Image Area Research Articles

Crystalline Orientation Control Enhanced Adhesion of Perovskite to Large‐Area Readout Board for High‐Performance X‐Ray Imaging

AbstractHalide perovskites are reputed as highly promising photoelectronic materials for direct X‐ray detectors, but realizing large‐area flat‐panel imaging requires to address the compatibility issue of the electronic, surficial, and mechanical properties between the perovskite and the readout circuit board. Here, a low‐dimensional MA3Bi2I9 perovskite is chosen to achieve a good match in a balancing act between the two by exploiting an orientation control strategy for perovskite film growth. The most striking consequence of the orientation controlled growth is the excellent adhesion of the thick perovskite film to the electronic board in large area and effectively addresses the charge sharing effect, which has been notoriously difficult to achieve. The resulting detector, exhibits an X‐ray imaging area of 2.8 × 3.2 cm, with a spatial resolution of 4.0 lp mm⁻¹, the highest yet achieved for polycrystalline perovskite detectors based on TFT backplanes, and a sensitivity of 588 µCGyair−1 cm−2 while maintaining a dark current below 10 nA cm⁻2, this is also the highest value recorded to date for polycrystalline zero‐dimensional perovskite detectors. This device clearly revealing the intricate internal structures of both biological specimens and industrial products. This outcome demonstrates the potential of zero‐dimensional perovskites in X‐ray planar imaging and highlights the critical role of orientation control strategies.

Improvements on speed, stability and field of view in adaptive optics OCT for anterior retinal imaging using a pyramid wavefront sensor.

We present improvements on the adaptive optics (AO) correction method using a pyramid wavefront sensor (P-WFS) and introduce a novel approach for closed-loop focus shifting in retinal imaging. The method's efficacy is validated through in vivo adaptive optics optical coherence tomography (AO-OCT) imaging in both, healthy individuals and patients with diabetic retinopathy. In both study groups, a stable focusing on the anterior retinal layers is achieved. We further report on an improvement in AO loop speed that can be used to expand the imaging area of AO-OCT in the slow scanning direction, largely independent of the eye's isoplanatic patch. Our representative AO-OCT data reveal microstructural details of the neurosensory retina such as vessel walls and microglia cells that are visualized in single volume data and over an extended field of view. The excellent performance of the P-WFS based AO-OCT imaging in patients suggests good clinical applicability of this technology.

Segmentation of mining subsidence areas in D-InSAR interferometric phase images using improved UNet++ network

Segmentation of mining subsidence areas in D-InSAR interferometric phase images using improved UNet++ network

SwinTExCo: Exemplar-based video colorization using Swin Transformer

Video colorization represents a compelling domain within the field of Computer Vision. The traditional approach in this field relies on Convolutional Neural Networks (CNNs) to extract features from each video frame and employs a recurrent network to learn information between video frames. While demonstrating considerable success in colorization, most traditional CNNs suffer from a limited receptive field size, capturing local information within a fixed-sized window. Consequently, they struggle to directly grasp long-range dependencies or pixel relationships that span large image or video frame areas. To address this limitation, recent advancements in the field have leveraged Vision Transformer (ViT) and their variants to enhance performance. This article introduces Swin Transformer Exemplar-based Video Colorization (SwinTExCo), an end-to-end model for the video colorization process that incorporates the Swin Transformer architecture as the backbone. The experimental results demonstrate that our proposed method outperforms many other state-of-the-art methods in both quantitative and qualitative metrics. The achievements of this research have significant implications for the domain of documentary and history video restoration, contributing to the broader goal of preserving cultural heritage and facilitating a deeper understanding of historical events through enhanced audiovisual materials.

In-field disease symptom detection and localisation using explainable deep learning: Use case for downy mildew in grapevine

Diseases and pests in agriculture significantly impact crop yield and quality. Downy mildew (Plasmopara viticola) is a particular noteworthy example in grapevines. Traditional detection methods are laborious, subjective and time-consuming. Consequently, a technological solution based on artificial intelligence, would provide higher levels of reproducibility and sampling. The aim of this work was to develop an interpretable, automated method for detection and localisation of plant disease symptoms under field conditions. Images of the grapevine canopy were taken in 14 commercial vineyard plots under a range of lightning conditions, including both static and on-the-go settings. The images were processed using a sliding window, classifying sub-images into areas with and without downy mildew. Transfer learning, fine-tuning and data augmentation were employed to automate the classification, comparing convolutional neural networks (CNNs) and vision transformers (ViT). Subsequently, the trained model was integrated into the sliding window to localise regions within the canopy images exhibiting symptoms of downy mildew. Model predictions were interpreted using explainable artificial intelligence (XAI) methods. The EfficientNetV2S model achieved an accuracy of 91 % and an F1-score of 0.92 when classifying image areas and an Intersection over Union (IoU) of 0.83 when locating symptomatic areas. This method showed promising results, enabling automatic and explainable detection and localisation of plant diseases in complex conditions. The straightforward labelling process facilitated adaptation to new conditions, making it suitable for different crops and diseases. Integration into mobile platforms could enhance disease management and reduce the spread of pathogens, making a significant advance in agricultural technology.

Study on microwave ablation temperature prediction model based on grayscale ultrasound texture and machine learning.

Temperature prediction is crucial in the clinical ablation treatment of liver cancer, as it can be used to estimate the coagulation zone of microwave ablation. Experiments were conducted on 83 fresh ex vivo porcine liver tissues at two ablation powers of 15 W and 20 W. Ultrasound grayscale images and temperature data from multiple sampling points were collected. The machine learning method of random forests was used to train the selected texture features, obtaining temperature prediction models for sampling points and the entire ultrasound imaging area. The accuracy of the algorithm was assessed by measuring the area of the hyperechoic area in the porcine liver tissue cross-section and ultrasound grayscale images. The model exhibited a high degree of accuracy in temperature prediction and the identification of coagulation zone. Within the test sets for the 15 W and 20 W power groups, the average absolute error for temperature prediction was 1.14°C and 4.73°C, respectively. Notably, the model's accuracy in measuring the area of coagulation was higher than that of traditional ultrasonic grey-scale imaging, with error ratios of 0.402 and 0.182 for the respective power groups. Additionally, the model can filter out texture features with a high correlation to temperature, providing a certain degree of interpretability. The temperature prediction model proposed in this study can be applied to temperature monitoring and coagulation zone range assessment in microwave ablation.

Review of Polarized Light‐Spin/Dipole Interactions: Fundamental Physics and Application in Circularly Polarized Detecting

AbstractCircularly polarized light (CPL) has attracted great attention due to its unique electromagnetic vector, which possesses potential practical applications in optical imaging, biometrics, and other interdisciplinary areas. At present, many materials with spontaneous CPL emitting have been extensively studied and reviewed for the generation of CPL. For the detection of CPL, mainly concentrate on the technical problems, that is, how to combine circularly polarized optical active materials with device structures to meet detection needs. Essentially, the resolution of CPL depends on the interaction between CPL and matter, Herein, the interactive modes including polarized light‐spin and light‐dipole (or charge) interactions in devices are summarized. Also, direct and indirect interactions of polarized light‐spin are presented. Meanwhile, the progress of light‐spin/dipole interaction dependence of CPL detectors is analyzed based on artificial structures of photoconductors, photodiodes, and photo field effect transistors. It is hoped that the review can broaden the bridge between the fundamental photon‐spin‐dipole interaction and CPL detectors with high performance, and then deepen the understanding of CPL detection and promote the development of CPL detectors.

Quaternion attention-based JND model for macrophotography image watermarking

With the advancement of imaging technology, macrophotography images (MPIs) have become a popular research topic. Unlike natural images, MPIs often feature sharp foregrounds and blurred backgrounds, leading to distinct perceptual characteristics in estimation. As the number of MPIs grows rapidly, concerns over image quality and security increase. Robust watermarking techniques have been introduced to address these challenges. Just Noticeable Difference (JND) has been widely used in quantization-based watermarking frameworks. However, existing JND models handle each image area with a single-level perceptual attention. Visual attention in Quaternion Discrete Wavelet Transform (QDWT), which can reflect the Multi-level perceptual attention feature. Therefore, we propose a new method called Quaternion Attention-based Just Noticeable Difference model for MPIs Watemarking (QAJnd-MW) for watermarking MPIs. This method uses visual attention mechanisms, recognizing that the HVS is more sensitive to attention regions. We generate a masking effect in the JND field. The input image undergoes QDWT to explore multi-scale features. The multi-scale feature maps, with multi-directional luminance and multi-channel color, help create local and global attention maps, which are fused to form the final attention map. Specifically, considering both attention-based masking effects, the quaternion attention-guided JND model is designed for a robust MPI watermarking framework, aiming to further improve MPI security. Extensive experiments on the MP2020 and Blur Detection datasets show that the proposed model significantly improves robustness against JPEG compression attacks, reducing the bit error rate (BER) by up to 12%. Additionally, the model performs well against other attacks, such as those in online social networks, with lower BER than current state-of-the-art techniques.

Stepwise Corrected Attention Registration Network for Preoperative and Follow-Up Magnetic Resonance Imaging of Glioma Patients.

The registration of preoperative and follow-up brain MRI, which is crucial in illustrating patients' responses to treatments and providing guidance for postoperative therapy, presents significant challenges. These challenges stem from the considerable deformation of brain tissue and the areas of non-correspondence due to surgical intervention and postoperative changes. We propose a stepwise corrected attention registration network grounded in convolutional neural networks (CNNs). This methodology leverages preoperative and follow-up MRI scans as fixed images and moving images, respectively, and employs a multi-level registration strategy that establishes a precise and holistic correspondence between images, from coarse to fine. Furthermore, our model introduces a corrected attention module into the multi-level registration network that can generate an attention map at the local level through the deformation fields of the upper-level registration network and pathological areas of preoperative images segmented by a mature algorithm in BraTS, serving to strengthen the registration accuracy of non-correspondence areas. A comparison between our scheme and the leading approach identified in the MICCAI's BraTS-Reg challenge indicates a 7.5% enhancement in the target registration error (TRE) metric and improved visualization of non-correspondence areas. These results illustrate the better performance of our stepwise corrected attention registration network in not only enhancing the registration accuracy but also achieving a more logical representation of non-correspondence areas. Thus, this work contributes significantly to the optimization of the registration of brain MRI between preoperative and follow-up scans.

Self‐Assembly of UiO‐66 on Conjugated Polyelectrolytes: Toward Enhanced Photophysical Properties

AbstractIn this study, the synthesis and characterization of the fluorescent metal–organic framework (MOF)‐polymer composites is reported based on zirconium‐based MOFs (UiO‐66 and UiO‐66(OH)₂) and a conjugated polyelectrolyte, poly(phenylene ethynylene) carboxylate (PPE‐CO₂‐108). The defect‐rich nature of these Zr‐MOFs facilitates strong interactions between the polyelectrolyte's carboxylic acid moieties and the open metal sites on the Zr clusters within the MOF nanoparticles. The composites are prepared by a simple impregnation approach, where MOF nanocrystals suspended in HEPES buffer are added to the polymeric solution under sonication for 10 min. The obtained MOF composites (i.e., UiO‐66‐CPE and UiO‐66 (OH)2‐CPE) are characterized using powder X‐ray diffraction (PXRD), scanning electron microscopy (SEM), thermogravimetric analysis (TGA), Brunauer‐Emmett‐Teller (BET) surface area, zeta potential measurements, and UV–vis spectroscopy. The characterization confirmed the homogeneous distribution of the MOF nanocrystals on the polymer as seen in the SEM images, and the interaction with PPE‐CO₂‐108 is confirmed by the decrease in the surface areas from 1050 to 590 m2 g−1 for UiO‐66‐CPE and from 500 to 137 m2 g−1, for UiO‐66(OH)2‐CPE. Fluorescence microscopy revealed strong fluorescence in the microparticles, confirming robust polymer‐MOF interaction. The composites also exhibit improved photostability of the conjugated polyelectrolyte, suggesting their potential for applications in biomedical imaging and other areas requiring stable and bright fluorescent systems.

Dual-Stream Feature Collaboration Perception Network for Salient Object Detection in Remote Sensing Images

As the core technology of artificial intelligence, salient object detection (SOD) is an important approach to improve the analysis efficiency of remote sensing images by intelligently identifying key areas in images. However, existing methods that rely on a single strategy, convolution or Transformer, exhibit certain limitations in complex remote sensing scenarios. Therefore, we developed a Dual-Stream Feature Collaboration Perception Network (DCPNet) to enable the collaborative work and feature complementation of Transformer and CNN. First, we adopted a dual-branch feature extractor with strong local bias and long-range dependence characteristics to perform multi-scale feature extraction from remote sensing images. Then, we presented a Multi-path Complementary-aware Interaction Module (MCIM) to refine and fuse the feature representations of salient targets from the global and local branches, achieving fine-grained fusion and interactive alignment of dual-branch features. Finally, we proposed a Feature Weighting Balance Module (FWBM) to balance global and local features, preventing the model from overemphasizing global information at the expense of local details or from inadequately mining global cues due to excessive focus on local information. Extensive experiments on the EORSSD and ORSSD datasets demonstrated that DCPNet outperformed the current 19 state-of-the-art methods.

Ultrasonic TFM imaging inspection of large complex rings using defect quantitative evaluation mappings

ABSTRACT Large complex rings are widely used in wind power energy, aerospace, large construction machinery. There are different scales of defects in the manufacturing process for large complex rings. Because of the complex cross-section and large thickness, it is difficult to quantitative evaluation of defects by conventional ultrasonic technology. Therefore, the ultrasonic total focusing method (TFM) defect quantitative inspection for large complex rings is proposed in this paper. First, the TFM inspection technology of large complex rings for simultaneous scanning of the end-face and side-face is designed. Then, the maximum amplitudes of defects are collected at each grid point of the imaging area by the TFM inspection of calibration specimens. The Φ1.5mm defect quantitative evaluation mappings are obtained by the interpolation fitting algorithm. Finally, the ultrasonic TFM and B-scan inspection experiments of the Φ3440mm large ring are carried out. The results show that the TFM quantitative evaluation mapping has higher accuracy compared to the conventional B-scan method. Especially for the Φ1.5mm defects, the average error of TFM quantitative evaluation is 2.92%. The proposed method can effectively identify defects of other sizes that exceed the calibration mapping. This work has industrial application value for developing ultrasonic TFM inspection of large complex components.

Segmentation Synergy with a Dual U-Net and Federated Learning with CNNRF Models for Enhanced Brain Tumor Analysis.

Brain tumours represent a diagnostic challenge, especially in the imaging area, where the differentiation of normal and pathologic tissues should be precise. The use of up-to-date machine learning techniques would be of great help in terms of brain tumor identification accuracy from MRI data. Objective This research paper aims to check the efficiency of a federated learning method that joins two classifiers, such as convolutional neural networks (CNNs) and random forests (R.F.F.), with dual U-Net segmentation for federated learning. This procedure benefits the image identification task on preprocessed MRI scan pictures that have already been categorized. In addition to using a variety of datasets, federated learning was utilized to train the CNN-RF model while taking data privacy into account. The processed MRI images with Median, Gaussian, and Wiener filters are used to filter out the noise level and make the feature extraction process easy and efficient. The surgical part used a dual U-Net layout, and the performance assessment was based on precision, recall, F1-score, and accuracy. The model achieved excellent classification performance on local datasets as CRPs were high, from 91.28% to 95.52% for macro, micro, and weighted averages. Throughout the process of federated averaging, the collective model outperformed by reaching 97% accuracy compared to those of 99%, which were subjected to different clients. The correctness of how data is used helps the federated averaging method convert individual model insights into a consistent global model while keeping all personal data private. The combined structure of the federated learning framework, CNN-RF hybrid model, and dual U-Net segmentation is a robust and privacypreserving approach for identifying MRI images from brain tumors. The results of the present study exhibited that the technique is promising in improving the quality of brain tumor categorization and provides a pathway for practical utilization in clinical settings.

Unifying Building Instance Extraction and Recognition in UAV Images

Building instance extraction and recognition (BEAR) extracts and further recognizes building instances in unmanned aerial vehicle (UAV) images, holds with paramount importance in urban understanding applications. To address this challenge, we propose a unified network, BEAR-Former. Given the difficulty of building instance recognition due to the small area and multiple instances in UAV images, we developed a novel multi-view learning method, Cross-Mixer. This method constructs a cross-regional branch and an intra-regional branch to, respectively, extract the global context dependencies and local spatial structural details of buildings. In the cross-regional branch, we cleverly employed cross-attention and polar coordinate relative position encoding to learn more discriminative features. To solve the BEAR problem end to end, we designed a channel group and fusion module (CGFM) as a shared encoder. The CGFM includes a channel group encoder layer to independently extract features and a channel fusion module to dig out the complementary information for multiple tasks. Additionally, an RoI enhancement strategy was designed to improve model performance. Finally, we introduced a new metric, Recall@(K, iou), to evaluate the performance of the BEAR task. Experimental results demonstrate the effectiveness of our method.

Super-resolution water body mapping with a feature collaborative CNN model by fusing Sentinel-1 and Sentinel-2 images

Mapping water bodies from remotely sensed imagery is crucial for understanding hydrological and biogeochemical processes. The identification of water extent is mainly dependent on optical and synthetic aperture radar (SAR) images. However, the use of remote sensing for water body mapping is often undermined by the mixed pixel dilemma inherent to traditional hard classification approaches. At the same time, the presence of clouds in optical imagery and speckle noise in SAR imagery, coupled with the difficulty in differentiating between water-like surfaces and actual water bodies, significantly compromise the accuracy of water body identification. This paper proposes a DEEP feature collaborative convolutional neural network (CNN) for Water Super-Resolution Mapping based on Optical and SAR images (DeepOSWSRM), which collaboratively leverages Sentinel-1 and Sentinel-2 imagery to address the challenges of missing data and mixed pixels. The Sentinel-1 image provides complementary water distribution information for the cloudy areas of the Sentinel-2 image, while the Sentinel-2 image enhances the perception capabilities for small water bodies in the Sentinel-1 image. Using PlanetScope imagery as the true reference data, the effectiveness of the proposed method was assessed through two experimental scenarios: one utilizing synthetic coarse-resolution imagery degraded from Sentinel-1 and Sentinel-2 data and another using actual Sentinel-1 and Sentinel-2 data, encompassing both simulated and real cloud conditions. A comparative analysis was conducted against three state-of-the-art CNN-based water mapping methods and two CNN SRM methods. The findings demonstrate that the proposed DeepOSWSRM method successfully produces accurate, fine-resolution water body maps, with its performance mainly benefiting from the fusion of SAR and optical images.

Multifocal microscopy for functional imaging of neural systems.

Rapid acquisition of large imaging volumes with microscopic resolution is an essential unmet need in biological research, especially for monitoring rapid dynamical processes such as fast activity in distributed neural systems. We present a multifocal strategy for fast, volumetric, diffraction-limited resolution imaging over relatively large and scalable fields of view (FOV) using single-camera exposures. Our multifocal microscopy approach leverages diffraction to image multiple focal depths simultaneously. It is based on a custom-designed diffractive optical element suited to low magnification and large FOV applications and customized prisms for chromatic correction, allowing for wide bandwidth fluorescence imaging. We integrate this system within a conventional microscope and demonstrate that our design can be used flexibly with a variety of magnification/numerical aperture (NA) objectives. We first experimentally and numerically validate this system for large FOV microscope imaging (three orders-of-magnitude larger volumes than previously shown) at resolutions compatible with cellular imaging. We then demonstrate the utility of this approach by visualizing high resolution three-dimensional (3D) distributed neural network at volume rates up to 100Hz. These demonstrations use genetically encoded indicators to measure functional neural imaging both in vitro and in vivo. Finally, we explore its potential in other important applications, including blood flow visualization and real-time, microscopic, volumetric rendering. Our study demonstrates the advantage of diffraction-based multifocal imaging techniques for 3D imaging of mm-scale objects from a single-camera exposure, with important applications in functional neural imaging and other areas benefiting from volumetric imaging.

Ultra-lightweight convolution-transformer network for early fire smoke detection

BackgroundForests are invaluable resources, and fire is a natural process that is considered an integral part of the forest ecosystem. Although fire offers several ecological benefits, its frequent occurrence in different parts of the world has raised concerns in the recent past. Covering millions of hectares of forest land, these fire incidents have resulted in the loss of human lives, wild habitats, civil infrastructure, and severe damage to the environment. Around 90% of wildland fires have been caused by humans intentionally or unintentionally. Early detection of fire close to human settlements and wildlife centuries can help mitigate fire hazards. Numerous artificial intelligence-based solutions have been proposed in the past decade that prioritize the detection of fire smoke, as it can be caught through remote sensing and provide an early sign of wildland fire. However, most of these methods are either computationally intensive or suffer from a high false alarm rate. In this paper, a lightweight deep neural network model is proposed for fire smoke detection in images captured by satellites or other remote sensing sources.ResultsWith only 0.6 million parameters and 0.4 billion floating point operations per second, the hybrid network of convolutional and vision transformer blocks efficiently detects smoke in normal and foggy environmental conditions. It outperforms seven state-of-the-art methods on four datasets, including a self-collected dataset from the “Moderate Resolution Imaging Spectroradiometer” satellite imagery. The model achieves an accuracy of more than 99% on three datasets and 93.90% on the fourth dataset. The t-distributed stochastic neighbor embedding of extracted features by the proposed model demonstrates its superior feature learning capabilities. It is remarkable that even a tiny occurrence of smoke covering just 2% of the satellite image area is efficiently detected by the model.ConclusionsWith low memory and computational demands, the proposed model works exceedingly well, making it suitable for deployment in resource constrained devices for forest surveillance and early fire smoke detection.

A novel multiscale cGAN approach for enhanced salient object detection in single haze images

In computer vision, image dehazing is a low-level task that employs algorithms to analyze and remove haze from images, resulting in haze-free visuals. The aim of Salient Object Detection (SOD) is to locate the most visually prominent areas in images. However, most SOD techniques applied to visible images struggle in complex scenarios characterized by similarities between the foreground and background, cluttered backgrounds, adverse weather conditions, and low lighting. Identifying objects in hazy images is challenging due to the degradation of visibility caused by atmospheric conditions, leading to diminished visibility and reduced contrast. This paper introduces an innovative approach called Dehaze-SOD, a unique integrated model that addresses two vital tasks: dehazing and salient object detection. The key novelty of Dehaze-SOD lies in its dual functionality, seamlessly integrating dehazing and salient object identification into a unified framework. This is achieved using a conditional Generative Adversarial Network (cGAN) comprising two distinct subnetworks: one for image dehazing and another for salient object detection. The first module, designed with residual blocks, Dark Channel Prior (DCP), total variation, and the multiscale Retinex algorithm, processes the input hazy images. The second module employs an enhanced EfficientNet architecture with added attention mechanisms and pixel-wise refinement to further improve the dehazing process. The outputs from these subnetworks are combined to produce dehazed images, which are then fed into our proposed encoder–decoder framework for salient object detection. The cGAN is trained with two modules working together: the generator aims to produce haze-free images, whereas the discriminator distinguishes between the generated haze-free images and real haze-free images. Dehaze-SOD demonstrates superior performance compared to state-of-the-art dehazing methods in terms of color fidelity, visibility enhancement, and haze removal. The proposed method effectively produces high-quality, haze-free images from various hazy inputs and accurately detects salient objects within them. This makes Dehaze-SOD a promising tool for improving salient object detection in challenging hazy conditions. The effectiveness of our approach has been validated using benchmark evaluation metrics such as mean absolute error (MAE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM).

DCFusion: Difference correlation-driven fusion mechanism of infrared and visible images

In end-to-end image fusion models, the loss function significantly impacts performance. However, most loss functions treat salient and background regions in source images equally, failing to distinguish complementary areas in multimodal images. This limits the model’s ability to effectively integrate information from these regions. Therefore, we propose difference correlation-driven fusion mechanism of infrared and visible images, which called DCFusion. Specifically, the model utilizes a dual-branch interactive network that dynamically fuses cross-modal multi-scale complementary information through element-wise multiplication, effectively integrating region-specific information. We introduce a two-stage method for generating salient target masks that adaptively focus on high-contrast regions in infrared images by analyzing pixel contrasts in local areas. Furthermore, we utilize the salient target masks to create heterogeneous images and design the LSCD loss function to minimize the information gap between the heterogeneous images and the fused image, thereby enhancing the model’s interpretability. Experiments on the RoadScene and TNO datasets show that DCFusion surpasses with existing representativity fusion approaches, achieving state-of-the-art performance in both subjective visual and objective evaluations. Our code will be publicly available at https://github.com/MinLila/DCFusion.

Lamb wave based damage imaging in variable thickness plates

The researches on Lamb wave based damage localization for constant thickness plates have been widely investigated in the field of structural health monitoring, while the issue of Lamb wave based damage imaging in variable thickness plates is rarely addressed. This is because the Lamb wave propagation characteristics in plates with varying thickness is more complex than that with constant thickness. In this study, a Lamb wave based damage imaging method using a sensor array is proposed for damage localization in variable thickness plates. In the process of point-by-point imaging within the interested imaging area, a signal back-propagation operator based on a Lamb wave propagation model can deal with the problem of dispersion compensation for Lamb waves propagating in variable thickness plates. The Lamb wave propagation model, which is based on the assumption that Lamb waves propagating in a variable thickness plate can be seen as that propagating in a sequence of short and constant thickness plates with different thicknesses, can predict Lamb wave response waveform in variable thickness plates. Numerical simulations and experiments on aluminum plates with linearly varying thicknesses are implemented, and the imaging results validate the effectiveness of the proposed method.