Image Pixels Research Articles

Enhancing healthcare cloud security with intelligent shuffled frog leaping optimized sequential long short-term memory (ISFLO-SLSTM)

Although medical image processing consumes much memory, computing time and specialized platforms are needed. As a result, it is crucial to implement cost-effective solutions to replace outdated ones. Due to these factors, we choose to adopt cloud computing to satisfy our needs for large-scale data processing. Meanwhile, this strategy offers accessibility to services upon request with excellent reliability and versatility. Therefore, employing cloud services rather than internal applications will assist healthcare organizations in outsourcing calculations to a third party, thereby reducing operating costs. However, to avoid malicious data leaks, comprehensive protection of information across unauthorized users and untrustworthy clouds is necessary. Different frameworks are created to allow consumers to save and analyze their information utilizing cloud-based computing. They are developed utilizing distributed systems, cryptosystems, or an amalgam of the two. The primary issue with applying cryptography methods for the enormous analysis of information on the cloud is the computing cost of image processing operations. Preventing unauthorized usage of healthcare records and private health details is the main concern. To secure data processing in a cloud environment by classifying image pixels, we offer a revolutionary intelligent shuffled frog jumping optimized sequential long short-term memory (ISFLO-SLSTM) approach. We added an additional layer, the cloud security module, to lower the danger of future medical data leakage. The effectiveness of the suggested strategy is assessed using medical RGB images taken from the Kaggle database. The findings of this study show how the ISFLO-SLSTM system has the potential to revolutionize healthcare information analysis by protecting patient privacy and security that utilizes the full extent of the latest machine learning methods.

Building Coarse to Fine Convex Hulls With Auxiliary Vertices for Palette-Based Image Recoloring.

Constructing a convex hull for the pixel colors of an image by viewing them as 3D points can extract a set of palette colors for the image, then image recoloring can be achieved by modifying the palette colors. For better recoloring effect, the convex hull should contain more pixels (inclusive) and be more compact. Otherwise, reconstruction error would occur or the extracted palette color would be less representative, yielding wrong recoloring results or less effective edit. We observe that convex hulls constructed by prior methods can contain all the image pixels, but are far from compact. Efforts have been made to optimize the vertices of convex hull to increase the compactness but are still not perfect. In this paper, we propose a novel coarse to fine convex hull construction scheme with auxiliary vertices. We start by constructing a coarse convex hull whose vertices are directly image pixels which is thus the most compact but cannot contain all pixels. We then make a remedy by adding auxiliary vertices into the coarse convex hull to obtain a fine convex hull. More auxiliary vertices are added, more image pixels will be contained into the fine convex hull. The auxiliary vertices are image pixels too so that the compactness can still be maintained. During editing, the auxiliary vertices are not allowed to be edited for edit convenience, but deformed as-rigid-as-possible with the adjusting of other vertices. Our convex hull is both inclusive and compact. Extensive experiments validate the effectiveness of the proposed method.

Pixel embedding for grayscale medical image classification

In our paper, we present an extension of text embedding architectures for grayscale medical image classification. We introduce a mechanism that combines n-gram features with an efficient pixel flattening technique to preserve spatial information during feature representation generation. Our approach involves flattening all pixels in grayscale medical images using a combination of column-wise, row-wise, diagonal-wise, and anti-diagonal-wise orders. This ensures that spatial dependencies are captured effectively in the feature representations. To evaluate the effectiveness of our method, we conducted a benchmark using 5 grayscale medical image datasets of varying sizes and complexities. 10-fold cross-validation showed that our approach achieved test accuracy score of 99.92 % on the Medical MNIST dataset, 90.06 % on the Chest X-ray Pneumonia dataset, 96.94 % on the Curated Covid CT dataset, 79.11 % on the MIAS dataset and 93.17 % on the Ultrasound dataset. The framework and reproducible code can be found on GitHub at https://github.com/xizhou/pixel_embedding.

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.

SkinNet-14: a deep learning framework for accurate skin cancer classification using low-resolution dermoscopy images with optimized training time

The increasing incidence of skin cancer necessitates advancements in early detection methods, where deep learning can be beneficial. This study introduces SkinNet-14, a novel deep learning model designed to classify skin cancer types using low-resolution dermoscopy images. Unlike existing models that require high-resolution images and extensive training times, SkinNet-14 leverages a modified compact convolutional transformer (CCT) architecture to effectively process 32 × 32 pixel images, significantly reducing the computational load and training duration. The framework employs several image preprocessing and augmentation strategies to enhance input image quality and balance the dataset to address class imbalances in medical datasets. The model was tested on three distinct datasets—HAM10000, ISIC and PAD—demonstrating high performance with accuracies of 97.85%, 96.00% and 98.14%, respectively, while significantly reducing the training time to 2–8 s per epoch. Compared to traditional transfer learning models, SkinNet-14 not only improves accuracy but also ensures stability even with smaller training sets. This research addresses a critical gap in automated skin cancer detection, specifically in contexts with limited resources, and highlights the capabilities of transformer-based models that are efficient in medical image analysis.

Single Pixel Imaging Based on Multiple Prior Deep Unfolding Network

Single Pixel Imaging Based on Multiple Prior Deep Unfolding Network

Intramuscular Adipose Tissue in the Lumbar Paraspinal Muscles Does Not Correlate With Low Back Pain in Medical Students

Objective: The objective of the study is to identify any intergroup differences or statistically significant correlations between paraspinal intramuscular adipose tissue (IntraMAT) deposition and variables such as low back pain, gender, self-reported activity level, body mass index (BMI), age, and academic class-year, as measured by sonographic intensity analysis. This study is specific to a cohort of first- and second-year medical students. Materials and Methods: The right lumbar paraspinal muscles, at the level of the fifth lumbar vertebrae, were investigated with sonography among a cohort of medical students. Image pixels, within the selected region of interest, were segregated by pixel intensity and analyzed for IntraMAT content. Participants reported on additional study variables by responding to a survey. The cohort responses were analyzed to seek correlations between those variables and IntraMAT. Results: The female participants were found to have more IntraMAT ( P < .001). Most participants reported low back pain. There were no significant correlations between IntraMAT and reported low back pain, academic class year, or BMI. Moderate exercise increased IntraMAT deposition, and each year of increasing age decreased IntraMAT ( P < .05). Second-year students experienced more self-reported low back pain than first-year students. Conclusion: A cohort of medical students who were reportedly sedentary had more low back pain than their peers. Back pain was more prevalent in second-year students, irrespective of age, suggesting that ill effects of a sedentary lifestyle may be cumulative. The validity of the sonographic pixel intensity analysis performed was supported by the highly significant increase in IntraMAT observed in female participants. The relationship between low back pain, exercise, BMI, and IntraMAT was uncertain based on available evidence and the results of this study.

Analisis Hasil Safire pada Imaging CT Scan Kepala

Background: Iterative Reconstruction (IR) method was first applied to CT in 1960 and successfully used for the first time in clinical research by reconstructing 128 x 128 images according to image metrics and using high-resolution images of 512 x 512 for special research activities such as image evaluation. artifacts and noise. In 2008, the development of IR can improve image quality and reduce the amount of radiation in clinical CT diagnosis. Iterative reconstruction promises to improve image quality while reducing radiation dose. This has been demonstrated in CT of the thorax, coronary arteries, abdomen, spine and neck, paranasal sinuses, and head. Sinogram-Afirmed Iterative Reconstruction (SAFIRE) is one of the iterative algorithm reconstruction methods that uses noise modeling techniques, Sinogram-Afirmed Iterative Reconstruction (SAFIRE), promises to improve Cranial CT (CCT). In this new technique, raw data-based iteration for artifact reduction is combined with image-based iteration using smooth regularization that estimates the variance of image noise in various directions at each image pixel and adjusts it with a spatial variance regularization function simultaneously. Methods: This study is a literature review, where literature exploration is carried out on various databases with keywords such as, Reference sources used in compiling this article include google scollar, as well as articles in English and Indonesian scientific journals. Results: Itarative Reconstruction (IR) Head CT Scan, SAFIRE includes reducing or adding noise to the image results, artifacts, acquisition time, increasing SNR and CNR and reducing dose in the examination. Conclusion: Analysis of Safire results in Head CT-Scan Imaging has an Itarative Reconstruction (SAFIRE) procedure, the role of safire in head CT scans is to optimize noise in the Reconstructed image and can reduce artifacts in the image and increase SNR, CNR in the Reconstructed results so that it can provide better information.

Fourier single-pixel imaging based on sampling prediction from intermediate frequencies

The imaging quality of Fourier single pixel imaging (FSI) is determined by the number of samples, therefore higher image quality requires more sampling times. Common low-frequency sampling methods compromise high-frequency signals to reduce the number of samples, but this will reduce the resolution of the reconstructed image. The recent adaptive sampling methods can reconstruct high-quality images with low sampling ratio, but the calculation of sampling trajectories is a time-consuming process. To improve imaging efficiency, we propose a fast sampling method based on intermediate frequency prediction for FSI. This method utilizes the continuity and directionality of important frequency distributions in the Fourier spectrum, according to which regions of important high-frequency components can be quickly predicted by firstly identifying important frequency components on the intermediate frequency ring. The simulation and experiment results demonstrated our method is 9 times faster than existing adaptive sampling methods in predicting sampling trajectories while maintaining similar image reconstruction quality for an image of 256 × 256 pixels under 5% sampling ratio. In addition, our method can efficiently sample important spectral components of images that has different frequency distributions, which proves that this method has the potential for wide applications.

FPWT: Filter pruning via wavelet transform for CNNs

The enormous data and computational resources required by Convolutional Neural Networks (CNNs) hinder the practical application on mobile devices. To solve this restrictive problem, filter pruning has become one of the practical approaches. At present, most existing pruning methods are currently developed and practiced with respect to the spatial domain, which ignores the potential interconnections in the model structure and the decentralized distribution of image energy in the spatial domain. The image frequency domain transform method can remove the correlation between image pixels and concentrate the image energy distribution, which results in lossy compression of images. In this study, we find that the frequency domain transform method is also applicable to the feature maps of CNNs. The filter pruning via wavelet transform (WT) is proposed in this paper (FPWT), which combines the frequency domain information of WT with the output feature map to more obviously find the correlation between feature maps and make the energy into a relatively concentrated distribution in the frequency domain. Moreover, the importance score of each feature map is calculated by the cosine similarity and the energy-weighted coefficients of the high and low frequency components, and prune the filter based on its importance score. Experiments on two image classification datasets validate the effectiveness of FPWT. For ResNet-110 on CIFAR-10, FPWT reduces FLOPs and parameters by more than 60.0 % with 0.53 % accuracy improvement. For ResNet-50 on ImageNet, FPWT reduces FLOPs by 53.8 % and removes parameters by 49.7 % with only 0.97 % loss of Top-1 accuracy.

A novel GM-APD array-based heterodyne imaging detection system supports large array multi-pixel parallel target motion state image detection

Existing laser active imaging detection methods are limited by the detection mechanism, which can only capture the intensity image and distance image of the target, and lack practical detection solutions for acquiring images of the target motion state characteristics (non-macroscopic centroid motion, such as rotation, rolling, and other motion characteristics around the centroid). In this paper, a detection method using Geiger mode avalanche photodiode (GM-APD) array detector for heterodyne imaging to obtain images of the target motion state is proposed. An innovative method based on photon counting time interval calculation (PCTIC) is proposed to obtain the Doppler frequency shift of the target echo for each GM-APD pixel, which effectively eliminates useless data unrelated to the signal. With limited data storage and processing speed, the heterodyne imaging performance has been effectively improved to achieve high-precision heterodyne imaging detection of very weak target echoes and to support heterodyne imaging detection of large arrays with more image pixels in parallel. Experiments show that the method can achieve video-level detection at an imaging resolution of 32×32, and with a paucity of echo photons (detection probability of echo is 0.0032), a millimetre-level velocimetry measurement error can be achieved by accumulating only 6 echo photons per image element. The system also shows good resistance to turbulence interference, with target motion state characteristics detected based on velocity images remaining virtually unaffected under turbulence conditions caused by strong flames. This advancement is crucial for target detection in complex working environments such as smart manufacturing and autonomous driving.

Application of CNN for multiple phase corrosion identification and region detection

Corrosion is a significant issue that contributes negatively to the degradation of materials most especially metals. To ensure proper maintenance, enhance reliability and prevent breakdown, it is very essential to not only effectively detect corrosion but to also understand its locations and distributions on the materials. A Multiple phase Convolutional Neural Network (CNN) model is created for this purpose. The Multiple phase CNN model consists of custom designed deep learning algorithms at various stages. This created the opportunity to make use of binary classification, multi-label classification and patch distribution algorithm to detect and identify corrosion regions on metallic materials. Six (6) different labels of corrosion were modelled to represent different levels of degradation using 600 anonymized images. The images were used in the various stages of the framework for training the respective models. Results at the binary level shows 94.87 % of corrosion detection. The multiclass stage of the Multiple phase CNN records the highest accuracy of 92.1 %. The patch distribution stage recorded a highest accuracy of 96.5 % and 94.6 % for the Average Image and Average Pixel ROCAUC (Region of Concentration Area Under Cover). It also shows a region segment average accuracy detection of 91.5 % (image level) and 89.2 %(pixel level) for 9 distinct regions. The research provides a comprehensive and detailed reliability and maintenance information for Aerospace, Transport and Manufacturing Materials experts and non-experts. The framework shows a robust approach to detecting corrosion which is essential for critical and safety applications as well as preventing economic loss due to corrosion. This can also be extended to other domains beyond the corrosion case study.

Phase identification and micromechanical properties of non-traditional and natural pozzolan based alkali-activated materials

Four groups of non-traditional and natural pozzolan (NNP) based (aluminosilicate-based) materials, calcined clays, ground bottom ashes, volcanic ashes, and fluidized bed combustion ashes, were alkali activated using a hybrid solution of sodium silicate and sodium hydroxide. The microhardness and reduced modulus of the phases present in eleven alkali-activated pastes were measured using nanoindentation. At least 800 data points were collected from 28-day old ambiently cured paste samples. Unsupervised machine learning techniques i.e., k-means clustering and Gaussian mixture modeling (GMM) were used for the classification of the micromechanical properties supplemented by scanning electron microscopy (SEM) and energy dispersive X-ray spectroscopy (EDS). The clustering of micromechanical and EDS data revealed five distinct phases in these hardened pastes. The alkali-activated gels identified had reduced modulus values ranging from 12 to 34 GPa. The remnant phases were partly reacted grains and unreacted minerals exhibiting reduced modulus values ranging from 35 to 105 GPa. Micromechanical property contour plots and SEM image pixel count plots were used to validate the phase assemblage. Additionally, the identification capabilities and advantages of the method are assessed by direct comparison with experimental results for different alkali-activated gels.

Extraction and reduction of parameters from hand-drawn Archimedes spirals for clinical tremor assessment

BackgroundPatients’ hand-drawn Archimedes spirals are widely used in the neurological community to grade tremors. These spirals are either drawn on paper and Xeroxed/scanned into digital images or digitizing tablets are used for the drawings. This process introduces artifacts such as variable widths of the drawn lines with varying pixel grey scale values. Xeroxing introduces additional artifacts resulting from paper misalignments. These artifacts and the presence of the reference spiral in the image complicate an automatic extraction of a mathematical spiral signal from the image. New methodsWe introduce a mathematical mapping that transforms the image pixels of the patient's hand-drawn spiral into a one-dimensional discrete signal that can be used for mathematical analysis. ResultsA cohort of 18 hand-drawn spirals with various artifacts is used to validate our method.We extract the parameters of the discrete signals and show that the signals can be represented by truncating to as few as 150 parameters with a truncation RMS error of 6.26 % across the cohort. Using only 150 features makes machine learning a viable option for future applications. Furthermore, our method can be used to evaluate the frequency and the amplitude of the tremor. Comparison with existing methodsIn existing methods, the patient draws the spiral on a digitizing tablet, and features are extracted from this data for machine learning. We recognize that a vast majority of hospitals are still using the pencil-and-paper approach, and there is an abundance of ready-to-be-mined tremor-related data already stored as paper or digitized drawings. Our procedure is equally applicable to Xeroxed documents as well as files generated from digital tablets. ConclusionsWe have validated a new procedure requiring minimal user intervention to automatically extract a patient's hand-drawn spiral as a discrete mathematical one-dimensional signal from a scanned image or a file from a digital tablet.

A new encryption algorithm for image data based on two-way chaotic maps and iterative cellular automata

Due to their simplicity of implementation and compliance with the encryption issue, chaotic models are often utilized in picture encryption applications. Despite having many benefits, this approach still has a crucial space issue that makes encryption algorithms based on it susceptible to brute-force assaults. This research’s proposed novel picture encryption technique has a vast key space and great key sensitivity. To achieve this goal, the proposed method combines two-way chaotic maps and reversible cellular automata (RCA). First, this approach uses a two-way chaotic model named spatiotemporal chaos for image confusion. This step includes permuting the image pixels using a chaotic map at the byte level. Then, the RCA model is utilized for image diffusion. In this step, the RCA model iterates over image pixels to modify them at the bit level. The method’s performance in encrypting grayscale images was evaluated using various analysis methods. According to the results, the proposed method is a compelling image encryption algorithm with high robustness against brute-force, statistical, and differential attacks.

Color image hybrid noise filtering algorithm based on deep convolution neural network

To solve the problems of the classical color image hybrid noise filtering method, a deep convolutional neural network improved by evolutionary strategy and jump connection is proposed and applied to the filtering noise reduction of color images. First, the color information of the image is described quantitatively by digital means. The common method is to build color space model. According to the characteristics of color and the needs of human vision, mathematical algorithms are used to convert images into machine recognizable data. The distance between pixels is measured according to the difference of pixels in the color image determined above. Then, the probability density function and noise probability density function of Gaussian noise are calculated to determine the hybrid noise feature points of color image. The filtering algorithm structure designed this time is as follows: A color image hybrid noise filter is used to map the noise points in the mapped image to the feature space, and linear regression is performed on the noise point data. Relaxation variables are introduced in the network to improve the denoising ability. The experimental results show that the Peak Signal to Noise Ratio and structural similarity index values of the filtering algorithm designed in this study are higher than the two methods in the literature. The color image hybrid noise filtering model designed in this study has good filtering performance, good image cleanliness, and high filtering efficiency.

Uncertainty-Aware Traction Force Microscopy.

Traction Force Microscopy (TFM) is a versatile tool to quantify cell-exerted forces by imaging and tracking fiduciary markers embedded in elastic substrates. The computations involved in TFM are ill-conditioned, and data smoothing or regularization is required to avoid overfitting the noise in the tracked substrate displacements. Most TFM calculations depend critically on the heuristic selection of regularization (hyper)parameters affecting the balance between overfitting and smoothing. However, TFM methods rarely estimate or account for measurement errors in substrate deformation to adjust the regularization level accordingly. Moreover, there is a lack of tools to quantify how these errors propagate to the recovered traction stresses. These limitations make it difficult to interpret TFM readouts and hinder comparing different experiments. This manuscript presents an uncertainty-aware TFM technique that estimates the variability in the magnitude and direction of the traction stress vector recovered at each point in space and time of each experiment. In this technique, substrate deformation and its uncertainty are quantified using a non-parametric bootstrap PIV method by resampling the microscopy image pixels (PIV-UQ). This information is passed to a hierarchical Bayesian framework that automatically selects its hyperparameters to perform spatially adaptive regularization conditioned on image quality and propagates the uncertainty to the traction stress readouts (TFM-UQ). We validate the performance of PIV-UQ and TFM-UQ using synthetic datasets with prescribed image quality variations and demonstrate the application of PIV-UQ and TFM-UQ to experimental datasets. These studies show that TFM-UQ locally adapts the level of smoothing, outperforming traditional regularization methods. They also illustrate how uncertainty-aware TFM tools can be used to objectively choose key image analysis parameters like PIV-UQ interrogation window size. We anticipate that these tools will allow for decoupling biological heterogeneity from measurement variability and facilitate automating the analysis of large datasets by parameter-free, input data-based regularization.

Research on automated rapid diagnosis of distal radius fractures using X-ray images

The primary diagnostic method for distal radius fractures remains conventional X-ray imaging. In emergency situations, rapid assessment and decision-making are often required from non-orthopedic physicians or junior radiologists in the emergency room. Therefore, an accurate and efficient auxiliary diagnostic technology for distal radius fractures is of great significance. This paper combines deep learning with image analysis techniques to propose an effective classification method for types of distal radius fractures. Firstly, an extended U-Net three-level cascade segmentation network is used for precise segmentation of the most critical joint surface and non-joint surface areas for fracture identification. The edge is further optimized using the central pixel image block classification method. Then, fracture identification is performed separately on the joint surface and non-joint surface areas. Finally, based on the classification results of the two types of images, a comprehensive judgment is made to determine normal or ABC fracture types. The experimental X-ray data comes from three tertiary hospitals, with a total of 12,000 images in the training set, 3,000 of each type, and 1,200 images in the test set, 300 of each type. To further demonstrate the generalization performance of the classification experiment, an additional 500 images were added for fracture classification testing, coming from collaborative medical institutions in the United States and Germany. All images were annotated by orthopedic medical experts with more than ten years of experience. The accuracy rates for normal, type A, type B, and type C fractures in the test set were 0.99, 0.92, 0.91, and 0.82, respectively. For orthopedic medical experts, the average recognition accuracy rates were 0.98, 0.90, 0.87, and 0.81. The proposed automatic recognition method overall performs better than experts and can be used for preliminary auxiliary diagnosis of distal radius fractures without expert participation.

Research on automated rapid diagnosis of distal radius fractures using X-ray images

The primary diagnostic method for distal radius fractures remains conventional X-ray imaging. In emergency situations, rapid assessment and decision-making are often required from non-orthopedic physicians or junior radiologists in the emergency room. Therefore, an accurate and efficient auxiliary diagnostic technology for distal radius fractures is of great significance. This paper combines deep learning with image analysis techniques to propose an effective classification method for types of distal radius fractures. Firstly, an extended U-Net three-level cascade segmentation network is used for precise segmentation of the most critical joint surface and non-joint surface areas for fracture identification. The edge is further optimized using the central pixel image block classification method. Then, fracture identification is performed separately on the joint surface and non-joint surface areas. Finally, based on the classification results of the two types of images, a comprehensive judgment is made to determine normal or ABC fracture types. The experimental X-ray data comes from three tertiary hospitals, with a total of 12,000 images in the training set, 3,000 of each type, and 1,200 images in the test set, 300 of each type. To further demonstrate the generalization performance of the classification experiment, an additional 500 images were added for fracture classification testing, coming from collaborative medical institutions in the United States and Germany. All images were annotated by orthopedic medical experts with more than ten years of experience. The accuracy rates for normal, type A, type B, and type C fractures in the test set were 0.99, 0.92, 0.91, and 0.82, respectively. For orthopedic medical experts, the average recognition accuracy rates were 0.98, 0.90, 0.87, and 0.81. The proposed automatic recognition method overall performs better than experts and can be used for preliminary auxiliary diagnosis of distal radius fractures without expert participation.

High-quality ghost imaging based on undersampled natural-order Hadamard source

Abstract Improving the speed of ghost imaging is one of the main ways to leverage its advantages in sensitivity and imperfect spectral regions for practical applications. Because of the proportional relationship between image resolution and measurement time, when the image pixels are large, the measurement time increases, making it difficult to achieve real-time imaging. Therefore, a high-quality ghost imaging method based on undersampled natural-order Hadamard is proposed. This method uses the characteristics of the Hadamard matrix under undersampling conditions where image information can be fully obtained but overlaps, as well as deep learning to extract aliasing information from the overlapping results to obtain the true original image information. We conducted numerical simulations and experimental tests on binary and grayscale objects under undersampling conditions to demonstrate the effectiveness and scalability of this method. This method can significantly reduce the number of measurements required to obtain high-quality image information and advance application promotion.