Wavelet-based Image Research Articles

DEEP NEURAL MULTI WAVELET SEGMENTATION AND RESNET-50 IMAGE CLASSIFICATION (DNMWS-RESNET-50IC) BASED EARLY GLAUCOMA DETECTION

Glaucoma, a leading cause of irreversible blindness worldwide, results from progressive damage to the optic nerve, often linked to elevated Intra Ocular Pressure (IOP). Early detection is critical for preventing vision loss, yet traditional diagnostic methods can be limited in accessibility and effectiveness, particularly in the early stages of the disease. Addressing the need for early detection, we propose the Deep Neural Multi-Wavelet Segmentation and ResNet-50 Image Classification (DNMWS-ResNet-50IC) method, specifically designed to detect glaucoma at an early stage using retinal fundus images. In this work, we apply Anisotropic Gaussian Filtering for the preprocessing of retinal fundus images, effectively reducing image noise while preserving the original quality of the image pixels by creating an adaptive window size and scale space. We then utilize multi- wavelet-based image segmentation, leveraging wavelet transforms to analyze and decompose the image into its various frequency components. This technique is particularly advantageous for managing images with complex structures and textures. Subsequently, the segmented features are classified using the ResNet-50 model, which categorizes the images as normal, abnormal, or indicative of early- stage glaucoma. The effectiveness of the proposed method is assessed by measuring three key performance indicators sensitivity, specificity, and accuracy on digital retinal images from the HRF image database. Additionally, the model's performance is further evaluated on a separate test set, considering metrics such as accuracy, precision, recall, and prediction time.

Literature Review of Wavelet-Based Image Filtering Methods

Abstract: Noise is a random signal that corrupts the quality of an image. For many decades, eliminating it or reducing its intensity in the image has been a major concern for many scientists. To this end, several studies on image processing (with the aim of eliminating or reducing the intensity of noise) have been carried out. Although a multitude of filtering methods emerged from these studies, numerous works have shown the effectiveness of the wavelet transform in image filtering. Thus, several wavelet-based methods (for image filtering purposes) have been illustrated in the literature. Some methods involve performing wavelet decomposition followed by thresholding and other methods involve combining wavelet decomposition with various filtering methods. This combination can have two or more methods. After filtering, the effectiveness of the filter can be evaluated. It is measured in terms of qualitative and/or quantitative parameters. Indeed, a filtering method is said to be efficient when the PSNR parameter (parameter most used in the literature) obtained has a minimum value of 30dB. This article presents a literature review of wavelet-based image filtering methods. Emphasis is placed on works presenting a better PSNR value (wavelet type, combination carried out, mother wavelet, decomposition number). In the end, this article gives a panoramic view of the choices of tools to use by a reader who would like to get involved in image filtering

Denoising of Digital Images Using Spatial Domain Edge Detection Approach

Better results can be produced by the Hybridization of the Wavelet-based image denoising technique and sparse representation of edges. A novel method for spatial domain edge identification that produces a denoised image that has been tainted by additive white Gaussian noise without sacrificing the image's detail information. By combining bivariate shrinkage and local profile edge detection, a denoised image is produced. In this paper, the hybridization method is proposed by modifying the existing Wavelet Transform for image denoising leading to an increase in the PSNR and SSIM as compared to that given by existing Wavelet denoising techniques, maintaining the visual quality of an image. To modify the wavelet coefficients Bivariate Wavelet Shrinkage is used. The quality assessment is evaluated in terms of SSIM value and PSNR value.

Multibranch Wavelet-Based Network for Image Demoiréing.

Moiré patterns caused by aliasing between the camera's sensor and the monitor can severely degrade image quality. Image demoiréing is a multi-task image restoration method that includes texture and color restoration. This paper proposes a new multibranch wavelet-based image demoiréing network (MBWDN) for moiré pattern removal. Moiré images are separated into sub-band images using wavelet decomposition, and demoiréing can be achieved using the different learning strategies of two networks: moiré removal network (MRN) and detail-enhanced moiré removal network (DMRN). MRN removes moiré patterns from low-frequency images while preserving the structure of smooth areas. DMRN simultaneously removes high-frequency moiré patterns and enhances fine details in images. Wavelet decomposition is used to replace traditional upsampling, and max pooling effectively increases the receptive field of the network without losing the spatial information. Through decomposing the moiré image into different levels using wavelet transform, the feature learning results of each branch can be fully preserved and fed into the next branch; therefore, possible distortions in the recovered image are avoided. Thanks to the separation of high- and low-frequency images during feature training, the proposed two networks achieve impressive moiré removal effects. Based on extensive experiments conducted using public datasets, the proposed method shows good demoiréing validity both quantitatively and qualitatively when compared with the state-of-the-art approaches.

Multi-scale gradient wavelet-based image quality assessment

Multi-scale gradient wavelet-based image quality assessment

Automated riverbed composition analysis using deep learning on underwater images

Abstract. The sediment of alluvial riverbeds plays a significant role in river systems both in engineering and natural processes. However, the sediment composition can show high spatial and temporal heterogeneity, even on river-reach scale, making it difficult to representatively sample and assess. Conventional sampling methods are inadequate and time-consuming for effectively capturing the variability of bed surface texture in these situations. In this study, we overcome this issue by adopting an image-based deep-learning (DL) algorithm. The algorithm was trained to recognise the main sediment classes in videos that were taken along cross sections underwater in the Danube. A total of 27 riverbed samples were collected and analysed for validation. The introduced DL-based method is fast, i.e. the videos of 300–400 m long sections can be analysed within minutes with continuous spatial sampling distribution (i.e. the whole riverbed along the path is mapped with images in ca. 0.3–1 m2 overlapping windows). The quality of the trained algorithm was evaluated (i) mathematically by dividing the annotated images into test and validation sets and also via (ii) intercomparison with other direct (sieving of physical samples) and indirect sampling methods (wavelet-based image processing of the riverbed images), focusing on the percentages of the detected sediment fractions. For the final evaluation, the sieving analysis of the collected physical samples were considered the ground truth. After correcting for samples affected by bed armouring, comparison of the DL approach with 14 physical samples yielded a mean classification error of 4.5 %. In addition, based upon the visual evaluation of the footage, the spatial trend in the fraction changes was also well captured along the cross sections. Suggestions for performing proper field measurements are also given; furthermore, possibilities for combining the algorithm with other techniques are highlighted, briefly showcasing the multi-purpose nature of underwater videos for hydromorphological assessment.

Bounded PCA based Multi Sensor Image Fusion Employing Curvelet Transform Coefficients

The fusion of thermal and visible images acts as an important device for target detection. The quality of the spectral content of the fused image improves with wavelet-based image fusion. However, compared to PCA-based fusion, most wavelet-based methods provide results with a lower spatial resolution. The outcome gets better when the two approaches are combined, but they may still be refined. Compared to wavelets, the curvelet transforms more accurately depict the edges in the image. Enhancing the edges is a smart way to improve spatial resolution and the edges are crucial for interpreting the images. The fusion technique that utilizes curvelets enables the provision of additional data in both spectral and spatial areas concurrently. In this paper, we employ an amalgamation of Curvelet Transform and a Bounded PCA (CTBPCA) method to fuse thermal and visible images. To evidence the enhanced efficiency of our proposed technique, multiple evaluation metrics and comparisons with existing image merging methods are employed. Our approach outperforms others in both qualitative and quantitative analysis, except for runtime performance. Future Enhancement-The study will be based on using the fused image for target recognition. Future work should also focus on this method’s continued improvement and optimization for real-time video processing.

An efficient audio watermarking scheme with scrambled medical images for secure medical internet of things systems.

In recent times, the security of communication channels between healthcare entities in Medical Internet of Things (MIoT) systems becomes a significant issue to facilitate and guarantee the exchange of medical image and expertise securely. This paper presents an efficient audio watermarking scheme employing professionally Wavelet-based Image Fusion, Arnold transforms, and Singular Value Decomposition (SVD) for the secure transmission of medical images and reports in the MIoT applications. The essential consequence of the proposed scheme is to first syndicate two medical watermarks into a fused watermark to upsurge the payload of the inserted medical images. The fused watermark is then scrambled utilizing Arnold transform. Lastly, the Arnold fused watermark is inserted in the audio signal using the SVD algorithm following converting it into a 2D format. The choice of the Arnold transform for watermark is ascribed to settling robustness that skirmishes respective types of severe attacks. Several assessment metrics such as SNR, LLR, SNRseg, SD, and Cr are used to evaluate the audio watermarked signal and extracted watermarks The results reveal that the proposed audio watermarking scheme increases the capacity with more embedded medical images and security of implanted medical images transmission deprived of affecting the quality of audio signals, especially for IoT-based Telemedicine systems.

Stationary Wavelet-Based Image Watermarking for E-Healthcare Applications

Watermarking is a technique for protecting multimedia data, mainly images, from malicious attacks by adding a signature into these images. Traditional watermarking techniques, unfortunately, have drawbacks when used on sensitive images like those used in medicine. A reliable and blind watermarking method is suggested in this work to protect medical picture transferred in telemedicine. Medical picture marking enables accurate patient identification, prevents scan confusion, and minimizes the risk of diagnostic mistakes that could have negative consequences. In this method, three distinct transforms are used to acquire the frequency content of the image. The low frequency subbands are subsequently subjected to Schur decomposition. In order to incorporate the watermark bits, the resultant upper triangular matrix values are modified. The proposed approaches effectively retain a considerable quality of watermarked images and are impressively resistant against numerous conventional attacks, according to imperceptibility and robustness experimental results. The average Peak signal-to-noise ratio (PSNR) which was obtained was 44.90 dB, demonstrating that the integration procedure produces very low distortion to the original image. The observed results for robustness demonstrate that the watermark is resilient to the most of the attacks performed in watermarking, with a normalized cross correlation rate higher than 0.9.

Multi-Task Learning with High-Dimensional Noisy Images

Recent medical imaging studies have given rise to distinct but inter-related datasets corresponding to multiple experimental tasks or longitudinal visits. Standard scalar-on-image regression models that fit each dataset separately are not equipped to leverage information across inter-related images, and existing multi-task learning approaches are compromised by the inability to account for the noise that is often observed in images. We propose a novel joint scalar-on-image regression framework involving wavelet-based image representations with grouped penalties that are designed to pool information across inter-related images for joint learning, and which explicitly accounts for noise in high-dimensional images via a projection-based approach. In the presence of nonconvexity arising due to noisy images, we derive nonasymptotic error bounds under nonconvex as well as convex grouped penalties, even when the number of voxels increases exponentially with sample size. A projected gradient descent algorithm is used for computation, which is shown to approximate the optimal solution via well-defined nonasymptotic optimization error bounds under noisy images. Extensive simulations and application to a motivating longitudinal Alzheimer’s disease study illustrate significantly improved predictive ability and greater power to detect true signals, that are simply missed by existing methods without noise correction due to the attenuation to null phenomenon. Supplementary materials for this article are available online.

Accelerating BPC-PaCo through Visually Lossless Techniques

Fast image codecs are a current need in applications that deal with large amounts of images. Graphics Processing Units (GPUs) are suitable processors to speed up most kinds of algorithms, especially when they allow fine-grain parallelism. Bitplane Coding with Parallel Coefficient processing (BPC-PaCo) is a recently proposed algorithm for the core stage of wavelet-based image codecs tailored for the highly parallel architectures of GPUs. This algorithm provides complexity scalability to allow faster execution at the expense of coding efficiency. Its main drawback is that the speedup and loss in image quality is controlled only roughly, resulting in visible distortion at low and medium rates. This paper addresses this issue by integrating techniques of visually lossless coding into BPC-PaCo. The resulting method minimizes the visual distortion introduced in the compressed file, obtaining higher-quality images to a human observer. Experimental results also indicate 12% speedups with respect to BPC-PaCo.

Effectiveness of Low-Numerical Rank Approximation to Image Compression in Wavelet Domain

In this paper, we report a modeling of approximation for images by finding numerical rank in the wavelet domain through singular value decomposition of approximation coefficients. Firstly, the digital image is transformed into the frequency domain. Then high-frequency sub-bands are quantized to zero. This is quite obvious in wavelet-based image compression. Simultaneously, the low-frequency sub-bands are compressing by using truncated singular value decomposition (TSVD) through a numerical rank. Finally, reconstruct the approximation matrix via inverse discrete wavelet transform with low computational intricacy. This mathematical model is more adequate for solving engineering problems arises in digital image processing such as the transmission of image (reducing the bandwidth size of a communication channel) and storage capacity (space saving). The simulation results on gray and color images show that there is a gain in: (i) the compression ratio with acceptable visual quality as per human vision system; (ii) balancing of performance measures over conventional SVD methods.

Learning-Based Scalable Image Compression With Latent-Feature Reuse and Prediction

Recently, learning-based image compression model has attracted much attention due to its impressive performance and ease of optimization, compared with traditional DCT and wavelet-based image compression standards. Most learning-based image compression models are trained to minimize joint rate-distortion (RD) loss on one single RD trade-off point. However, in many multimedia applications, due to communication constraints, or display adaptation needs for different spatial formats, bit rates or power, it is necessary to provide a variety of image versions for different client devices. To fulfill this requirement, typical end-to-end image compression methods have to compress an image into several bit streams independently by a number of pre-trained networks, which are resource-consuming because of redundancy among these streams. To address this problem, inspired by traditional scalable video coding framework, we propose a learning-based end-to-end quality and spatial scalable image compression (QSSIC) model in multi-layer structure, in which each layer could generate one bitstream corresponding to a specified resolution and image fidelity. This scalability is achieved by exploring the potential of feature-domain representation prediction and reuse. To be specific, firstly, bitstreams of previous layers are used to predict the current layer representations which contains the enhancement information, and then only prediction residuals need to be coded in enhancement layers. Secondly, previous bitstreams are reused in image reconstruction in higher layers to provide basic information. The proposed model could be optimized in an end-to-end manner. Extensive experiments show that our method outperforms state-of-art deep neural networks (DNN)-based auto-encoders in simulcast scenarios. In addition, our method has a better performance than the traditional scalable image compression method scalable extension of H.264/AVC (SVC) and is comparable to scalable extension of H.265/HEVC (SHVC).

Wavelet-Based Multi-Focus Image Fusion Using Average Method Noise Diffusion (AMND)

Aim: This paper presents a new and upgraded wavelet-based multi-focus image fusion technique using average method noise diffusion (AMND). Objective: Improved visual appearance of the final image, no blurring in the final fused image and clearly visible objects (fine edges). Methods: This method extends the standard wavelet-based image fusion technique on multi-focus images by incorporating the hybrid of method noise and anisotropic diffusion in it. This hybrid structure of method noise and anisotropic diffusion is implemented as the post-processing operation in the proposed method. Results: The proposed work shows excellent results in terms of visual appearance and edge preservation. The experimental results of the proposed method are compared with some of the traditional and non-traditional approaches where the proposed method shows comparatively better results. Conclusion: This paper depicts the robustness, effectiveness and adaptive nature of method noise in the field of image enhancement especially in the field of image fusion. The performance of the proposed method is analyzed qualitatively (good visual appearance) and quantitatively (entropy, spatial frequency, and standard deviation). This method has the capability to be incorporated in real-time applications like surveillance in the visual sensor network (VSN).

Hydraulic fracture mapping using wavelet-based fusion of wave transmission and emission measurements

Fracture characterization is essential to hydrocarbon and geothermal exploration and production as well as carbon geo-sequestration. Active and passive measurements have been extensively applied to map fractures across various scales. Active and passive methods have inherent advantages and limitations that complement each other. In this study, to improve the mapping of embedded fractures and the surrounding geomechanically altered regions, we integrate active shear-wave transmission measurement with passive acoustic-emission measurement collected during a lab-scale hydraulic-fracturing experiment. The proposed data fusion leverages the advantages of the two modalities of measurements, while minimizing their individual limitations. Polarized shear-wave transmission (active) measurement was collected before and after the hydraulic fracturing, and the acoustic emission (passive) measurement was collected during hydraulic fracturing. Two sets of two-dimensional maps of fracture and fracture-induced damage in axial, median and frontal planes were obtained by separately processing active and passive measurements. These 2D maps are then fed to wavelet-based image fusion technique to integrate the two sources of information for the reliable mapping/imaging of the embedded fractures and the surrounding geomechanically altered regions.

A Novel approach in Hybrid Median Filtering for Denoising Medical images

Image denoising is a key pre-processing step in medical image analysis. At current, deep learning-based models have shown a great promise, which outperformed many conventional methods over the past three decades. Speckle noise removal is a major issue in preserving all the delicate details and the edges in ultrasound image processing as it degrades the visual evaluation of ultrasound images. The multiplicative behavior of speckle-noise is converted into additive by using log transform as the additive noise removal is easy as compared to multiplicative noise. An innovative approach for denoising highly distorted images affected by speckle noise is proposed. This paper presents a result of significant work in image denoising and exploring several thresholding methods of denoising images such as SureShrink, VisuShrink and BayesShrink. The results of different approaches of wavelet-based image denoising methods are tabulated to find the best method. The main aim is to show the result of wavelet coefficients on a new basis, so that the noise can be minimized or removed from the data.

Fast Adaptive Augmented Lagrangian Digital Image Correlation

Digital image correlation (DIC) is a powerful experimental technique for measuring full-field displacement and strain. The basic idea of the method is to compare images of an object decorated with a speckle pattern before and after deformation in order to compute the displacement and strain fields. Local Subset DIC and finite element-based Global DIC are two widely used image matching methods; however there are some drawbacks to these methods. In Local Subset DIC, the computed displacement field may not satisfy compatibility, and the deformation gradient may be noisy, especially when the subset size is small. Global DIC incorporates displacement compatibility, but can be computationally expensive. In this thesis, we propose a new method, the augmented-Lagrangian digital image correlation (ALDIC), that combines the advantages of both the local (fast and in parallel) and global (compatible) methods. We demonstrate that ALDIC has higher accuracy and behaves more robustly compared to both Local Subset DIC and Global DIC. DIC requires a large number of high resolution images, which imposes significant needs on data storage and transmission. We combined DIC algorithms with image compression techniques and show that it is possible to obtain accurate displace- ment and strain fields with only 5 % of the original image size. We studied two compression techniques – discrete cosine transform (DCT) and wavelet transform, and three DIC algorithms – Local Subset DIC, Global DIC and our newly proposed augmented Lagrangian DIC (ALDIC). We found the Local Subset DIC leads to the largest errors and ALDIC to the smallest when compressed images are used. We also found wavelet-based image compression introduces less error compared to DCT image compression. To further speed up and improve the accuracy of DIC algorithms, especially in the study of complex heterogeneous strain fields at various length scales, we apply an adaptive finite element mesh to DIC methods. We develop a new h-adaptive technique and apply it to ALDIC. We show that this adaptive mesh ALDIC algorithm significantly decreases computation time with no loss (and some gain) in accuracy.

Charge Injection Device Extreme Contrast Imaging of the Sirius Field

Abstract The intrinsic nature of many astronomical objects, such as binary systems, exoplanets, circumstellar disks, and quasar host galaxies, introduces challenging requirements on observational instrumentation and techniques. In each case, we encounter situations where the light from bright sources completely outshines the surrounding faint targets. As a result, we are yet to fully understand the processes governing star and galaxy formation and evolution, and there are ongoing attempts to search for habitable worlds around other stars. To explore all features of such astronomical objects, we must perform observations at the maximum possible contrast ratios. Here, we demonstrate the extreme contrast ratio imaging capabilities of the latest generation of commercially available charge injection devices, the SpectraCAM XDR, using Sirius field observations from a world-class observing site. Based on wavelet-based image analysis and precise photometric calibration, we report a direct contrast ratio of 1 part in 100 million.

An efficient wavelet-based image fusion for brain tumor detection and segmentation over PET and MRI image

A brain tumor is an abnormal growth of cells, reproducing themselves in an uncontrolled manner. In a medical diagnosis system, the accurate detection of location and size plays a very important role in the diagnosis of brain tumors. Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) are the most widely used techniques for diagnosis. The detection of a brain tumor in PET and MRI images is a challenging task due to its low sensitive boundary pixels. For accurate detection of brain tumors, in this paper, an efficient fusion-based brain tumor detection and segmentation is proposed. Here, at first, we fuse the input image using a discrete wavelet transform (DWT) and novel fusion rule. After the fusion process, the gray-level co-occurrence matrix (GLCM) features are extracted. Then, we categorize the brain images as normal and abnormal images using Optimal Deep Neural Network (ODNN). Here, the network weights of DNN are optimally selected using Spider Monkey Optimization (SMO) algorithm. After the classification process, the brain tumor region is extracted from abnormal brain images using the weighted k-means technique. The performance of the proposed methodology is analyzed in terms of sensitivity, specificity, and accuracy.

A survey of various wavelet-based image retrieval techniques and tuning of hyperparameters

A survey of various wavelet-based image retrieval techniques and tuning of hyperparameters