSST Domain

Multi-focus image fusion is a popular technique for generating a full-focus image, where all objects in the scene are clear. In order to achieve a clearer and fully focused fusion effect, in this paper, the multi-focus image fusion method based on the parameter-adaptive pulse-coupled neural network and fractal dimension in the nonsubsampled shearlet transform domain was developed. The parameter-adaptive pulse coupled neural network-based fusion rule was used to merge the low-frequency sub-bands, and the fractal dimension-based fusion rule via the multi-scale morphological gradient was used to merge the high-frequency sub-bands. The inverse nonsubsampled shearlet transform was used to reconstruct the fused coefficients, and the final fused multi-focus image was generated. We conducted comprehensive evaluations of our algorithm using the public Lytro dataset. The proposed method was compared with state-of-the-art fusion algorithms, including traditional and deep-learning-based approaches. The quantitative and qualitative evaluations demonstrated that our method outperformed other fusion algorithms, as evidenced by the metrics data such as QAB/F, QE, QFMI, QG, QNCIE, QP, QMI, QNMI, QY, QAG, QPSNR, and QMSE. These results highlight the clear advantages of our proposed technique in multi-focus image fusion, providing a significant contribution to the field.

A novel medical image fusion method based on multi-scale shearing rolling weighted guided image filter.

Medical image fusion is a crucial technology for biomedical diagnoses. However, current fusion methods struggle to balance algorithm design, visual effects, and computational efficiency. To address these challenges, we introduce a novel medical image fusion method based on the multi-scale shearing rolling weighted guided image filter (MSRWGIF). Inspired by the rolling guided filter, we construct the rolling weighted guided image filter (RWGIF) based on the weighted guided image filter. This filter offers progressive smoothing filtering of the image, generating smooth and detailed images. Then, we construct a novel image decomposition tool, MSRWGIF, by replacing non-subsampled shearlet transform's non-sampling pyramid filter with RWGIF to extract richer detailed information. In the first step of our method, we decompose the original images under MSRWGIF to obtain low-frequency subbands (LFS) and high-frequency subbands (HFS). Since LFS contain a large amount of energy-based information, we propose an improved local energy maximum (ILGM) fusion strategy. Meanwhile, HFS employ a fast and efficient parametric adaptive pulse coupled-neural network (AP-PCNN) model to combine more detailed information. Finally, the inverse MSRWGIF is utilized to generate the final fused image from fused LFS and HFS. To test the proposed method, we select multiple medical image sets for experimental simulation and confirm its advantages by combining seven high-quality representative metrics. The simplicity and efficiency of the method are compared with 11 classical fusion methods, illustrating significant improvements in the subjective and objective performance, especially for color medical image fusion.

A pansharpening method combining iterative filtering and NSST-NSML-PAPCNN to optimize spatial detail extraction and injection

ABSTRACT Spatial injection-based pansharpening methods are prone to spatial or spectral distortions in pansharpening images due to insufficient extraction of spatial details and a mismatch between the amount of spatial detail information injected and the required amount. To this end, this paper proposes a pansharpening method that optimizes spatial detail extraction and injection. Firstly, a method to optimize the amount of spatial detail injection is proposed, that is, to extract the high-frequency information of the image through iterative filtering and determine the optimal number of iterations based on the global analysis of the method. Then, to fully extract and combine the spatial detail information of the source image, the detailed high-frequency image extracted corresponding to the optimal iterative filtering times is decomposed by non-subsampled shearlet transform (NSST), and a new multi-scale sum-modified-Laplacian (NSML) as an external stimulus to a parameter-adaptive pulse-coupled neural network model (PAPCNN). A fusion rule based on multi-scale morphological gradients is designed to extract a small amount of detailed information for the low-frequency subband. The fused spatial detail image can be obtained by combining the fused low-frequency and high-frequency subbands and inverse NSST transformation. Finally, pansharpening can be realized by combining spatial detail image, injection coefficient, and MS image. In this paper, many experiments are carried out on the QuickBird, GeoEye-1, and WorldView-4 datasets, and quantitative and qualitative comparisons are made with eight advanced methods. Experimental results show that the method proposed in this paper can achieve better fusion results.

Multimodal brain image fusion based on error texture elimination and salient feature detection.

As an important clinically oriented information fusion technology, multimodal medical image fusion integrates useful information from different modal images into a comprehensive fused image. Nevertheless, existing methods routinely consider only energy information when fusing low-frequency or base layers, ignoring the fact that useful texture information may exist in pixels with lower energy values. Thus, erroneous textures may be introduced into the fusion results. To resolve this problem, we propose a novel multimodal brain image fusion algorithm based on error texture removal. A two-layer decomposition scheme is first implemented to generate the high- and low-frequency subbands. We propose a salient feature detection operator based on gradient difference and entropy. The proposed operator integrates the gradient difference and amount of information in the high-frequency subbands to effectively identify clearly detailed information. Subsequently, we detect the energy information of the low-frequency subband by utilizing the local phase feature of each pixel as the intensity measurement and using a random walk algorithm to detect the energy information. Finally, we propose a rolling guidance filtering iterative least-squares model to reconstruct the texture information in the low-frequency components. Through extensive experiments, we successfully demonstrate that the proposed algorithm outperforms some state-of-the-art methods. Our source code is publicly available at https://github.com/ixilai/ETEM.

Multimodal medical image fusion in NSST domain with structural and spectral features enhancement

For the past 25 years, medical imaging has been extensively used for clinical diagnosis. The main difficulties in medicine are accurate disease recognition and improved therapy. Using a single imaging modality to diagnose disease is challenging for clinical personnel. In this paper, a novel structural and spectral feature enhancement method in NSST Domain for multimodal medical image fusion (MMIF) is proposed. Initially, the proposed method uses the Intensity, Hue, Saturation (IHS) method to generate two pairs of images. The input images are then decomposed using the Non-Subsampled Shearlet Transform (NSST) method to obtain low frequency and high frequency sub-bands. Next, a proposed Structural Information (SI) fusion strategy is employed to Low Frequency Sub-bands (LFS's). It will enhance the structural (texture, background) information. Then, Principal Component Analysis (PCA) is employed as a fusion rule to High Frequency Sub-bands (HFS's) to obtain the pixel level information. Finally, the fused final image is obtained by employing inverse NSST and IHS. The proposed algorithm was validated using different modalities containing 120 image pairs. The qualitative and quantitative results demonstrated that the algorithm proposed in this research work outperformed numerous state-of-the-art MMIF approaches.