Target Image Research Articles

Sea–Land Segmentation of Remote-Sensing Images with Prompt Mask-Attention

Remote-sensing technology has gradually become one of the most important ways to extract sea–land boundaries due to its large scale, high efficiency, and low cost. However, sea–land segmentation (SLS) is still a challenging problem because of data diversity and inconsistency, “different objects with the same spectrum” or “the same object with different spectra”, and noise and interference problems, etc. In this paper, a new sea–land segmentation method (PMFormer) for remote-sensing images is proposed. The contributions are mainly two points. First, based on Mask2Former architecture, we introduce the prompt mask by normalized difference water index (NDWI) of the target image and prompt encoder architecture. The prompt mask provides more reasonable constraints for attention so that the segmentation errors are alleviated in small region boundaries and small branches, which are caused by insufficiency of prior information by large data diversity or inconsistency. Second, for the large intra-class difference problem in the foreground–background segmentation in sea–land scenes, we use deep clustering to simplify the query vectors and make them more suitable for binary segmentation. Then, traditional NDWI and eight other deep-learning methods are thoroughly compared with the proposed PMFormer on three open sea–land datasets. The efficiency of the proposed method is confirmed, after the quantitative analysis, qualitative analysis, time consumption, error distribution, etc. are presented by detailed contrast experiments.

SAR-NTV-YOLOv8: A Neural Network Aircraft Detection Method in SAR Images Based on Despeckling Preprocessing

Monitoring aircraft using synthetic aperture radar (SAR) images is a very important task. Given its coherent imaging characteristics, there is a large amount of speckle interference in the image. This phenomenon leads to the scattering information of aircraft targets being masked in SAR images, which is easily confused with background scattering points. Therefore, automatic detection of aircraft targets in SAR images remains a challenging task. For this task, this paper proposes a framework for speckle reduction preprocessing of SAR images, followed by the use of an improved deep learning method to detect aircraft in SAR images. Firstly, to improve the problem of introducing artifacts or excessive smoothing in speckle reduction using total variation (TV) methods, this paper proposes a new nonconvex total variation (NTV) method. This method aims to ensure the effectiveness of speckle reduction while preserving the original scattering information as much as possible. Next, we present a framework for aircraft detection based on You Only Look Once v8 (YOLOv8) for SAR images. Therefore, the complete framework is called SAR-NTV-YOLOv8. Meanwhile, a high-resolution small target feature head is proposed to mitigate the impact of scale changes and loss of depth feature details on detection accuracy. Then, an efficient multi-scale attention module was proposed, aimed at effectively establishing short-term and long-term dependencies between feature grouping and multi-scale structures. In addition, the progressive feature pyramid network was chosen to avoid information loss or degradation in multi-level transmission during the bottom-up feature extraction process in Backbone. Sufficient comparative experiments, speckle reduction experiments, and ablation experiments are conducted on the SAR-Aircraft-1.0 and SADD datasets. The results have demonstrated the effectiveness of SAR-NTV-YOLOv8, which has the most advanced performance compared to other mainstream algorithms.

Research on the Depth Image Reconstruction Algorithm Using the Two-Dimensional Kaniadakis Entropy Threshold.

The photon-counting light laser detection and ranging (LiDAR), especially the Geiger mode avalanche photon diode (Gm-APD) LiDAR, can obtain three-dimensional images of the scene, with the characteristics of single-photon sensitivity, but the background noise limits the imaging quality of the laser radar. In order to solve this problem, a depth image estimation method based on a two-dimensional (2D) Kaniadakis entropy thresholding method is proposed which transforms a weak signal extraction problem into a denoising problem for point cloud data. The characteristics of signal peak aggregation in the data and the spatio-temporal correlation features between target image elements in the point cloud-intensity data are exploited. Through adequate simulations and outdoor target-imaging experiments under different signal-to-background ratios (SBRs), the effectiveness of the method under low signal-to-background ratio conditions is demonstrated. When the SBR is 0.025, the proposed method reaches a target recovery rate of 91.7%, which is better than the existing typical methods, such as the Peak-picking method, Cross-Correlation method, and the sparse Poisson intensity reconstruction algorithm (SPIRAL), which achieve a target recovery rate of 15.7%, 7.0%, and 18.4%, respectively. Additionally, comparing with the SPIRAL, the reconstruction recovery ratio is improved by 73.3%. The proposed method greatly improves the integrity of the target under high-background-noise environments and finally provides a basis for feature extraction and target recognition.

Towards imaging the immune state of cancer by PET: Targeting legumain with 11C-labeled P1-Asn peptidomimetics carrying a cyano-warhead

PurposeM2-type tumor-associated macrophages (TAM) residing in the tumor microenvironment (TME) have been linked to tumor invasiveness, metastasis and poor prognosis. M2 TAMs suppress T cell activation, silencing the recognition of the cancer by the immune system. Targeting TAMs in anti-cancer therapy may support the immune system and immune-checkpoint inhibitor therapies to fight the cancer cells. We aimed to develop a PET tracer for the imaging of M2 TAM infiltration of cancer, using activated legumain as the imaging target. Basic proceduresTwo P1-mimicking inhibitors with a cyano-warhead were labeled with carbon-11 and evaluated in vitro and in vivo with a CT26 tumor mouse model. Target expression and activity were quantified from RT-qPCR and in vitro substrate conversion, respectively. The co-localization of legumain and TAMs was assessed by fluorescence microscopy. The two tracers were evaluated by PET with subsequent biodistribution analysis with the dissected tissues. Parent-to-total radioactivity in plasma was determined at several time points after i.v. tracer injection, using reverse phase radio-UPLC. Main findingsLegumain displayed a target density of 40.7 ± 19.1 pmol per mg total protein in tumor lysate (n = 4) with high substrate conversion and colocalization with M2 macrophages in the tumor periphery. [11C]1 and [11C]2 were synthesized with >95 % radiochemical purity and 12.9–382.2 GBq/μmol molar activity at the end of synthesis. We observed heterogeneous tumor accumulation in in vitro autoradiography and PET for both tracers. However, excess unlabeled 1 or 2 did not compete with tracer accumulation. Both [11C]1 and [11C]2 were rapidly metabolized to a polar radiometabolite in vivo. Principal conclusionsThe legumain tracers [11C]1 and [11C]2, synthesized with high radiochemical purity and molar activity, accumulate in the legumain-positive CT26 tumor in vivo. However, the lack of competition by excess compound questions their specificity. Both tracers are rapidly metabolized in vivo, requiring structural modifications towards more stable tracers for further investigations.

Remote sensing ghost imaging based on Hadamard modulated Gaussian array beam

A ghost imaging (GI) scheme by using Hadamard modulated Gaussian array beam (HMGAB) is proposed. Compared to traditional light sources modulated using ground glass, DMD, or SLM, HMGAB has higher emitting energy, making it advantageous for remote sensing GI. Moreover, the incoherent superposition of array sub-beams makes our scheme avoid the periodic aliasing which usually occurs in GI systems using optical phased array beam. The relationship between imaging maximum distance and target size is established and verified. In addition, GANs are used to address the issue of point-like reconstructed images caused by the spacing between array sub-beams.

Evolutionary computation-based self-supervised learning for image processing: a big data-driven approach to feature extraction and fusion for multispectral object detection

The image object recognition and detection technology are widely used in many scenarios. In recent years, big data has become increasingly abundant, and big data-driven artificial intelligence models have attracted more and more attention. Evolutionary computation has also provided a powerful driving force for the optimization and improvement of deep learning models. In this paper, we propose an image object detection method based on self-supervised and data-driven learning. Differ from other methods, our approach stands out due to its innovative use of multispectral data fusion and evolutionary computation for model optimization. Specifically, our method uniquely combines visible light images and infrared images to detect and identify image targets. Firstly, we utilize a self-supervised learning method and the AutoEncoder model to perform high-dimensional feature extraction on the two types of images. Secondly, we fuse the extracted features from the visible light and infrared images to detect and identify objects. Thirdly, we introduce a model parameter optimization method using evolutionary learning algorithms to enhance model performance. Validation on public datasets shows that our method achieves comparable or superior performance to existing methods.

Automatic detection and extraction of lost shipping containers based on YOLO and the segment anything model

ABSTRACT The artificial visual method is currently commonly used to decipher multi-beam water column images to obtain the position and state of lost shipping containers. However, the recognition efficiency and accuracy of this method need to be improved. The You Only Look Once (YOLO) series model has strong real-time target detection capability. Meanwhile, the Segment Anything Model (SAM) has strong zero-shot transferability. A detection and extraction method for lost shipping containers, which combines the two models mentioned above, is proposed in this study. First, the YOLO series model is employed to detect lost shipping container targets in a single-frame water column image. On this basis, the output of bounding box positions by the optimal target detection model is used as a prompt for the SAM. Finally, the SAM is used to extract lost shipping container targets in images through zero-shot transferability. Experimental results in the Pearl River estuary show that the combined modelling method of YOLOv5-n and EdgeSAM-3× achieves the best overall performance. The precision and recall for the detection of lost shipping containers by this method is better than 95%. In terms of target extraction, YOLOv5-n and EdgeSAM-3× have the best Intersection over Union, recall, and F1 scores.

Tumour Marker Expression in Head and Neck Malignancies to Identify Potential Targets for Intraoperative Molecular Near-Infrared Imaging.

Oral and laryngeal squamous cell carcinoma (OSCC and LSCC) and papillary thyroid carcinoma (PTC) are common head and neck cancers (HNCs) typically treated surgically. Challenges in tumour delineation often lead to inadequate resection margins in OSCC and LSCC, and missed multifocality in PTC. Fluorescence imaging (FLI) using near-infrared tumour-targeting tracers may improve intraoperative identification of malignancy, facilitating precise excision. This study evaluates six potential FLI targets in OSCC, LSCC and PTC. Immunohistochemical staining was performed on OSCC (n = 20), LSCC (n = 10) and PTC (n = 10), assessing CEA, c-Met, EpCAM, EGFR, integrin αvβ6 and VEGF-α. Expression was scored (0-12) using the total immunostaining score (TIS) system, and categorized into absent (TIS 0), low (TIS 1-5), moderate (TIS 6-8) or high (TIS 9-12). Integrin αvβ6 showed significant overexpression in OSCC (TIS: 12; p < 0.001) and LSCC (TIS: 8; p = 0.002), with 80% of OSCC and 90% of LSCC exhibiting moderate-high expression. Similarly, EGFR expression was moderate-high in most OSCC (87.5%; TIS: 8) and universally high in LSCC (100%; TIS: 12). In PTC, EGFR and VEGF-α expressions were low-moderate, but significantly higher than in healthy tissue (TIS: 6; p < 0.006). This study highlights integrin αvβ6 and EGFR as viable FLI targets in OSCC and LSCC, especially integrin αvβ6 for tumour margin delineation. In PTC, despite lower expressions, the significant overexpression of VEGF-α, c-MET, and EGFR suggests their potential as FLI targets. Our findings support the development of tumour-targeted FLI tracers to improve surgical precision in HNC.

A New Transmission Target for Cultural Heritage Imaging

A New Transmission Target for Cultural Heritage Imaging

A Texture-Considerate Convolutional Neural Network Approach for Color Consistency in Remote Sensing Imagery

Remote sensing allows us to conduct large-scale scientific studies that require extensive mapping and the amalgamation of numerous images. However, owing to variations in radiation, atmospheric conditions, sensor perspectives, and land cover, significant color discrepancies often arise between different images, necessitating color consistency adjustments for effective image mosaicking and applications. Existing methods for color consistency adjustment in remote sensing images struggle with complex one-to-many nonlinear color-mapping relationships, often resulting in texture distortions. To address these challenges, this study proposes a convolutional neural network-based color consistency method for remote sensing cartography that considers both global and local color mapping and texture mapping constrained by the source domain. This method effectively handles complex color-mapping relationships while minimizing texture distortions in the target image. Comparative experiments on remote sensing images from different times, sensors, and resolutions demonstrated that our method achieved superior color consistency, preserved fine texture details, and provided visually appealing outcomes, assisting in generating large-area data products.

Semantic redundancy-aware implicit neural compression for multidimensional biomedical image data

The surge in advanced imaging techniques has generated vast biomedical image data with diverse dimensions in space, time and spectrum, posing big challenges to conventional compression techniques in image storage, transmission, and sharing. Here, we propose an intelligent image compression approach with the first-proved semantic redundancy of biomedical data in the implicit neural function domain. This Semantic redundancy based Implicit Neural Compression guided with Saliency map (SINCS) can notably improve the compression efficiency for arbitrary-dimensional image data in terms of compression ratio and fidelity. Moreover, with weight transfer and residual entropy coding strategies, it shows improved compression speed while maintaining high quality. SINCS yields high quality compression with over 2000-fold compression ratio on 2D, 2D-T, 3D, 4D biomedical images of diverse targets ranging from single virus to entire human organs, and ensures reliable downstream tasks, such as object segmentation and quantitative analyses, to be conducted at high efficiency.

Gini Coefficient-Based Feature Learning for Unsupervised Cross-Domain Classification with Compact Polarimetric SAR Data

Remote sensing image classification usually needs many labeled samples so that the target nature can be fully described. For synthetic aperture radar (SAR) images, variations of the target scattering always happen to some extent due to the imaging geometry, weather conditions, and system parameters. Therefore, labeled samples in one image could not be suitable to represent the same target in other images. The domain distribution shift of different images reduces the reusability of the labeled samples. Thus, exploring cross-domain interpretation methods is of great potential for SAR images to improve the reuse rate of existing labels from historical images. In this study, an unsupervised cross-domain classification method is proposed that utilizes the Gini coefficient to rank the robust and stable polarimetric features in both the source and target domains (GRFST) such that an unsupervised domain adaptation (UDA) can be achieved. This method selects the optimal features from both the source and target domains to alleviate the domain distribution shift. Both fully polarimetric (FP) and compact polarimetric (CP) SAR features are explored for crop-domain terrain type classification. Specifically, the CP mode refers to the hybrid dual-pol mode with an arbitrary transmitting ellipse wave. This is the first attempt in the open literature to investigate the representing abilities of different CP modes for cross-domain terrain classification. Experiments are conducted from four aspects to demonstrate the performance of CP modes for cross-data, cross-scene, and cross-crop type classification. Results show that the GRFST-UDA method yields a classification accuracy of 2% to 12% higher than the traditional UDA methods. The degree of scene similarity has a certain impact on the accuracy of cross-domain crop classification. It was also found that when both the FP and circular CP SAR data are used, stable, promising results can be achieved.

Detection and Tracking of Low-Frame-Rate Water Surface Dynamic Multi-Target Based on the YOLOv7-DeepSORT Fusion Algorithm

This study aims to address the problem in tracking technology in which targeted cruising ships or submarines sailing near the water surface are tracked at low frame rates or with some frames missing in the video image, so that the tracked targets have a large gap between frames, leading to a decrease in tracking accuracy and inefficiency. Thus, in this study, we proposed a water surface dynamic multi-target tracking algorithm based on the fusion of YOLOv7 and DeepSORT. The algorithm first introduces the super-resolution reconstruction network. The network can eliminate the interference of clouds and waves in images to improve the quality of tracking target images and clarify the target characteristics in the image. Then, the shuffle attention module is introduced into YOLOv7 to enhance the feature extraction ability of the target features in the recognition network. Finally, Euclidean distance matching is introduced into the cascade matching of the DeepSORT algorithm to replace the distance matching of IOU to improve the target tracking accuracy. Simulation results showed that the algorithm proposed in this study has a good tracking effect, with an improvement of 9.4% in the improved YOLOv7 model relative to the mAP50-95 value and an improvement of 13.1% in the tracking accuracy in the DeepSORT tracking network compared with the SORT tracking accuracy.

Programming Fast DNA Amplifier Circuits with Versatile Toehold Exchange Pathway.

DNA amplifier circuits establish powerful tools to dynamically control molecular assembly for computation, sensing, and biological applications. However, the slow reaction speed remains a major barrier to their practical utility. Here, diverse fast DNA amplifier circuits termed toehold exchange polymerization (TEP) and toehold exchange catalysis (TEC) using toehold exchange-mediated assembly as a fundamental mechanism are built. Both TEP and TEC with a duplex and a hairpin can respond within minutes to diverse nucleic acid inputs with high fidelity. In addition, the circuits can amplify live-cell signals for fluorescence imaging target RNA dynamics and discriminating different cell lines. Compared with existing DNA circuits that involve time scales of hours for transducing small signals, TEP and TEC exhibit much faster dynamics, simpler design, and comparable sensitivity. These features make TEP and TEC promising platforms to develop programmable nucleic acid tools and devices and to create fast sensing and processing systems, amenable to wide practical applications.

Image Registration Algorithm for Stamping Process Monitoring Based on Improved Unsupervised Homography Estimation

Homography estimation is a crucial task in aligning template images with target images in stamping monitoring systems. To enhance the robustness and accuracy of homography estimation against random vibrations and lighting variations in stamping environments, this paper proposes an improved unsupervised homography estimation model. The model takes as input the channel-stacked template and target images and outputs the estimated homography matrix. First, a specialized deformable convolution module and Group Normalization (GN) layer are introduced to expand the receptive field and enhance the model’s ability to learn rotational invariance when processing large, high-resolution images. Next, a multi-scale, multi-stage unsupervised homography estimation network structure is constructed to improve the accuracy of homography estimation by refining the estimation through multiple stages, thereby enhancing the model’s resistance to scale variations. Finally, stamping monitoring image data is incorporated into the training through data fusion, with data augmentation techniques applied to randomly introduce various levels of perturbation, brightness, contrast, and filtering to improve the model’s robustness to complex changes in the stamping environment, making it more suitable for monitoring applications in this specific industrial context. Compared to traditional methods, this approach provides better homography matrix estimation when handling images with low texture, significant lighting variations, or large viewpoint changes. Compared to other deep-learning-based homography estimation methods, it reduces estimation errors and performs better on stamping monitoring images, while also offering broader applicability.

Differential Lucy-Richardson-Rosen algorithm for near diffraction-limited image restoration assisting by a wavefront sensor

Lucy-Richardson-Rosen algorithm (LR2A) is one of the most important tools for image restoration, especially in computer vision, target imaging and so on. However, the performance of the LR2A can be affected by large optical aberration and imaging noise and even failure under severe environment. To address the mentioned problem, we proposed a new Differential Lucy-Richardson-Rosen Algorithm(D-LR2A) to reduce the influence of optical aberrations and detection noise with advantages of faster speed of convergence and better restoration quality. In the modified optical configuration, a Hartmann-Shack wavefront sensor is employed to measure optical aberration and estimate accurately the Point Spread Function (PSF) of the optical imaging system. The numeric and experimental results show that the proposed method can be used to restore images with large optical aberration and worse noise level. Besides that, it also has faster speed, better restoration quality, and thus easier application as compared to those of LR2A

MMHCA: Multi-feature representations based on multi-scale hierarchical contextual aggregation for UAV-view geo-localization

In global navigation satellite system denial environment, cross-view geo-localization based on image retrieval presents an exceedingly critical visual localization solution for Unmanned Aerial Vehicle (UAV) systems. The essence of cross-view geo-localization resides in matching images containing the same geographical targets from disparate platforms, such as UAV-view and satellite-view images. However, images of the same geographical targets may suffer from occlusions and geometric distortions due to variations in the capturing platform, view, and timing. The existing methods predominantly extract features by segmenting feature maps, which overlook the holistic semantic distribution and structural information of objects, resulting in loss of image information. To address these challenges, dilated neighborhood attention Transformer is employed as the feature extraction backbone, and Multi-feature representations based on Multi-scale Hierarchical Contextual Aggregation (MMHCA) is proposed. In the proposed MMHCA method, the multi-scale hierarchical contextual aggregation method is utilized to extract contextual information from local to global across various granularity levels, establishing feature associations of contextual information with global and local information in the image. Subsequently, the multi-feature representations method is utilized to obtain rich discriminative feature information, bolstering the robustness of model in scenarios characterized by positional shifts, varying distances, and scale ambiguities. Comprehensive experiments conducted on the extensively utilized University-1652 and SUES-200 benchmarks indicate that the MMHCA method surpasses the existing techniques, showing outstanding results in UAV localization and navigation.

"One Method to Label Them All": A Single Fully Automated Protocol for GMP-Compliant 68Ga Radiolabeling of PSMA-11, Transposable to PSMA-I&T and PSMA-617.

Prostate-specific membrane antigen (PSMA) is an ideal target for molecular imaging and targeted radionuclide therapy in prostate cancer. Consequently, various PSMA ligands were developed. Some of these molecules are functionalized with a chelator that can host radiometals, such as 68Ga for PET imaging. The 68Ga radiolabeling step benefits from process automation, making it more robust and reducing radiation exposure. To design a single automated radiolabeling protocol for the GMP-compliant preparation of [68Ga]Ga-PSMA-11, transposable to the production of [68Ga]Ga-PSMA-617 and [68Ga]Ga-PSMA-I&T. A GAIA® synthesis module and a GALLIAD® generator were used. Radio-TLC and radio-HPLC methods were validated for radiochemical purity (RCP) determination. Three [68Ga]Ga-PSMA-11 validation batches were produced and thoroughly tested for appearance and pH, radionuclide identity and purity, RCP, stability, residual solvent and sterility. Minimal modifications were made to the reagents and disposables for optimal application to other PSMA ligands. [68Ga]Ga-PSMA-11 for clinical application was produced in 27 min. The 3 validation batches met the quality criteria expected by the European Pharmacopoeia to allow routine production. For optimal transposition to PSMA-617, the solid phase extraction cartridge was changed to improve purification of the radiolabeled product. For application to PSMA-I&T, the buffer solution initially used was replaced by HEPES 2.7 M to achieve good radiochemical yields. Residual HEPES content was checked in the final product and was below the Ph. Eur. threshold. A single automated radiolabeling method on the GAIA® module was developed and implemented for 68Ga radiolabeling of 3 PSMA ligands, with slight adjustments for each molecule.

Biomimetic copper-containing nanogels for imaging-guided tumor chemo-chemodynamic-immunotherapy

Developing multifunctional nanoplatforms to comprehensively modulate the tumor microenvironment and enhance diagnostic and therapeutic outcomes still remains a great challenge. Here, we report the facile construction of a multivariate nanoplatform based on cancer cell membrane (CM)-encapsulated redox-responsive poly(N-vinylcaprolactam) (PVCL) nanogels (NGs) co-loaded with Cu(II) and chemotherapeutic drug toyocamycin (Toy) for magnetic resonance (MR) imaging-guided combination tumor chemodynamic therapy/chemoimmunotherapy. We show that redox-responsive PVCL NGs formed through precipitation polymerization can be aminated, conjugated with 3,4-dihydroxyhydrocinnamic acid for Cu(II) complexation, physically loaded with Toy, and finally camouflaged with CMs. The created ADCT@CM NGs with an average size of 113.0 nm are stable under physiological conditions and can efficiently release Cu(II) and Toy under tumor microenvironment with a high level of glutathione. Meanwhile, the developed NGs are able to enhance cancer cell oxidative stress and endoplasmic reticulum stress by synergizing the effects of chemodynamic therapy mediated by Cu-based Fenton-like reaction and Toy-mediated chemotherapy, thereby triggering significant immunogenic cell death (ICD). In a melanoma mouse model, the NGs show potent immune activation effects to reinforce tumor therapeutic efficacy through ICD induction and immune modulation including high levels of immune cytokine secretion, increased tumor infiltration of CD8+ cytotoxic T cells, and reduced tumor infiltration of regulatory T cells. With the CM coating and Cu(II) loading, the developed NG platform demonstrates homologous tumor targeting and T1-weighted MR imaging, hence providing a general biomimetic NG platform for ICD-facilitated tumor theranostic nanoplatform. Statement of significanceDeveloping multifunctional nanoplatforms to comprehensively modulate the tumor microenvironment (TME) and enhance theranostic outcomes remains a challenge. Here, a cancer cell membrane (CM)-camouflaged nanoplatform based on aminated poly(N-vinylcaprolactam) nanogels (NGs) co-loaded with Cu(II) and toyocamycin (Toy) was prepared for magnetic resonance (MR) imaging-guided combination tumor chemodynamic therapy/chemoimmunotherapy. The tumor targeting specificity and efficient TME-triggered release of Cu(II) and Toy could enhance tumor cell oxidative stress and endoplasmic reticulum stress by synergizing the effects of chemodynamic therapy mediated by Cu-based Fenton-like reaction and Toy-mediated chemotherapy, respectively, thereby leading to significant immunogenic cell death (ICD) and immune response. With the CM coating and Cu(II) loading, the developed NG platform also demonstrates good T1-weighted tumor MR imaging performance. Hence, this study provides a general biomimetic NG platform for ICD-facilitated tumor theranostics.

A Distorted Light Field Image Correction Method Based on Improved Hough Transform

Introduction: In using a camera to take photos, due to environmental limitations, uneven lighting can cause uneven distribution of the image light field, resulting in distortion of the image background and target, blurring of details, and distorted light field images. Method: In view of this, research is conducted on the correction of distorted light field images based on the Hough transform. First, the improved Hough transform is utilized to locate the four coordinates, the matrix information of the normal image is applied to calculate the corresponding parameter amount, and then the low-frequency part of the image spectrum is removed. Finally, it uses the Gaussian function for difference, inputs the original data, and gets the correction result of the distorted light field image. Result: The research results indicate that in the practical application of the distorted light field image correction algorithm based on the Hough transform, the improved Hough transform algorithm is superior to the traditional one. Conclusion: In comparative experiments, the research algorithm outperforms the other three algorithms, with an average color restoration of 93.76% and an average signal-to-noise ratio of 54.22dB. The superiority of the research algorithm has been verified, indicating that the research method can perfectly correct distorted light field images and achieve good correction results.