Search

Various techniques were combined to optimize an optical inspection system designed to automatically inspect defects in manufactured paper bowls. A self-assembled system was utilized to capture images of defects on the bowls. The system employed an image sensor with a multi-pixel array that combined a complementary metal-oxide semiconductor and a photo detector. A combined ring light served as the light source, while an infrared (IR) LED matrix panel was used to provide constant IR light to highlight the outer edges of the objects being inspected. The techniques employed in this study to enhance defect inspections on produced paper bowls included Gaussian filtering, Sobel operators, binarization, and connected components. Captured images were processed using these technologies. Once the non-contact inspection system's machine vision method was completed, defects on the produced paper bowls were inspected using the system developed in this study. Three inspection methods were used in this study: internal inspection, external inspection, and bottom inspection. All three methods were able to inspect surface features of produced paper bowls, including dirt, burrs, holes, and uneven thickness. The results of our study showed that the average time required for machine vision inspections of each paper bowl was significantly less than the time required for manual inspection. Therefore, the investigated machine vision system is an efficient method for inspecting defects in fabricated paper bowls. [ABSTRACT FROM AUTHOR]

Video halftoning is a key technology for use in electronic paper (e-paper) or smart paper, which is an emerging display device that has received considerable attention recently. In this paper, a temporal frequency of flickering-distortion optimized video halftoning method is proposed. We first uncover three visual defects that conventional neighboring frame referencing-based video halftoning methods, due to their sequential changes of reference frames, will encounter. To deal with the problem, we then propose a reference frame update per GOP-based error diffusion video halftoning method based on a flickering sensitivity-based human visual model. To efficiently compromise between average temporal frequency of flickering (ATFoF) and visual quality, temporal frequency of flickering-distortion (TFoFD) is presented as a metric for video halftoning performance evaluation. Based on the proposed probability model of video halftoning, the TFoFD curve can be accurately estimated to optimize the tradeoff between quality and ATFoF before the video is halftoned. Our temporal frequency of flickering-distortion optimization strategy can also be applied to other video halftoning schemes for performance improvement. Experimental results and comparisons with known methods demonstrate the effectiveness of our video halftoning method. [ABSTRACT FROM PUBLISHER]

Electrical switching of nanophotonic structural color elements is a promising approach towards addressable color switching pixels for next generation reflective displays. However, electrical switching between the primary colors to colorless near-white state remains a challenge. Here, we present a reversible electrical switching approach, relying on the electrocoagulation of Ag nanoparticles between silicon nanostructures that support Mie resonances. The electrodeposited Ag nanoparticles enable the excitation of the hybrid plasmon-Mie resonance as supported on Ag-silicon nanostructures, resulting in a large spectral transformation. Importantly, this process is reversible. This device design outperforms other designs in terms of electrotonic color control since it is highly stable and reliable for use in high-resolution reflective displays, such as colored electronic papers and smart display glass, where the combination is scalable to other nanostructure designs and electrolytic solutions. [ABSTRACT FROM AUTHOR]

Digital camouflage is a common countermeasure against military reconnaissance. In the face of high-tech imaging reconnaissance, battlefield detection means tend to be automated and refined. In order to adapt to the concealment requirements under various environmental backgrounds, combined with the camouflage performance of digital camouflage and its feedback mechanism in camouflage pattern design, this paper proposed a digital camouflage pattern design method based on biased random walk. Firstly, the original background is preprocessed, and the background texture's direction, corner, step length, and pixel intensity difference are statistically analyzed, and the boundary probability between pixel nodes is estimated. Then, a biased random walk is used to outline the camouflage patches. The edge scatter is enriched according to the density of the patches, and the camouflage patches are filled according to the proportion of the main color of the background. Finally, a digital camouflage pattern is obtained. The quantitative analysis results show that the mean heart rate of the digital camouflage pattern based on multiscene design is at least 31.0% higher than that of the original background segmentation texture, and the standard deviation index of equivalent diameter is increased by 14.9% on average. In addition, the results of simulation camouflage image detection in multiple scenes show that the proposed method can effectively deal with camouflage target detection on the basis of fully retaining the original background texture information and has strong camouflage concealment effect in the scene. [ABSTRACT FROM AUTHOR]

The precise segmentation of retinal vasculature is crucial for the early screening of various eye diseases, such as diabetic retinopathy and hypertensive retinopathy. Given the complex and variable overall structure of retinal vessels and their delicate, minute local features, the accurate extraction of fine vessels and edge pixels remains a technical challenge in the current research. To enhance the ability to extract thin vessels, this paper incorporates a pyramid channel attention module into a U-shaped network. This allows for more effective capture of information at different levels and increased attention to vessel-related channels, thereby improving model performance. Simultaneously, to prevent overfitting, this paper optimizes the standard convolutional block in the U-Net with the pre-activated residual discard convolution block, thus improving the model's generalization ability. The model is evaluated on three benchmark retinal datasets: DRIVE, CHASE_DB1, and STARE. Experimental results demonstrate that, compared to the baseline model, the proposed model achieves improvements in sensitivity (Sen) scores of 7.12%, 9.65%, and 5.36% on these three datasets, respectively, proving its strong ability to extract fine vessels. [ABSTRACT FROM AUTHOR]

Manuscript binarization is used to convert each pixel in the script image into text and background. Many manuscript binarization methods have been proposed, such as the Otsu, Bernsen, Sauvola, Niblack, Phansalkar and Singh methods. These methods only focus on one problem of a degraded manuscript. In this research, a deep learning approach based on the U-Net method is applied for binarization of degraded ancient manuscripts. Adding layers to the U-Net architecture can cause more parameters and excessive computational calculations. Residual U-Net (ResUNet) is a development of the U-Net method. ResUNet, with its residual blocks, enables efficient and effective feature extraction, capturing fine details of degraded documents. This is important for identifying and distinguishing text from various artifacts and noise in the document. ResUNet can handle various types of image degradation thanks to its residual blocks that prevent gradient loss and strengthen features over the network. Convolutional Long Short-Term Memory (ConvLSTM) is a variant of LSTM (Long Short-Term Memory) designed for spatial data such as images. ConvLSTM combines the ability of LSTM to learn long-term dependencies with the power of CNN in processing spatial data. The combination of ResUNet and ConvLSTM for binarization of degraded documents is a powerful strategy that leverages the power of both architectures to improve quality and accuracy in separating text from degraded background. The aim of this research is to determine the performance evaluation results of the combination of ResUNet and ConvLSTM architectures on the binarization of degraded ancient Javanese manuscripts. The trial was conducted using datasets taken from several museums. The dataset consists of 1200 images of Javanese ancient manuscripts that were damaged in the form of perforated paper, ink bleed through from the previous page, and red or brownish spots. The proposed method produces a loss value of 0.0559, F-Measure 92.89%, PSNR 18.52 dan IoU 0.85. [ABSTRACT FROM AUTHOR]

This paper presents a comparatively simple approach for showthrough and strikethrough print defect detection using computer vision method. Showthrough and strikethrough are common printing problem and are typically functions of a paper's opacity. Under normal lighting condition the visibility of printing on the reverse side of printed paper is termed as showthrough whereas the penetration of ink to the other side is termed as strikethrough. Moreover the intensity of showthrough pixel is extremely low thus it is difficult to identify the showthrough pixel from the printed area. On the other hand strikethrough is the result of penetration of ink through paper and depends on the absorbent nature of paper. Comparatively the intensity of the strikethrough pixel is higher than that of the showthrough but due to similar intensity of the ink of the printed pixel and strikethrough pixel, both overlapped with each other in the foreground of the image. These print defects can degrade the image quality as well as print production. In this study, the detection of these two print defects achieved using histogram equalization technique, to enhance the contrast between foreground and back ground pixels. A global thresholding algorithm was applied on a histogram equalized image to segment the printed area from the background of the image. Pixels in the background which are considered as showthrough and strike through pixels are identified by image subtraction. The pictorial representations of the results show the remarkable potential of the proposed technique which can be possible alternative of present subjective measures of showthrough and strikethrough. [ABSTRACT FROM AUTHOR]

Small UAV target detection and tracking based on cross-modality image fusion have gained widespread attention. Due to the limited feature information available from small UAVs in images, where they occupy a minimal number of pixels, the precision required for detection and tracking algorithms is particularly high in complex backgrounds. Image fusion techniques can enrich the detailed information for small UAVs, showing significant advantages under extreme lighting conditions. Image registration is a fundamental step preceding image fusion. It is essential to achieve accurate image alignment before proceeding with image fusion to prevent severe ghosting and artifacts. This paper specifically focused on the alignment of small UAV targets within infrared and visible light imagery. To address this issue, this paper proposed a cross-modality image registration network based on deep learning, which includes a structure preservation and style transformation network (SPSTN) and a multi-level cross-attention residual registration network (MCARN). Firstly, the SPSTN is employed for modality transformation, transferring the cross-modality task into a single-modality task to reduce the information discrepancy between modalities. Then, the MCARN is utilized for single-modality image registration, capable of deeply extracting and fusing features from pseudo infrared and visible images to achieve efficient registration. To validate the effectiveness of the proposed method, comprehensive experimental evaluations were conducted on the Anti-UAV dataset. The extensive evaluation results validate the superiority and universality of the cross-modality image registration framework proposed in this paper, which plays a crucial role in subsequent image fusion tasks for more effective target detection. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the SSD algorithm does not fully extract the feature information contained in each feature layer, as well as the feature information is easily lost during the sampling process, which makes the feature expression ineffective and leads to insufficient performance in small target detection. In this paper, AMT-SSD is proposed, a small target detection algorithm that incorporates the multi-branch stacking and new sampling transition module of the attention mechanism. In this algorithm, the composite attention mechanism is utilized to improve the correlation of features of the samples to be detected in terms of spatial and channels, and the efficiency of the algorithm; secondly, multi-branch stacking module is used to extract multi-size features for each feature layer, and different sizes of convolution kernels are utilized in parallel to fully extract their features and improve the expression of features; meanwhile, during the sampling process, the problem of missing features is solved by applying inverse subpixel convolution in the new sampling transition module. Experimentally, the AMT-SSD algorithm achieves 84.6% and 53.4% mAP metrics on the PASCAL VOC dataset and MS COCO dataset, respectively. This indicates that the AMT-SSD algorithm can effectively extract feature information that is beneficial to detection samples, and also performs well in reducing feature loss, which is effective for the algorithm to improve the algorithm on small targets. [ABSTRACT FROM AUTHOR]

The difficulty of lane detection lies in the imbalance of the number of target pixels and background pixels. The sparse target distribution misleads the neural network to pay more attention to background segmentation in order to obtain a better loss convergence result. This makes it difficult for some models to detect lane line pixels and leads to the training fail (unable to output useful lane information). Increasing receptive field properly can enlarge the sphere of action between pixels, so as to restrain this trouble. Moreover, the interference information and noise existing in the real environment increase the difficulty of lane classification, such as vehicle occlusion, car glass reflection, and tree shadow. In this paper, we do think that the features obtained by the reasonable combination of receptive fields can help avoid oversegmentation of the image, so that most of the interference information can be filtered out. Based on this idea, Adaptive Receptive Field Net (ARFNet) is proposed to solve the problem of receptive field combination with the help of multireceptive field aggregation layers and scoring mechanism. This paper explains the working principle of ARFNet and analyzes several results of experiments, which are carried out to adjust network structure parameters in order to get better effects in the CuLane dataset testing. [ABSTRACT FROM AUTHOR]

The focus of this paper is impulse noise reduction in digital color images. The most popular noise reduction schemes are the vector median filter and its many variants that operate by minimizing the aggregate distance from one pixel to every other pixel in a chosen window. This minimizing operation determines the most confirmative pixel based on its similarity to the chosen window and replaces the central pixel of the window with the determined one. The peer group filters, unlike the vector median filters, determine a set of pixels that are most confirmative to the window and then perform filtering over the determined set. Using a set of pixels in the filtering process rather than one pixel is more helpful as it takes into account the full information of all the pixels that seemingly contribute to the signal. Hence, the peer group filters are found to be more robust to noise. However, the peer group for each pixel is computed deterministically using thresholding schemes. A wrong choice of the threshold will easily impair the filtering performance. In this paper, we propose a peer group filtering approach using principles of Bayesian probability theory and clustering. Here, we present a method to compute the probability that a pixel value is clean (not corrupted by impulse noise) and then apply clustering on the probability measure to determine the peer group. The key benefit of this proposal is that the need for thresholding in peer group filtering is completely avoided. Simulation results show that the proposed method performs better than the conventional vector median and peer group filtering methods in terms of noise reduction and structural similarity, thus validating the proposed approach. [ABSTRACT FROM AUTHOR]

Generalized target detection algorithms perform well for large- and medium-sized targets but struggle with small ones. However, with the growing importance of aerial images in urban transportation and environmental monitoring, detecting small targets in such imagery has been a promising research hotspot. The challenge in small object detection lies in the limited pixel proportion and the complexity of feature extraction. Moreover, current mainstream detection algorithms tend to be overly complex, leading to structural redundancy for small objects. To cope with these challenges, this paper recommends the PCSG model based on yolov5, which optimizes both the detection head and backbone networks. (1) An enhanced detection header is introduced, featuring a new structure that enhances the feature pyramid network and the path aggregation network. This enhancement bolsters the model's shallow feature reuse capability and introduces a dedicated detection layer for smaller objects. Additionally, redundant structures in the network are pruned, and the lightweight and versatile upsampling operator CARAFE is used to optimize the upsampling algorithm. (2) The paper proposes the module named SPD-Conv to replace the strided convolution operation and pooling structures in yolov5, thereby enhancing the backbone's feature extraction capability. Furthermore, Ghost convolution is utilized to optimize the parameter count, ensuring that the backbone meets the real-time needs of aerial image detection. The experimental results from the RSOD dataset show that the PCSG model exhibits superior detection performance. The value of mAP increases from 97.1% to 97.8%, while the number of model parameters decreases by 22.3%, from 1,761,871 to 1,368,823. These findings unequivocally highlight the effectiveness of this approach. [ABSTRACT FROM AUTHOR]

Pixel‐level labeling of regions of interest in an image is a key step in building a labeled training dataset for supervised deep learning networks of images. However, traditional manual labeling of cancerous regions in digital pathological images by doctors is time‐consuming and inefficient. To address this issue, this paper proposes an automatic labeling method for whole slide images, which combines clustering and edge detection techniques. The proposed method utilizes the multi‐level feature fusion model and the Long‐Short Term Memory network to discriminate the cancerous nature of the whole slide images, thereby improving the classification accuracy of the whole slide images. Subsequently, the automatic labeling of cancerous regions is achieved by integrating a density‐based clustering algorithm and an edge point extraction algorithm, both based on the discriminated results of the cancerous properties of whole slide images. The experimental results demonstrate the effectiveness of the proposed method, which offers an efficient and accurate solution to the challenging task of cancerous region labeling in digital pathological images. [ABSTRACT FROM AUTHOR]

The canopy height model (CHM) derived from LiDAR point cloud data is usually used to accurately identify the position and the canopy dimension of single tree. However, local invalid values (also called data pits) are often encountered during the generation of CHM, which results in low-quality CHM and failure in the detection of treetops. For this reason, this paper proposes an innovative method, called "pixels weighted differential gradient", to filter these data pits accurately and improve the quality of CHM. First, two characteristic parameters, gradient index (GI) and Z-score value (ZV) are extracted from the weighted differential gradient between the pit pixels and their eight neighbors, and then GIs and ZVs are commonly used as criterion for initial identification of data pits. Secondly, CHMs of different resolutions are merged, using the image processing algorithm developed in this paper to distinguish either canopy gaps or data pits. Finally, potential pits were filtered and filled with a reasonable value. The experimental validation and comparative analysis were carried out in a coniferous forest located in Triangle Lake, United States. The experimental results showed that our method could accurately identify potential data pits and retain the canopy structure information in CHM. The root-mean-squared error (RMSE) and mean bias error (MBE) from our method are reduced by between 73% and 26% and 76% and 28%, respectively, when compared with six other methods, including the mean filter, Gaussian filter, median filter, pit-free, spike-free and graph-based progressive morphological filtering (GPMF). The average F1 score from our method could be improved by approximately 4% to 25% when applied in single-tree extraction. [ABSTRACT FROM AUTHOR]

In recent years, Federated Learning has attracted much attention because it solves the problem of data silos in machine learning to a certain extent. However, many studies have shown that attacks based on Generative Adversarial Networks pose a great threat to Federated Learning. This paper proposes Defense-GAN, a defense method against Generative Adversarial Network attacks under Federated Learning. Under this method, the attacker cannot learn the real image data distribution. Each Federated Learning participant uses SHAP to explain the model and masks the pixel features that have a greater impact on classification and recognition in their respective image data. The experimental results show that while attacking the federated training model using masked images, the attacker cannot always obtain the ground truth of the images. At the same time, this paper also uses CutMix to improve the generalization ability of the model, and the obtained model accuracy is only 1% different from that of the model trained with the original data. The results show that the defense method proposed in this paper can not only resist Generative Adversarial Network attacks in Federated Learning and protect client privacy, but also ensure that the model accuracy of the Federated model will not be greatly affected. [ABSTRACT FROM AUTHOR]

To address the issues of blurred details and distortion of color in the images recovered by the original AOD-Net dehazing method, this paper proposes a CPAD-Net dehazing network model based on attention mechanism and dense residual blocks. The network is improved on the basis of AOD-Net, which can reduce the errors arising from the separately determined transmittance and atmospheric light values. A new dense residual block structure is designed to replace the traditional convolution method, which effectively improves the detail processing capability and the representation ability of the network model for image feature information. On this basis, the attention module determines how to learn the weights according to the feature importance of distinct channels and distinct pixels, and then obtain the recovery of images in terms of color and texture. The experiments showed that the dehazing efficiency of our method are richer in texture detail information and more natural in color recovery. Compared with other algorithms, the PSNR and SSIM indexes of our method are considerably superior to those listed algorithms, which definitively demonstrates that the dehazing effect of our method is more effective, and the recovered images are more realistic and natural. [ABSTRACT FROM AUTHOR]

Visual Cryptography (VC) is a process employed for the maintenance of secret information by hiding the secret messages that are embedded within the images. Typically, an image is partitioned into a number of shares that are stacked over one another in order to reconstruct back the original image accurately. The major limitation that existed in the traditional VC techniques is pixel expansion, in which pixel expansion is replaced with a number of sub-pixels in individual share, which causes a considerable impact on the contrast and resolution of the image that further gradually decreases the quality of the image. VC is named for its essential characteristics, such as transmitting the images with two or more shares with an equal number of black pixels and color pixel distribution. The secret message can be decrypted using Human Visual System (HVS). In this paper, 50 research papers are reviewed based on various classification algorithms, which are effectively used for the VC technique. The classification algorithms are categorized into three types, namely, meta-heuristic, heuristic, and evolutionary, and the research issues and challenges confronted by the existing techniques are reported in this survey. Moreover, the analysis is done based on the existing research works by considering the classification algorithms, tools, and evaluation metrics. [ABSTRACT FROM AUTHOR]

In this paper, we present a new objective quality metric designed for immersive video applications—IV-SSIM. The proposed IV-SSIM metric is an evolution of our previous work—IV-PSNR (immersive video peak signal-to-noise ratio)—which became a commonly used metric in research and ISO/IEC MPEG standardization activities on immersive video. IV-SSIM combines the advantages of IV-PSNR and metrics based on the structural similarity of images, being able to properly mimic the subjective quality perception of immersive video with its characteristic distortions induced by the reprojection of pixels between multiple views. The effectiveness of IV-SSIM was compared with 16 state-of-the-art quality metrics (including other metrics designed for immersive video). Tested metrics were evaluated in an immersive video coding scenario and against a commonly used image quality database—TID2013—showing their performance in both immersive and typical, non-immersive use cases. As presented, the proposed IV-SSIM metric clearly outperforms other metrics in immersive video applications, while also being highly competitive for 2D image quality assessment. The authors of this paper have provided a publicly accessible, efficient implementation of the proposed IV-SSIM metric, which is used by ISO/IEC MPEG video coding experts in the development of the forthcoming second edition of the MPEG immersive video (MIV) coding standard. [ABSTRACT FROM AUTHOR]

The Arnold Cat Map (ACM) is a popular chaotic map used in image encryption. Chaotic maps are known for their sensitivity to initial conditions and their ability to permute, or rearrange, pixels. However, ACM is periodic, and its period is relatively short. This periodicity decreases the effective key-space and security of a cryptosystem using ACM. Further, ACM is typically only able to be performed on square images. To solve the low periodicity and typical limitation to square images, this paper proposes performing ACM on overlapping square partitions which cover the entirety of an image. The presence of overlap results in a greatly increased image period. The resulting system will be referred to as overlapping ACM or OACM. Several papers have already discussed systems involving overlapping ACM. However, they did not discuss the implementation or periodicity of such a system in detail. This paper does cover the implementation and periodicity analysis of OACM and proposes a simple symmetric encryption system which uses OACM. The proposed encryption system is not as sophisticated or secure as other modern encryption schemes, since it is mainly intended as an initial test of OACM's utility. Histogram and sensitivity analyses did however indicate a level of security against various cryptographic attacks, and OACM performed reasonably in both the permutation and diffusion stages of the cryptosystem. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Xi'an Polytechnic University is the property of Editorial Department of Journal of Xi'an Polytechnic University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To address the high complexity and low accuracy issues of traditional methods in mixed coal vitrinite identification, this paper proposes a method based on an improved DeepLabv3+ network. First, MobileNetV2 is used as the backbone network to reduce the number of parameters. Second, an atrous convolution layer with a dilation rate of 24 is added to the ASPP (atrous spatial pyramid pooling) module to further increase the receptive field. Meanwhile, a CBAM (convolutional block attention module) attention mechanism with a channel multiplier of 8 is introduced at the output part of the ASPP module to better filter out important semantic features. Then, a corrective convolution module is added to the network's output to ensure the consistency of each channel's output feature map for each type of vitrinite. Finally, images of 14 single vitrinite components are used as training samples for network training, and a validation set is used for identification testing. The results show that the improved DeepLabv3+ achieves 6.14% and 3.68% improvements in MIOU (mean intersection over union) and MPA (mean pixel accuracy), respectively, compared to the original DeepLabv3+; 12% and 5.3% improvements compared to U-Net; 9.26% and 4.73% improvements compared to PSPNet with ResNet as the backbone; 5.4% and 9.34% improvements compared to PSPNet with MobileNetV2 as the backbone; and 6.46% and 9.05% improvements compared to HRNet. Additionally, the improved ASPP module increases MIOU and MPA by 3.23% and 1.93%, respectively, compared to the original module. The CBAM attention mechanism with a channel multiplier of 8 improves MIOU and MPA by 1.97% and 1.72%, respectively, compared to the original channel multiplier of 16. The data indicate that the proposed identification method significantly improves recognition accuracy and can be effectively applied to mixed coal vitrinite identification. [ABSTRACT FROM AUTHOR]

Visual ranging technology holds great promise in various fields such as unmanned driving and robot navigation. However, complex dynamic environments pose significant challenges to its accuracy and robustness. Existing monocular visual ranging methods are susceptible to scale uncertainty, while binocular visual ranging is sensitive to changes in lighting and texture. To overcome the limitations of single visual ranging, this paper proposes a fusion method for monocular and binocular visual ranging based on an adaptive Unscented Kalman Filter (AUKF). The proposed method first utilizes a monocular camera to estimate the initial distance based on the pixel size, and then employs the triangulation principle with a binocular camera to obtain accurate depth. Building upon this foundation, a probabilistic fusion framework is constructed to dynamically fuse monocular and binocular ranging using the AUKF. The AUKF employs nonlinear recursive filtering to estimate the optimal distance and its uncertainty, and introduces an adaptive noise-adjustment mechanism to dynamically update the observation noise based on fusion residuals, thus suppressing outlier interference. Additionally, an adaptive fusion strategy based on depth hypothesis propagation is designed to autonomously adjust the noise prior of the AUKF by combining current environmental features and historical measurement information, further enhancing the algorithm's adaptability to complex scenes. To validate the effectiveness of the proposed method, comprehensive evaluations were conducted on large-scale public datasets such as KITTI and complex scene data collected in real-world scenarios. The quantitative results demonstrate that the fusion method significantly improves the overall accuracy and stability of visual ranging, reducing the average relative error within an 8 m range by 43.1% and 40.9% compared to monocular and binocular ranging, respectively. Compared to traditional methods, the proposed method significantly enhances ranging accuracy and exhibits stronger robustness against factors such as lighting changes and dynamic targets. The sensitivity analysis further confirmed the effectiveness of the AUKF framework and adaptive noise strategy. In summary, the proposed fusion method effectively combines the advantages of monocular and binocular vision, significantly expanding the application range of visual ranging technology in intelligent driving, robotics, and other fields while ensuring accuracy, robustness, and real-time performance. [ABSTRACT FROM AUTHOR]

In the spectrum measurement experiment, the roughness of the object surface is an essential factor that cannot be ignored. In this experiment, a group of mixed pixel samples with different mixing ratios were designed, and these samples were printed on four kinds of papers with different roughness. The spectral characteristics of mixed pixels with different roughness are quantitatively analyzed by using the measured spectral data. The linear spectral mixture model is used for spectral decomposition, and the effect of roughness on the unmixing precision of mixed pixels was studied. The surface roughness will affect the reflectivity of the mixed pixel. Specifically, the higher the roughness is, the higher the reflectivity of the sample is. This phenomenon is more noticeable when the proportion of white endmember (PWE) is large, and as the white area ratio decreases, the reflectance difference gradually decreases. When the surface roughness of the sample is less than 3.339 μm, the spectral decomposition is performed using a linear spectral mixing model in the visible light band. The average error of the unmixing is less than 0.53%, which is lower than the conventional standard spectral measurement error. In other words, when the surface roughness of the sample is controlled within a specific range, the effect of roughness on the unmixing accuracy of the mixed pixels is small, and this effect can be almost ignored. Multiple scattering within the pixels is the key to model selection and unmixing accuracy, when using the ASD FieldSpec3 spectrometer to perform spectral reflectance measurement and linear spectral unmixing experiments. If the surface roughness of the sample to be measured is less than the maximum wavelength of the spectrometer, the experimental results believe that the photon energy is mainly mirror reflection on the surface of the object and diffuse reflection. At this time, it is still a better choice to use a linear spectral mixing model to decompose the mixed pixels. [ABSTRACT FROM AUTHOR]

Urban green spaces (UGS) play a crucial role in the urban environmental system by aiding in mitigating the urban heat island effect, promoting sustainable urban development, and ensuring the physical and mental well-being of residents. The utilization of remote sensing imagery enables the real-time surveying and mapping of UGS. By analyzing the spatial distribution and spectral information of a UGS, it can be found that the UGS constitutes a kind of low-rank feature. Thus, the accuracy of the UGS segmentation model is not heavily dependent on the depth of neural networks. On the contrary, emphasizing the preservation of more surface texture features and color information contributes significantly to enhancing the model's segmentation accuracy. In this paper, we proposed a UGS segmentation model, which was specifically designed according to the unique characteristics of a UGS, named the Green Space Reverse Pixel Shuffle Network (GSRPnet). GSRPnet is a straightforward but effective model, which uses an improved RPS-ResNet as the feature extraction backbone network to enhance its ability to extract UGS features. Experiments conducted on GaoFen-2 remote sensing imagery and the Wuhan Dense Labeling Dataset (WHDLD) demonstrate that, in comparison with other methods, GSRPnet achieves superior results in terms of precision, F1-score, intersection over union, and overall accuracy. It demonstrates smoother edge performance in UGS border regions and excels at identifying discrete small-scale UGS. Meanwhile, the ablation experiments validated the correctness of the hypotheses and methods we proposed in this paper. Additionally, GSRPnet's parameters are merely 17.999 M, and this effectively demonstrates that the improvement in accuracy of GSRPnet is not only determined by an increase in model parameters. [ABSTRACT FROM AUTHOR]

This paper presents our new formaldehyde (H2CO) retrievals, obtained from spectra recorded by the nadir instrument of the Ozone Mapping and Profiler Suite (OMPS) flown on-board NASA's Suomi National Polar-orbiting Partnership (SUOMI-NPP) satellite. Our algorithm is similar to the one currently in place for the production of NASA's Ozone Monitoring Instrument (OMI) operational H2CO product. We are now able to produce a consistent set of long term data from two different instruments that share a similar concept. The ongoing overlap period between OMI and OMPS offers a perfect opportunity to study the consistency between both data sets. The different spatial and spectral resolution of the instruments is a source of discrepancy in the retrievals despite the similarity of the physic assumptions of the algorithm. We have concluded that the reduced spectral resolution of OMPS in comparison with OMI is not a significant obstacle in obtaining good quality retrievals. Indeed, the improved signal to noise ratio (SNR) of OMPS with respect to OMI helps to reduce the noise of the retrievals performed using OMPS spectra. However, the size of OMPS spatial pixels imposes a limitation in the capability to distinguish particular features of H2CO that are discernible with OMI. With root mean square (RMS) residuals ~5×10-4 for individual pixels we estimate the detection limit to be about 7.5×1015 moleculescm-2. Total vertical column densities (VCD) errors for individual pixels range between 40% for pixels with high concentrations to 100% or more for pixels with concentrations at or below the detection limit. We compare different OMI products with our OMPS product using one year of data, between September 2012 and September 2013. The seasonality of the retrieved slant columns is captured similarly by all products but there are discrepancies in the values of the VCDs. The mean biases among the two OMI products and our OMPS product are 21% between OMI SAO and OMPS SAO and 38% between OMI BIRA and OMPS SAO for eight selected regions. [ABSTRACT FROM AUTHOR]

Every year, the number of women affected by breast tumors is increasing worldwide. Hence, detecting and segmenting the cancer regions in mammogram images is important to prevent death in women patients due to breast cancer. The conventional methods obtained low sensitivity and specificity with cancer region segmentation accuracy. The high-resolution standard mammogram images were supported by conventional methods as one of the main drawbacks. The conventional methods mostly segmented the cancer regions in mammogram images concerning their exterior pixel boundaries. These drawbacks are resolved by the proposed cancer region detection methods stated in this paper. The mammogram images are classified into normal, benign, and malignant types using the Adaptive Neuro- Fuzzy Inference System (ANFIS) approach in this paper. This mammogram classification process consists of a noise filtering module, spatial-frequency transformation module, feature computation module, and classification module. The Gaussian Filtering Algorithm (GFA) is used as the pixel smooth filtering method and the Ridgelet transform is used as the spatial-frequency transformation module. The statistical Ridgelet feature metrics are computed from the transformed coefficients and these values are classified by theANFIS technique in this paper. Finally, Probability Histogram Segmentation Algorithm (PHSA) is proposed in this work to compute and segment the tumor pixels in the abnormal mammogram images. This proposed breast cancer detection approach is evaluated on the mammogram images in MIAS and DDSM datasets. From the extensive analysis of the proposed tumor detection methods stated in this work with other works, the proposed work significantly achieves a higher performance. The methodologies proposed in this paper can be used in breast cancer detection hospitals to assist the breast surgeon to detect and segment the cancer regions. [ABSTRACT FROM AUTHOR]

Fragile watermarking is embedding a watermark in a media (an image in this paper) such that even small changes, called tamper, can be detected or even recovered to prevent unauthorized alteration. A well-known category of spatial fragile watermarking methods is based on embedding the watermark in the least significant bits of the image to preserve the quality. In addition, Hamming code is a coding algorithm in communication that transmits the data bits by augmenting some check bits to detect and recover single-bit modifications precisely. This property was previously used to detect and perfectly recover the images modified by small tampers less than a quarter of the image in diameter. To achieve this goal, the Hamming code is applied on a distributed pixel, bits of which are gathered from sufficient far pixels in the image. It guarantees that such tampers can toggle at most one bit of each distributed Hamming code that is recoverable. It was the only guaranteed perfect reconstruction method of small tampers, based on our knowledge. In this paper, the method has been extended to support distortion in two bits of a Hamming code by the use of common structures of distributed codes. It guarantees the recovery of tampers less than half of the image in width and height. According to the experimental results, the proposed method achieved better performance, in terms of recovering the tampered areas, in comparison to state-of-the-art. [ABSTRACT FROM AUTHOR]

Polarimetric calibration is one of the preprocessing steps in the quantitative processing of Polarimetric synthetic aperture radar (PolSAR) data, and its accuracy will affect subsequent applications. At present, the polarimetric calibration method based on distributed targets is widely used, and this kind of method needs to extract distributed targets that satisfy certain scattering characteristics as the calibration reference ground object samples before calibrating. Therefore, the extraction accuracy of distributed targets has a great influence on the accuracy of polarimetric calibration methods based on such targets. Therefore, this paper proposes a new distribution target extraction method, which is based on the idea of KS hypothesis testing, and uses the homogeneity of the pixels in the window to determine whether it is a distribution target. To verify the effectiveness of the method, the X-band airborne PolSAR images are used as the data of the polarimetric calibration experiment. Experiments show that, compared with other extraction methods, our method can not only ensure the extraction accuracy of distributed targets, but also further improve the accuracy of polarimetric calibration. [ABSTRACT FROM AUTHOR]

3D modeling is the most basic technology to realize VR (virtual reality). VOS (video object segmentation) is a pixel-level task, which aims to segment the moving objects in each frame of the video. Combining theory with practice, this paper studies the process of 3D virtual scene construction, and on this basis, researches the optimization methods of 3D modeling. In this paper, an unsupervised VOS algorithm is proposed, which initializes the target by combining the moving edge of the target image and the appearance edge of the target and assists the modeling of the VR 3D model, which has reference significance for the future construction of large-scale VR scenes. The results show that the segmentation accuracy of this algorithm can reach more than 94%, which is about 9% higher than that of the FASTSEG method. 3D modeling technology is the foundation of 3D virtual scene; so, it is of practical significance to study the application of 3D modeling technology. At the same time, it is of positive significance to use the unsupervised VOS algorithm to assist the VR 3D model modeling. [ABSTRACT FROM AUTHOR]

In order to effectively protect and verify the copyright information of multimedia digital works, this paper proposes a zero-watermarking algorithm based on carrier image feature point descriptors. The constructed feature matrix of this algorithm consists of two parts: the feature descriptor vector calculated from scale-invariant feature reconstruction transform (SIFRT) and the multi-radius local binary pattern (MrLBP) descriptor vector. The algorithm performs a standardization, feature decomposition, and redundancy reduction on the traditional keypoint descriptor matrix, combines it with the texture feature matrix, and achieves the dimensional matching of copyright information. The advantage of this algorithm lies in its non-modification of the original data. Compared to computing global features, the local features computed from a subset of key points reduce the amount of attack interference introduced during copyright verification, thereby reducing the number of erroneous pixel values that are introduced. The algorithm introduces a timestamp mechanism when uploading the generated zero-watermarking image to a third-party copyright center, preventing subsequent tampering. Experimental data analysis demonstrates that the algorithm exhibits good discriminability, security, and robustness. [ABSTRACT FROM AUTHOR]

Accurate and comprehensive detection of pavement cracks is important for maintaining road quality and ensuring traffic safety. However, the complexity of road surfaces and the diversity of cracks make it difficult for existing methods to accomplish this challenging task. This paper proposes a novel network named the global graph multiscale network (GGMNet) for automated pixel-level detection of pavement cracks. The GGMNet network has several innovations compared with the mainstream road crack detection network: (1) a global contextual Res-block (GC-Resblock) is proposed to guide the network to emphasize the identities of cracks while suppressing background noises; (2) a graph pyramid pooling module (GPPM) is designed to aggregate the multi-scale features and capture the long-range dependencies of cracks; (3) a multi-scale features fusion module (MFF) is established to efficiently represent and deeply fuse multi-scale features. We carried out extensive experiments on three pavement crack datasets. These were DeepCrack dataset, with complex background noises; the CrackTree260 dataset, with various crack structures; and the Aerial Track Detection dataset, with a drone's perspective. The experimental results demonstrate that GGMNet has excellent performance, high accuracy, and strong robustness. In conclusion, this paper provides support for accurate and timely road maintenance and has important reference values and enlightening implications for further linear feature extraction research. [ABSTRACT FROM AUTHOR]

This paper introduces a novel loss function, the boundary Gaussian distance loss, designed to enhance character segmentation in high-resolution scans of old metal-type printed documents. Despite various printing defects caused by low-quality printing technology in the 14th and 15th centuries, the proposed loss function allows the segmentation network to accurately extract character strokes that can be attributed to the typeface of the movable metal type used for printing. Our method calculates deviation between the boundary of predicted character strokes and the counterpart of the ground-truth strokes. Diverging from traditional Euclidean distance metrics, our approach determines the deviation indirectly utilizing boundary pixel-value difference over a Gaussian-smoothed version of the stroke boundary. This approach helps extract characters with smooth boundaries efficiently. Through experiments, it is confirmed that the proposed method not only smoothens stroke boundaries in character extraction, but also effectively eliminates noise and outliers, significantly improving the clarity and accuracy of the segmentation process. [ABSTRACT FROM AUTHOR]

The verification of image integrity has attracted increasing attention. Irreversible algorithms embed fragile watermarks into cover images to verify their integrity, but they are not reversible due to unrecoverable loss. In this paper, a new dual tampering detection scheme for reversible image fragile watermarking is proposed. The insect matrix reversible embedding algorithm is used to embed the watermark into the cover image. The cover image can be fully recovered when the dual-fragile-watermarked images are not tampered with. This study adopts two recovery schemes and adaptively chooses the most appropriate scheme to recover tampered data according to the square errors between the tampered data and the recovered data of two watermarked images. Tampering coincidence may occur when a large region of the fragile-watermarked image is tampered with, and the recovery information corresponding to the tampered pixels may be missing. The tampering coincidence problem is solved using image-rendering techniques. The experimental results show that the PSNR value of the watermarked image obtained using our scheme can reach 46.37 dB, and the SSIM value is 0.9942. In addition, high-accuracy tampering detection is achieved. [ABSTRACT FROM AUTHOR]

Superpixel segmentation can get the middle features in image processing, effectively reduce the dimensionality of the image, and is widely used in image processing fields. To get the regular and compact superpixels in real-time, a superpixel segmentation algorithm based on image density is proposed in this paper. Firstly, the image is uniformly divided according to the number of superpixels to be obtained. Secondly, to get the clustering ability of the pixels, the density image is produced. Thirdly, the seed is chosen in each sub-region block according to the density and then the superpixels are obtained by clustering. During the clustering process, the pixel around the seed should be added into the superpixel if it meets the conditions, and the small supeipixels are merged into the big superpixels around them. Finally, the result shows that the proposed algorithm has the best segmentation effect, and a good balance in accuracy, regularity, and time cost. [ABSTRACT FROM AUTHOR]

The pixels of remote images often contain more than one distinct material (mixed pixels), and so their spectra are characterized by a mixture of spectral signals. Since 1971, a shared effort has enabled the development of techniques for retrieving information from mixed pixels. The most analyzed, implemented, and employed procedure is spectral unmixing. Among the extensive literature on the spectral unmixing, nineteen reviews were identified, and each highlighted the many shortcomings of spatial validation. Although an overview of the approaches used to spatially validate could be very helpful in overcoming its shortcomings, a review of them was never provided. Therefore, this systematic review provides an updated overview of the approaches used, analyzing the papers that were published in 2022, 2021, and 2020, and a dated overview, analyzing the papers that were published not only in 2011 and 2010, but also in 1996 and 1995. The key criterion is that the results of the spectral unmixing were spatially validated. The Web of Science and Scopus databases were searched, using all the names that were assigned to spectral unmixing as keywords. A total of 454 eligible papers were included in this systematic review. Their analysis revealed that six key issues in spatial validation were considered and differently addressed: the number of validated endmembers; sample sizes and sampling designs of the reference data; sources of the reference data; the creation of reference fractional abundance maps; the validation of the reference data with other reference data; the minimization and evaluation of the errors in co-localization and spatial resampling. Since addressing these key issues enabled the authors to overcome some of the shortcomings of spatial validation, it is recommended that all these key issues be addressed together. However, few authors addressed all the key issues together, and many authors did not specify the spatial validation approach used or did not adequately explain the methods employed. [ABSTRACT FROM AUTHOR]

Pixel-level detection of expansion joints on complex pavements is significant for traffic safety and the structural integrity of highway bridges. This paper proposed an improved HRNet-OCR, named as expansion joints segmentation network (EJSNet), for automated pixel-level detection of the expansion joints on asphalt pavement. Different from the high-resolution network (HRNet), the proposed EJSNet modifies the residual structure of the first stage by conducting a Conv. + BN + ReLU (convolution + batch normalization + rectified linear unit) operation for each shortcut connection, which can avoid the network degradation. The feature selection module (FSM) and receptive field block (RFB) module are incorporated into the proposed EJSNet model to learn and extract the contexts at different resolution levels for enhanced latent representations. The convolutional block attention module (CBAM) is introduced to enhance the adaptive feature refinement of the network. Moreover, the shared multilayer perceptron (MLP) architecture of the channel attention module (CAM) is also modified in this paper. Experimental results demonstrate that the F-measure and intersection-over-union (IOU) attained by the proposed EJSNet model on 500 testing image sets are 95.14% and 0.9036, respectively. Compared with four state-of-the-art models for semantic segmentation (i.e., SegNet, DeepLabv3+, dual attention network (DANet), and HRNet-OCR), the proposed EJSNet model can yield higher detection accuracy on both private and public datasets. [ABSTRACT FROM AUTHOR]

The objects presented in synthetic-aperture radar (SAR) images are the products of the joint actions of ground objects and SAR sensors in specific geospatial contexts. With the accumulation of massive time-domain SAR data, scholars have the opportunity to better understand ground-object targets and sensor systems, providing some useful feedback for SAR-data processing. Aiming at normalized and low-cost SAR radiometric monitoring, this paper proposes a new hyper-pixel concept for handling multi-pixel ensembles of semantic ground targets. The special hyper-pixel in this study refers to low-rise single-family residential areas, and its radiation reference is highly stable in the time domain when the other dimensions are fixed. The stability of its radiometric data can reach the level of 0.3 dB (1 σ), as verified by the multi-temporal data from Sentinel-1. A comparison with tropical-rainforest data verified its availability for SAR radiometric monitoring, and possible radiation variations and radiation-intensity shifts in the Sentinel-1B SAR products ere experimentally monitored. In this paper, the effects of seasonal climate and of the relative geometrical states observed on the intensity of the hyper-pixel's radiation are investigated. This paper proposes a novel hyper-pixel concept for processing and interpreting SAR-image data. The proposed residential hyper-pixel is shown to be useful in multi-temporal-data observations for normalized radiometric monitoring and has the potential to be used for cross-calibration, in addition to other applications. [ABSTRACT FROM AUTHOR]

Aiming at the current lane line detection algorithm in complex traffic scenes, such as lane lines being blocked by shadows, blurred roads, and road sparseness, which lead to low lane line detection accuracy and poor real-time detection speed, this paper proposes a lane line detection algorithm based on instance segmentation. Firstly, the improved lightweight network RepVgg-A0 is used to encode road images, which expands the receptive field of the network; secondly, a multi-size asymmetric shuffling convolution model is proposed for the characteristics of sparse and slender lane lines, which enhances the ability to extract lane line features; an adaptive upsampling model is further proposed as a decoder, which upsamples the feature map to the original resolution for pixel-level classification and detection, and adds the lane line prediction branch to output the confidence of the lane line; and finally, the instance segmentation-based lane line detection algorithm is successfully deployed on the embedded platform Jetson Nano, and half-precision acceleration is performed using NVDIA's TensorRT framework. The experimental results show that the Acc value of the lane line detection algorithm based on instance segmentation is 96.7%, and the FPS is 77.5 fps/s. The detection speed deployed on the embedded platform Jetson Nano reaches 27 fps/s. [ABSTRACT FROM AUTHOR]

The article presents a study on the new Digital Elevation Model (DEM) of the Antarctic Peninsula based on the Advanced Spaceborne Emission and Reflection Radiometer (ASTER) Global Digital Elevation Model (GDEM) data. The study used a method to improve the ASTER GDEM dataset that will create a DEM with a 100 meter (m) pixel which is suitable for glaciological applications. The new DEM is evaluated using the Ice, Cloud and land Elevation Satellite (ICESat)-derived elevations.

It is of great scientific and practical value to use effective technical means to monitor and warn the structural damage of bridges in real time and for a long time. Traditional image recognition network models are often limited by the lack of on-site images. In order to solve the problem of automatic recognition and parameter acquisition in digital images of bridge structures in the absence of data information, this paper proposes an automatic identification method for bridge structure damage areas based on digital images, which effectively achieves contour carving and quantitative characterization of bridge structure damage areas. Firstly, the digital image features of the bridge structure damage area are defined. By making full use of the feature that the pixel value of the damaged area is obviously different from that of the surrounding image, an image pre-processing method of the structure damaged area that can effectively improve the quality of the field shot image is proposed. Then, an improved Ostu method is proposed to organically fuse the global and local threshold features of the image to achieve the damaged area contour carving of the bridge structure surface image. The scale of damage area, the proportion of damage area and the calculation rule of damage area orientation are constructed. The key inspection and characteristic parameter diagnosis of bridge structure damage area are realized. Finally, test and analysis are carried out in combination with an actual project case. The results show that the method proposed in this paper is feasible and stable, which can improve the damage area measurement accuracy of the current bridge structure. The method can provide more data support for the detection and maintenance of the bridge structure. [ABSTRACT FROM AUTHOR]

Chilies undergo multiple stages from field production to reaching consumers, making them susceptible to contamination with foreign materials. Visually similar foreign materials are difficult to detect manually or using color sorting machines, which increases the risk of their presence in the market, potentially affecting consumer health. This paper aims to enhance the detection of visually similar foreign materials in chilies using hyperspectral technology, employing object detection algorithms for fast and accurate identification and localization to ensure food safety. First, the samples were scanned using a hyperspectral camera to obtain hyperspectral image information. Next, a spectral pattern recognition algorithm was used to classify the pixels in the images. Pixels belonging to the same class were assigned the same color, enhancing the visibility of foreign object targets. Finally, an object detection algorithm was employed to recognize the enhanced images and identify the presence of foreign objects. Random forest (RF), support vector machine (SVM), and minimum distance classification algorithms were used to enhance the hyperspectral images of the samples. Among them, RF algorithm showed the best performance, achieving an overall recognition accuracy of up to 86% for randomly selected pixel samples. Subsequently, the enhanced targets were identified using object detection algorithms including R-CNN, Faster R-CNN, and YoloV5. YoloV5 exhibited a recognition rate of over 96% for foreign objects, with the shortest detection time of approximately 12 ms. This study demonstrates that the combination of hyperspectral imaging technology, spectral pattern recognition techniques, and object detection algorithms can accurately and rapidly detect challenging foreign objects in chili peppers, including red stones, red plastics, red fabrics, and red paper. It provides a theoretical reference for online batch detection of chili pepper products, which is of significant importance for enhancing the overall quality of chili pepper products. Furthermore, the detection of foreign objects in similar particulate food items also holds reference value. [ABSTRACT FROM AUTHOR]

Nearshore ship detection has significant applications in both the military and civilian domains. Compared to synthetic aperture radar (SAR), polarimetric synthetic aperture radar (PolSAR) provides richer information for analyzing the scattering mechanisms of ships and enables better detection of ship targets. However, ships in nearshore areas tend to be highly concentrated, and ship detection is often affected by adjacent strong scattering, resulting in false alarms or missed detections. While the GP-PNF detector performs well in PolSAR ship detection, it cannot obtain satisfactory results in these scenarios, and it also struggles in the presence of azimuthal ambiguity or strong clutter interference. To address these challenges, we propose a nearshore ship detection method named ECD-PNF by integrating superpixel-level GP-PNF and refined polarimetric decomposition. Firstly, polarimetric superpixel segmentation and sea–land segmentation are performed to reduce the influence of land on ship detection. To estimate the sea clutter more accurately, an automatic censoring (AC) mechanism combined with superpixels is used to select the sea clutter superpixels. By utilizing refined eight-component polarimetric decomposition to improve the scattering vector, the physical interpretability of the detector is enhanced. Additionally, the expression of polarimetric coherence is improved to enhance the target clutter ratio (TCR). Finally, this paper combines the third eigenvalue of eigenvalue–eigenvector decomposition to reduce the impact of azimuthal ambiguity. Three spaceborne PolSAR datasets from Radarsat-2 and GF-3 are adopted in the experiments for comparison. The proposed ECD-PNF method achieves the highest figure of merit (FoM) value of 0.980, 1.000, and 1.000 for three datasets, validating the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

The text in the natural scene can express rich semantic information, which helps people understand and analyse daily things. This paper focuses on the problems of discrete text spatial distribution and variable text geometric size in natural scenes with complex backgrounds and proposes an end‐to‐end natural scene text detection method based on DBNet. The authors first use IResNet as the backbone network, which does not increase network parameters while retaining more text features. Furthermore, a module with Transformer is introduced in the feature extraction stage to strengthen the correlation between high‐level feature pixels. Then, the authors add a spatial pyramid pooling structure in the end of feature extraction, which realises the combination of local and global features, enriches the expressive ability of feature maps, and alleviates the detection limitations caused by the geometric size of features. Finally, to better integrate the features of each level, a dual attention module is embedded after multi‐scale feature fusion. Extensive experiments on the MSRA‐TD500, CTW1500, ICDAR2015, and MLT2017 data set are conducted. The results showed that IDBNet can improve the average precision, recall, and F‐measure of a text compared with the state of art text detection methods and has higher predictive ability and practicability. [ABSTRACT FROM AUTHOR]