Low-frequency Image Research Articles

Imaging of ventilation and lung injury with low-frequency tomographic ultrasound.

Mechanical ventilation in the intensive care unit (ICU) is a life-saving technique for patients with acute respiratory failure, but is also associated with a high incidence of complications in the injured lung. Currently, there is no widely used monitoring technique to guide the ventilator setting to facilitate a precision medicine approach or to provide a real-time alert for developing adverse pulmonary conditions. Conventional ultrasound has been used as a thoracic bedside technology, but the lack of signal penetration into lung tissue results in images that often contain more information in their artifacts than in the images themselves. Perhaps the greatest obstacle to using traditional ultrasound in the ICU is the need for highly skilled technicians to perform the data collection. In contrast, low-frequency ultrasound (50-500 kHz) has been shown to penetrate the lung, and can detect air trapping in patients with chronic obstructive pulmonary disease (COPD). Here, we present a method of collecting low-frequency ultrasound computed tomographic (USCT) data in vivo on a mechanically ventilated porcine model and computing tomographic reconstructions of airflow during tidal breathing and induced lung injuries. We evaluate the ability of the novel low-frequency USCT system to image regional changes in sound speed in the thorax due to changes in airflow during tidal breathing and induced lung injuries. This represents the first study of low-frequency tomographic ultrasound imaging in vivo and the first to produce tomographic images of ventilatory changes invivo. USCT and computed tomography (CT) scan data were collected alternately on a mechanically ventilated Landrace pig weighing approximately 75 kg during tidal breathing, induced pneumothorax, atelectasis, and pleural effusion. The pneumothorax was induced by injecting air through a 5 mm thick intrathoracic tube inserted in the 8th posterior intercostal space. After removing the air, atelectasis was induced by ventilating the animal with a high concentration of oxygen and low tidal volumes. The pleural effusion was induced by injecting a saline solution through the tube. The USCT data were collected at 125 kHz using the USCT low-frequency ultrasound tomography (LUFT) system on a transducer belt placed around the animal's thorax. Tomographic reconstructions were computed from the USCT data using a regularized refraction-corrected Gauss-Newton-based time-of-flight reconstructionalgorithm. Cyclic changes in computed lung area during tidal breathing were demonstrated to agree with the respiratory rate on the mechanical ventilator. Reconstructed images computed at time steps during the procedure demonstrate regional changes consistent with what would be expected during the induced lung injury. No ground truth was available for images during the procedures since CT scans could only be taken before and after each established lunginjury. In this work, we have demonstrated in the first in vivo study using a mechanically ventilated porcine animal model that low-frequency ultrasound tomography has the ability to image regional changes in sound speed in the thorax corresponding to changes in airflow during tidal breathing and induced lung injury. The results show promise for using low-frequency USCT as a bedside imaging technique in the future for patients with acute respiratory distresssyndrome.

Underwater Bubble Plume Recognition Algorithm Based on Multi-Feature Fusion Understanding

Underwater bubble plume images contain a wealth of information on wave field and flow characteristics, which can provide valuable research data for marine development, environmental protection, and underwater surveys. However, based on fusing image features and wave field environment features, identifying accurately the underwater bubble plume is still very difficult. In order to improve the accuracy and robustness of bubble plume identification in complex underwater environments, an underwater bubble plume recognition algorithm based on multi-feature fusion understanding is proposed. In this paper, a weight-independent dual-channel residual convolutional neural network (CNN) for feature extraction of the original optical images and the nonsubsampled contourlet transform (NSCT) low-frequency images, and the multi-scale composite feature map groups are generated. Then adaptive fusion is performed based on the feature contribution of the target in different types of images. Next, logical region of interest (ROI) masks are generated by the attention mechanism and superimposed on the fused image to further highlight the target features. Finally, the multi-scale dual-channel fused feature maps containing ROI masks are used for underwater bubble plume target recognition. The experimental results show that the designed recognition network can effectively fuse the features of the original optical images and the NSCT low-frequency imagers, improve the depth of information fusion, and retain the target texture features and the morphological features while reducing the interference of the background information, and have good recognition accuracy and robustness for multi-scale bubble targets in the underwater environment.

Infrared and visible image fusion method based on target enhancement and rat swarm optimization

In order to solve the target ambiguity and information loss in the fusion results of traditional infrared and visible images, a fusion method of infrared and visible images based on the target enhancement and mouse swarm optimization, which is abbreviated as TERSFuse. Firstly, in order to reduce the loss of the original image details in the fusion results, the infrared contrast enhancement module and the visible image enhancement module based on the brightness perception are constructed respectively. Secondly, the infrared and visible enhanced images were decomposed by using the Laplace pyramid transform to obtain the corresponding high and low frequency images. In order to make the fusion result fully retain the original information, the "maximum absolute value" rule is used to fuse the infrared and visible high frequency images, and the low frequency images are fused by calculating the weight coefficient. Finally, the image reconstruction module based on the rat swarm optimization is designed to achieve the adaptive allocation of weight parameters of high frequency and low frequency image reconstruction, and then improve the visual effect of the fused image. In order to verify the advantages of the present algorithm, the experimental results show that the present algorithm not only obtains the good visual effects, but also can retains the rich edge texture and contrast information of the original image.

Flicker adaptation improves acuity for briefly presented stimuli by reducing crowding.

Adaptation to flickering/dynamic noise improves visual acuity for briefly presented stimuli (Arnold et al., 2016). Here, we investigate whether such adaptation operates directly on our ability to see detail or by changing fixational eye movements and pupil size or by reducing visual crowding. Following earlier work, visual acuity was measured in observers who were either unadapted or who had adapted to a 60-Hz flickering noise pattern. Participants reported the orientation of a white tumbling-T target (four-alternative forced choice [4AFC], ⊤⊣⊥⊢). The target was presented for 110 ms either in isolation or flanked by randomly oriented T's (e.g., ⊣⊤⊢) followed by an isolated (+) or flanked (+++) mask, respectively. We measured fixation stability (using an infrared eye tracker) while observers performed the task (with and without adaptation). Visual acuity improved modestly (around 8.4%) for flanked optotypes following adaptation to flicker (mean, -0.038 ± 0.063 logMAR; p = 0.015; BF10 = 3.66) but did not when measured with isolated letters (mean, -0.008 ± 0.055 logMAR; p = 0.5; BF10 = 0.29). The magnitude of acuity improvement was associated with individuals' (unadapted) susceptibility to crowding (the ratio of crowded to uncrowded acuity; r = -0.58, p = 0.008, BF10 = 7.70) but to neither fixation stability nor pupil size. Confirming previous reports, flicker improved acuity for briefly presented stimuli, but we show that this was only the case for crowded letters. These improvements likely arise from attenuation of sensitivity to a transient low spatial frequency (SF) image structure (Arnold et al., 2016; Tagoh et al., 2022), which may, for example, reduce masking of high SFs by low SFs. We also suggest that this attenuation could reduce backward masking and so reduce foveal crowding.

Self-supervised tomographic image noise suppression via residual image prior network

Computed tomography (CT) denoising is a challenging task in medical imaging that has garnered considerable attention. Supervised networks require a lot of noisy-clean image pairs, which are always unavailable in clinical settings. Existing self-supervised algorithms for suppressing noise with paired noisy images have limitations, such as ignoring the residual between similar image pairs during training and insufficiently learning the spectrum information of images. In this study, we propose a Residual Image Prior Network (RIP-Net) to sufficiently model the residual between the paired similar noisy images. Our approach offers new insights into the field by addressing the limitations of existing methods. We first establish a mathematical theorem clarifying the non-equivalence between similar-image-based self-supervised learning and supervised learning. It helps us better understand the strengths and limitations of self-supervised learning. Secondly, we introduce a novel regularization term to model a low-frequency residual image prior. This can improve the accuracy and robustness of our model. Finally, we design a well-structured denoising network capable of exploring spectrum information while simultaneously sensing context messages. The network has dual paths for modeling high and low-frequency compositions in the raw noisy image. Additionally, context perception modules capture local and global interactions to produce high-quality images. The comprehensive experiments on preclinical photon-counting CT, clinical brain CT, and low-dose CT datasets, demonstrate that our RIP-Net is superior to other unsupervised denoising methods.

Hierarchical disentangled representation for image denoising and beyond

Image denoising is a typical ill-posed problem due to complex degradation. Leading methods based on normalizing flows have tried to solve this problem with an invertible transformation instead of a deterministic mapping. However, it is difficult to construct feasible bijective mapping to remove spatial-variant noise while recovering fine texture and structure details due to latent ambiguity in inverse problems. Inspired by a common observation that noise tends to appear in the high-frequency part of the image, we propose a fully invertible denoising method that injects the idea of disentangled learning into a general invertible architecture to split noise from the high-frequency part. More specifically, we decompose the noisy image into clean low-frequency and hybrid high-frequency parts with an invertible transformation and then disentangle case-specific noise and high-frequency components in the latent space. In this way, denoising is made tractable by inversely merging noiseless low and high-frequency parts. Furthermore, we construct a flexible hierarchical disentangling framework, which aims to decompose most of the low-frequency image information while disentangling noise from the high-frequency part in a coarse-to-fine manner. Extensive experiments on real image denoising, JPEG compressed artifact removal, and medical low-dose CT image restoration have demonstrated that the proposed method achieves competitive performance on both quantitative metrics and visual quality, with significantly less computational cost.

Low-Frequency Coherent Raman Imaging Robust to Optical Scattering.

We demonstrate low-frequency interferometric impulsive stimulated Raman scattering (ISRS) imaging with high robustness to distortions by optical scattering. ISRS is a pump-probe coherent Raman spectroscopy that can capture Raman vibrational spectra. Recording of ISRS spectra requires isolation of a probe pulse from the pump pulse. While this separation is simple in nonscattering specimens, such as liquids, scattering leads to significant pump pulse contamination and prevents the extraction of a Raman spectrum. We introduce a robust method for ISRS microscopy that works in complex scattering samples. High signal-to-noise ISRS spectra are obtained even when the pump and probe pulses pass through many scattering layers.

Modern high-tech approaches to the diagnosis of gastrointestinal diseases

The article discusses modern high-tech approaches to the diagnosis of gastrointestinal diseases. Revealing the relevance of the problem and the importance of accurate and timely diagnosis for the successful treatment of patients, the authors draw attention to the latest methods and technologies used in this field of medicine. The article discusses various diagnostic methods, including endoscopy, ultrasound, computed tomography, magnetic resonance imaging, molecular genetic analyses, as well as the use of artificial intelligence and machine learning to analyze medical data. The advantages and limitations of each method, their effectiveness and development prospects are discussed. The question is also raised about the need for an integrated approach to diagnosis, including a combination of various methods to improve the accuracy and reliability of the results. It is concluded that low-frequency imaging technologies provide a promising strategy for diagnosing diseases of the gastrointestinal tract. These technologies provide more complete information about the disease by integrating multiple contrast agents for imaging.

PW-NeRF: Progressive wavelet-mask guided neural radiance fields view synthesis

Neural Radiance Fields (NeRF) can achieve state-of-the-art new view results when given a sufficient number of training views. However, NeRF's rendering is based on minimizing photometric consistency loss, and during the optimization process, it can suffer from overfitting due to factors such as lighting and texture, resulting in poor geometric and color reconstruction. The less data there is in the overlapping areas of the images, the greater the impact on the results, such as insufficient data caused by occlusion relationships. In this paper, we observed through experiments that introducing low-frequency images into NeRF during training can quickly obtain approximate geometric structures, which can guide NeRF to achieve more stable view synthesis results. Therefore, we propose a progressive wavelet mask to assist in the training of neural radiance fields. By first constructing a gaussian pyramid for the training images and then applying wavelet decomposition to them, we can obtain a series of low-frequency region masks to guide the neural radiance field to focus on learning low-frequency pixel regions and gradually introduce high-frequency lighting and texture changes. Our experiments on the LLFF and Blender datasets show that using a progressive wavelet mask in NeRF training can achieve more realistic generation effects with almost no additional computational overhead. At the same time, we also tested our method in sparse scenes, where it still performs well in avoiding overfitting.

Image inpainting based on GAN-driven structure- and texture-aware learning with application to object removal

In this paper, a novel deep learning-based image inpainting framework consisting of restoring image structure and reconstructing image details from corrupted images is proposed. Most image inpainting methods in the literature aim at restoring image details, outlines, and colors, simultaneously, which may suffer from blurring, deformation, and unreasonable content recovery due to interference among various information. To solve these problems, a two-stage image inpainting deep neural network based on GAN (generative adversarial network) architecture is proposed. The proposed inpainting framework consists of two modules: (1) the first stage, called the structure-aware learning stage, aims at learning a GAN-based structure restoration network, focusing on recovering the low-frequency image component, including colors and outlines of the missing regions of the input corrupted image; and (2) the second stage, called the texture-aware learning stage, aims at learning a GAN-based detail refinement network, focusing on rebuilding the high-frequency image details and texture information. In particular, we also propose to remove details from the training images to better train the structure restoration network to avoid inadequate image structure recovery induced by richer image textures, where the detail reconstruction task is left to the second stage. This strategy achieves to balance the workload between the two stages and the image quality can be progressively enhanced through the two stages. Experimental results have shown that the proposed deep inpainting framework quantitatively and qualitatively achieves state-of-the-art performance on the well-known datasets, including the CelebA, Places2, and ImageNet datasets, compared with existing deep learning-based image inpainting approaches. More specifically, in terms of the two well-known image quality assessment metrics, PSNR (peak signal-to-noise ratio) and SSIM (structural similarity), the improvement percentage of the proposed method, compared with the baseline approach, respectively, ranges from 3.23 % to 11.12 %, and 1.95 % to 13.39 %. The improvements have been shown to stably and significantly outperform the compared state-of-the-art methods in most types of inpainting mask. We also show that the proposed method is applicable to image editing in object removal from a single image.

Fusion of full-field optical angiography images via gradient feature detection

Full-field optical angiography (FFOA)—a real-time non-invasive imaging technique for extracting biological blood microcirculation information—contributes to an in-depth understanding of the functional and pathological changes of biological tissues. However, owing to the limitation of the depth-of-field (DOF) of optical lenses, existing FFOA imaging methods cannot capture an image containing every blood-flow information. To address this problem, this study develops a long-DOF full-field optical angiography imaging system and proposes a novel multi-focus image fusion scheme to expand the DOF. First, FFOA images with different focal lengths are acquired by the absorption intensity fluctuation modulation effect. Second, an image fusion scheme based on gradient feature detection in a nonsubsampled contourlet transform domain is developed to capture focus features from FFOA images and synthesize an all-focused image. Specifically, FFOA images are decomposed by NSCT into coefficients and low-frequency difference images; thereafter, two gradient feature detection-based fusion rules are used to select the pre-fused coefficients. The experimental results of both phantom and animal cases show that the proposed fusion method can effectively extend the DOF and address practical FFOA image defocusing problems. The fused FFOA image can provide a more comprehensive description of blood information than a single FFOA image.

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.

Low-frequency ultrasonic array imaging for detecting concrete structural defects in blind zones

Ultrasonic array (UA) imaging is a promising non-destructive testing (NDT) method that is extensively used for defect detection. Due to the high attenuation characteristics of ultrasonic wave propagation in concrete structures and the directivity of sensors, the total focus method (TFM) easily misses specific defects in blind zones that are far from the sensors or located at a large deflection angle. To overcome this limitation, the diffusion attenuation compensation factor and solid directivity correction factor are adopted to improve the scattered signal energy of defects that are in blind zones. On this basis, the diffusion attenuation compensation method (DACM), the solid directivity correction method (SDCM), and the diffusion attenuation compensation-based solid directivity correction method (DAC-SDCM) are proposed. These methods are applied to characterize multiple circular holes in concrete structures using the dry point contact (DPC) low-frequency UA, and the detection results are evaluated from the intensity curve and detection area of ultrasonic images. The numerical and experimental results indicate that DACM is suitable for detecting defects located at longer distances, SDCM is capable of detecting defects located at larger deflection angles, and DAC-SDCM can significantly improve the detection performance of defects that are distant and have large deflection angles. The findings demonstrate that the proposed methods can significantly improve the detection ability of defects in blind zones and broaden the application of DPC low-frequency UA in the health monitoring of concrete structures.

Low-frequency Radio Interferometric Array Imaging Pipeline Optimization Based on Distributed Execution Framework

The Square Kilometre Array (SKA) project is an international collaboration to build the world’s largest radio telescope, whose sensitivity and measurement speed will be an order of magnitude higher than those of all current radio telescopes. Radio continuum survey is one of the main observation mode of the SKA, and the establishment of a standard map of the survey area based on continuum imaging will provide an important foundation for subsequent astronomical science. The GaLactic and Extragalactic All-sky Murchison Widefield Array survey eXtended (GLEAM-X) is a project of the SKA pilot telescope Murchison Widefield Array (MWA) in 2018—2020. GLEAM-X is a new radio continuum survey project to be carried out with the MWA Phase II expansion array in 2018—2020. The experience of optimizing the imaging pipeline based on the distributed execution framework will help to solve the problem of massive data processing. In this paper, we describe the process steps of GLEAM-X imaging pipeline, integrate and improve it, and realize parallel processing of multiple pipelines on the China SKA Regional Centre Prototype (CSRC-P), and verify the deployment and test the correctness of the imaging pipeline system using GLEAM-X observation data. The GLEAM-X observations were used to validate the deployment of the imaging pipeline system and test its correctness. Then, to optimize the pipelines and improve the processing efficiency, the Data Activated Liu Graph Engine (DALiuGE) was used to integrate the imaging pipelines into the DALiuGE execution framework to automate the distributed parallel processing of the pipelines. Performance tests and results’ analysis show that the optimized imaging pipeline based on the DALiuGE execution framework has better performance, more flexible adaptability, and scalability than the traditional parallel approach, and can support future large-scale continuum imaging experiments during the first phase of SKA commissioning.

FSformer: A combined frequency separation network and transformer for LDCT denoising

Low-dose computed tomography (LDCT) has been widely concerned in the field of medical imaging because of its low radiation hazard to humans. However, under low-dose radiation scenarios, a large amount of noise/artifacts are present in the reconstructed image, which reduces the clarity of the image and is not conducive to diagnosis. To improve the LDCT image quality, we proposed a combined frequency separation network and Transformer (FSformer) for LDCT denoising. Firstly, FSformer decomposes the LDCT images into low-frequency images and multi-layer high-frequency images by frequency separation blocks. Then, the low-frequency components are fused with the high-frequency components of different layers to remove the noise in the high-frequency components with the help of the potential texture of low-frequency parts. Next, the estimated noise images can be obtained by using Transformer stage in the frequency aggregation denoising block. Finally, they are fed into the reconstruction prediction block to obtain improved quality images. In addition, a compound loss function with frequency loss and Charbonnier loss is used to guide the training of the network. The performance of FSformer has been validated and evaluated on AAPM Mayo dataset, real Piglet dataset and clinical dataset. Compared with previous representative models in different architectures, FSformer achieves the optimal metrics with PSNR of 33.7714 dB and SSIM of 0.9254 on Mayo dataset, the testing time is 1.825 s. The experimental results show that FSformer is a state-of-the-art (SOTA) model with noise/artifact suppression and texture/organization preservation. Moreover, the model has certain robustness and can effectively improve LDCT image quality.

Efficient Lightweight Image Denoising with Triple Attention Transformer

Transformer has shown outstanding performance on image denoising, but the existing Transformer methods for image denoising are with large model sizes and high computational complexity, which is unfriendly to resource-constrained devices. In this paper, we propose a Lightweight Image Denoising Transformer method (LIDFormer) based on Triple Multi-Dconv Head Transposed Attention (TMDTA) to boost computational efficiency. LIDFormer first implements Discrete Wavelet Transform (DWT), which transforms the input image into a low-frequency space, greatly reducing the computational complexity of image denoising. However, the low-frequency image lacks fine-feature information, which degrades the denoising performance. To handle this problem, we introduce the Complementary Periodic Feature Reusing (CPFR) scheme for aggregating the shallow-layer features and the deep-layer features. Furthermore, TMDTA is proposed to integrate global context along three dimensions, thereby enhancing the ability of global feature representation. Note that our method can be applied as a pipeline for both convolutional neural networks and Transformers. Extensive experiments on several benchmarks demonstrate that the proposed LIDFormer achieves a better trade-off between high performance and low computational complexity on real-world image denoising tasks.

Spatially resolved radio signatures of electron beams in a coronal shock

Context. Type II radio bursts are a type of solar radio bursts associated with coronal shocks. Type II bursts usually exhibit fine structures in dynamic spectra that represent signatures of accelerated electron beams. So far, the sources of individual fine structures in type II bursts have not been spatially resolved in high-resolution low-frequency radio imaging. Aims. The objective of this study is to resolve the radio sources of the herringbone bursts found in type II solar radio bursts and investigate the properties of the acceleration regions in coronal shocks. Methods. We used low-frequency interferometric imaging observations from the Low Frequency Array to provide a spatially resolved analysis for three herringbone groups (A, B, and C) in a type II radio burst that occurred on 16 October 2015. Results. The herringbones in groups A and C have a typical frequency drift direction and a propagation direction along the frequency. Their frequency drift rates correspond to those of type III bursts and previously studied herringbones. Group B has a more complex spatial distribution, with two distinct sources separated by 50 arcsec and no clear spatial propagation with frequency. One of the herringbones in group B was found to have an exceptionally large frequency drift rate. Conclusions. The characteristics derived from imaging spectroscopy suggest that the studied herringbones originate from different processes. Herringbone groups A and C most likely originate from single-direction beam electrons, while group B may be explained by counterstreaming beam electrons.

Multi-Frequency Ultrasound Imaging Fusion Method Based on Wavelet Transform for Guided Screw Insertion.

Intraosseous ultrasound imaging can serve as a guiding tool for the placement of pedicle screws during spinal fusion surgery; thus far, there has been limited scholarly exploration of methods for intraosseous multifrequency ultrasound imaging, which can achieve simultaneous high resolution and deep penetration. The proposed method introduced a dynamic fusion strategy grounded in wavelet transformation for multifrequency image decomposition. This strategy accomplished the effective amalgamation of high-frequency ultrasound images and low-frequency ultrasound images, enabling the obtaining of fused images with enhanced details and better overall image quality. A novel near-field effect elimination method was also proposed to improve the quality of ultrasound imaging in the near-field region. Experimental evaluations were conducted on isolated bovine circle bone and sheep spine with pedicle screw tracks. The fusion images are capable of effectively detecting areas within the pedicle screw track that have either ruptured or are in close proximity to rupture, even measuring the size of breaches. Evaluation criteria, including information entropy (IE), spatial frequency (SF), average gradient (AG), mutual information (MI), structural similarity index (SSIM), and edge information-based image fusion quality metric (QAB/F), were employed to assess the fusion performance; moreover, the influence of mother wavelet function selection and decomposition levels on computational complexity and fusion image quality was thoroughly discussed. The proposed method exhibited promising potential for intraosseous imaging navigation, which can aid in accurate diagnosis, treatment planning, and monitoring in fields such as orthopedics, surgery, and interventional procedures.

SuperPCA and 2-D compact variational mode decomposition for feature extraction from hyperspectral images

ABSTRACT The 2-D compact variational mode decomposition (2-D-C-VMD) has potential research significance in data mining of hyperspectral images (HSIs). The paper proposes a method of concatenation of features. First, the 2-D-C-VMD technique is used to decompose the HSIs to obtain smooth and clear boundary sub-band images when the 2-D-C-VMD takes the most preferred a priori parameter K × . Second, the optimal low-frequency component features of the image and the optimal high-frequency component constructed features are concatenated first and last, and the structure of the concatenation is constructed into a new fused data. Finally, in order to avoid the redundancy of the fused data band information from affecting the classification result, combine a recently developed simple and practical superpixelwise principal component analysis (SuperPCA) dimensionality reduction method to effectively reduce the dimensionality of the fused data. By comparing the analysis with relying only on the optimal low-frequency image feature information and with the direct linear superposition fusion that has been employed, it is verified that the concatenation of features approach proposed in this paper can obtain better recognition results.

Neural Network-Based Algorithm for Identification of Recaptured Images

With the improvement of digital image display technology, the “secondary imaging” caused by digital cameras is also gradually popularized, and the quality of the recaptured image formed by this imaging is also getting higher and higher, and this kind of high-quality fake image has caused great threat to digital images security. We propose a neural network-based recaptured image identification algorithm and use the difference between two types of images to build the identification algorithm in the frequency domain. The algorithm uses filtering to obtain the feature images which are the high-frequency and low-frequency filtering images, in order to further distinguish the image differences, the direction of the filtered image obtained from high-frequency images, each direction of the filtered image contains high-frequency information at different angles, and the low-frequency image is downsampled. At the same time, the low-frequency image is downsampled to obtain a multi-scale filtered image. The algorithm extracts the features from previous images as the feature values for classification, and finally uses neural networks for classification to obtain the classification results, and these prove that the algorithm presented is able to differentiate the recaptured images effectively in this paper.