43,644 results on '"Image registration"'
Search Results
2. Image stitching algorithm based on two-stage optimal seam line search
- Author
-
Han, Guijin, Zhang, Yuanzheng, and Zhou, Mengchun
- Published
- 2024
- Full Text
- View/download PDF
3. Improving deep learning-based automatic cranial defect reconstruction by heavy data augmentation: From image registration to latent diffusion models
- Author
-
Wodzinski, Marek, Kwarciak, Kamil, Daniol, Mateusz, and Hemmerling, Daria
- Published
- 2024
- Full Text
- View/download PDF
4. CCMNet: Cross-scale correlation-aware mapping network for 3D lung CT image registration
- Author
-
Long, Li, Xue, Xufeng, and Xiao, Hanguang
- Published
- 2024
- Full Text
- View/download PDF
5. Contrast-insensitive motion correction for MRI cardiac T1 mapping
- Author
-
Yue, Chengyu, Huang, Lu, Huang, Lihong, Guo, Yi, Tao, Qian, Xia, Liming, and Wang, Yuanyuan
- Published
- 2025
- Full Text
- View/download PDF
6. WUTrans: Whole-spectrum unilateral-query-secured transformer for 4D CBCT reconstruction
- Author
-
Yuan, Peng, Lyu, Tianling, Lyu, Fei, Zhang, Yudong, Yang, Chunfeng, Zhu, Wentao, Gao, Zhiqiang, Wu, Zhan, Chen, Yang, Zhao, Wei, and Coatrieux, Jean Louis
- Published
- 2025
- Full Text
- View/download PDF
7. A visual analytical method for evaluating tool flank wear volumes of micro-milling cutters with AKAZE features matching: A preliminary study
- Author
-
Zhang, Yu, Gao, Shuaishuai, Duan, Xianyin, and Zhu, Kunpeng
- Published
- 2025
- Full Text
- View/download PDF
8. Fast and highly accurate registration of textile double-sided images: An innovative solution for the calibration of binocular measuring systems
- Author
-
Guo, Dan, Li, Nana, Fang, Changshuai, Li, Jiang, Tang, Yuxiao, and Zhang, Xiaodong
- Published
- 2025
- Full Text
- View/download PDF
9. Balancing data consistency and diversity: Preprocessing and online data augmentation for multi-center deep learning-based MR-to-CT synthesis
- Author
-
Han, Songyue, Hémon, Cédric, Texier, Blanche, Kortli, Yassin, Queffelec, Adélie, de Crevoisier, Renaud, Dowling, Jason, Greer, Peter, Bessières, Igor, Barateau, Anaïs, Lafond, Caroline, and Nunes, Jean-Claude
- Published
- 2025
- Full Text
- View/download PDF
10. EyeLiner: A Deep Learning Pipeline for Longitudinal Image Registration Using Fundus Landmarks
- Author
-
Veturi, Yoga Advaith, McNamara, Steve, Kinder, Scott, Clark, Christopher William, Thakuria, Upasana, Bearce, Benjamin, Manoharan, Niranjan, Mandava, Naresh, Kahook, Malik Y., Singh, Praveer, and Kalpathy-Cramer, Jayashree
- Published
- 2025
- Full Text
- View/download PDF
11. A survey on deep learning in medical image registration: New technologies, uncertainty, evaluation metrics, and beyond
- Author
-
Chen, Junyu, Liu, Yihao, Wei, Shuwen, Bian, Zhangxing, Subramanian, Shalini, Carass, Aaron, Prince, Jerry L., and Du, Yong
- Published
- 2025
- Full Text
- View/download PDF
12. AI-based tool for early detection of Alzheimer's disease
- Author
-
Ul Rehman, Shafiq, Tarek, Noha, Magdy, Caroline, Kamel, Mohammed, Abdelhalim, Mohammed, Melek, Alaa, N. Mahmoud, Lamees, and Sadek, Ibrahim
- Published
- 2024
- Full Text
- View/download PDF
13. Image registration method for full-field deformation measurement
- Author
-
Zhu, Yi, Wang, Qinghua, Xie, Xinyun, and Yan, Xiaojun
- Published
- 2025
- Full Text
- View/download PDF
14. Bone marrow sparing oriented multi-model image registration in cervical cancer radiotherapy
- Author
-
Wang, Yuening, Sun, Ying, Gan, Kexin, Yuan, Jie, Xu, Hanzi, Gao, Han, and Zhang, Xiuming
- Published
- 2023
- Full Text
- View/download PDF
15. CFOG-like image registration algorithm based on 3D-structural feature descriptor for suburban optical and SAR
- Author
-
Wang, Lina, Liang, Huaidan, Wang, Zhongshi, Xu, Rui, and Shi, Guangfeng
- Published
- 2023
- Full Text
- View/download PDF
16. Reliable Reference Areas for 3D Smiling Facial Model Alignment: Posed vs Natural Smile Expressions.
- Author
-
Hang-Nga Mai, Thaw Thaw Win, Chau Pham Duong, Jaewon Kim, Seok-Hwan Cho, and Du-Hyeong Lee
- Subjects
IMAGE registration ,BONFERRONI correction ,TWO-way analysis of variance ,SMILING ,SURFACE area - Abstract
Purpose: To evaluate the reliability of various reference areas for digital alignment between 3D resting and smiling facial models. Materials and Methods: 3D posed and natural smiling faces of 33 adults were registered to the respective neutral faces, using six matching strategies with different reference matching surfaces: nose (N), nose + central forehead (NFc), nose + whole forehead (NFw), nose + chin (NC), nose + central forehead + chin (NFcC), and nose + whole forehead + chin (NFwC). The positional discrepancies of the registered images were measured at the left and right pupil centers. Results: Two-way ANOVA and post hoc multiple pairwise t test with Bonferroni correction (α = .05) were used to evaluate the measurements. As a result, the use of larger reference areas increases the trueness of image-matching, whereas there was no statistically significant difference between the matching strategies within the same smiling type. Meanwhile, the image registration of posed smiles resulted in fewer positional disparities than the natural smiles with significant differences observed for the registration using the NC and NFcC surface-based matching areas at the right pupil (P = .030 and .026, respectively). Conclusions: The findings of this study suggest that the reference surface areas and smiling types have some impact on the accuracy of 3D smiling facial image alignments. Large and evenly distributed matching surfaces are recommended for posed smiles, whereas caution should be taken when using the chin area as a reference surface for matching natural smile facial images. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
17. Uncertainty-Guided Joint Semi-supervised Segmentation and Registration of Cardiac Images
- Author
-
Chen, Junjian, Yang, Xuan, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Ide, Ichiro, editor, Kompatsiaris, Ioannis, editor, Xu, Changsheng, editor, Yanai, Keiji, editor, Chu, Wei-Ta, editor, Nitta, Naoko, editor, Riegler, Michael, editor, and Yamasaki, Toshihiko, editor
- Published
- 2025
- Full Text
- View/download PDF
18. Accuracy of Image Registration During Similarity Transformation
- Author
-
Babayan, Pavel, Kozhina, Ekaterina, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Tan, Kay Chen, Series Editor, Kumar Singh, Koushlendra, editor, Singh, Sangeeta, editor, Srivastava, Subodh, editor, and Bajpai, Manish Kumar, editor
- Published
- 2025
- Full Text
- View/download PDF
19. Learning to Estimate Motion Between Non-adjacent Frames in Cardiac Cine MRI Data: A Fusion Approach
- Author
-
Portal, Nicolas, Dietenbeck, Thomas, Khan, Saud, Nguyen, Vincent, Prigent, Mikael, Zarai, Mohamed, Bouazizi, Khaoula, Sylvain, Johanne, Redheuil, Alban, Montalescot, Gilles, Kachenoura, Nadjia, Achard, Catherine, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Antonacopoulos, Apostolos, editor, Chaudhuri, Subhasis, editor, Chellappa, Rama, editor, Liu, Cheng-Lin, editor, Bhattacharya, Saumik, editor, and Pal, Umapada, editor
- Published
- 2025
- Full Text
- View/download PDF
20. Unsupervised Feature Matching for Affine Histological Image Registration
- Author
-
Pyatov, Vladislav A., Sorokin, Dmitry V., Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Antonacopoulos, Apostolos, editor, Chaudhuri, Subhasis, editor, Chellappa, Rama, editor, Liu, Cheng-Lin, editor, Bhattacharya, Saumik, editor, and Pal, Umapada, editor
- Published
- 2025
- Full Text
- View/download PDF
21. Beyond Intensity Transforms: Medical Image Synthesis Under Large Deformation
- Author
-
Chaudhary, Muhammad F. A., Reinhardt, Joseph M., Gerard, Sarah E., Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Fernandez, Virginia, editor, Wolterink, Jelmer M., editor, Wiesner, David, editor, Remedios, Samuel, editor, Zuo, Lianrui, editor, and Casamitjana, Adrià, editor
- Published
- 2025
- Full Text
- View/download PDF
22. ISAApp – Image Based Smart Attendance Application
- Author
-
Dutta, Aritra, Suseela, G., Niranjana, G., Boral, Pushpita, Gupta, Pranav, Pal, Subha Bal, Ghosh, Ashish, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Geetha, R., editor, Dao, Nhu-Ngoc, editor, and Khalid, Saeed, editor
- Published
- 2025
- Full Text
- View/download PDF
23. A Survey on Deep Learning-Based Medical Image Registration
- Author
-
Xu, Ronghao, Liu, Chongxin, Liu, Shuaitong, Huang, Weijie, Zhang, Menghua, Ghosh, Ashish, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Zhang, Haijun, editor, Li, Xianxian, editor, Hao, Tianyong, editor, Meng, Weizhi, editor, Wu, Zhou, editor, and He, Qian, editor
- Published
- 2025
- Full Text
- View/download PDF
24. AutoCT: Automated CT registration, segmentation, and quantification
- Author
-
Bai, Zhe, Essiari, Abdelilah, Perciano, Talita, and Bouchard, Kristofer E
- Subjects
Medical and Biological Physics ,Information and Computing Sciences ,Physical Sciences ,Biomedical Imaging ,Bioengineering ,Networking and Information Technology R&D (NITRD) ,4.1 Discovery and preclinical testing of markers and technologies ,Computed tomography ,Image registration ,Diffeomorphic mapping ,Image segmentation ,Quantitative analysis ,Computer Software - Abstract
The processing and analysis of computed tomography (CT) imaging is important for both basic scientific development and clinical applications. In AutoCT, we provide a comprehensive pipeline that integrates an end-to-end automatic preprocessing, registration, segmentation, and quantitative analysis of 3D CT scans. The engineered pipeline enables atlas-based CT segmentation and quantification leveraging diffeomorphic transformations through efficient forward and inverse mappings. The extracted localized features from the deformation field allow for downstream statistical learning that may facilitate medical diagnostics. On a lightweight and portable software platform, AutoCT provides a new toolkit for the CT imaging community to underpin the deployment of artificial intelligence-driven applications.
- Published
- 2024
25. Chapter Eight - Image registration for 3D medical images
- Author
-
Nair, Rekha R. and Babu, Tina
- Published
- 2025
- Full Text
- View/download PDF
26. ClearFinder: a Python GUI for annotating cells in cleared mouse brain.
- Author
-
Pastore, Stefan, Hillenbrand, Philipp, Molnar, Nils, Kovlyagina, Irina, Chongtham, Monika Chanu, Sys, Stanislav, Lutz, Beat, Tevosian, Margarita, and Gerber, Susanne
- Subjects
- *
QUALITY control , *GRAPHICAL user interfaces , *IMAGE registration , *USER interfaces , *THREE-dimensional imaging - Abstract
Background: Tissue clearing combined with light-sheet microscopy is gaining popularity among neuroscientists interested in unbiased assessment of their samples in 3D volume. However, the analysis of such data remains a challenge. ClearMap and CellFinder are tools for analyzing neuronal activity maps in an intact volume of cleared mouse brains. However, these tools lack a user interface, restricting accessibility primarily to scientists proficient in advanced Python programming. The application presented here aims to bridge this gap and make data analysis accessible to a wider scientific community. Results: We developed an easy-to-adopt graphical user interface for cell quantification and group analysis of whole cleared adult mouse brains. Fundamental statistical analysis, such as PCA and box plots, and additional visualization features allow for quick data evaluation and quality checks. Furthermore, we present a use case of ClearFinder GUI for cross-analyzing the same samples with two cell counting tools, highlighting the discrepancies in cell detection efficiency between them. Conclusions: Our easily accessible tool allows more researchers to implement the methodology, troubleshoot arising issues, and develop quality checks, benchmarking, and standardized analysis pipelines for cell detection and region annotation in whole volumes of cleared brains. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
27. Constructions of multi-scale 3D digital rocks by associated image segmentation method.
- Author
-
Wang, Haiyan, Yang, Xuefeng, Zhou, Cong, Yan, Jingxu, Yu, Jiaqi, and Xie, Kui
- Subjects
IMAGE segmentation ,X-ray computed microtomography ,ELASTIC modulus ,THREE-dimensional imaging ,IMAGE registration - Abstract
Digital rocks constructed from micro-CT image at a single-resolution face limitations in accurately identifying the entire pore space and mineral components of tight sandstones, due to their high content of nanoscale pores and clay. Consequently, the porosity values derived from such digital rocks are significantly lower compared to those obtained through laboratory measurements, resulting in discrepancies between the measured and calculated petrophysical properties. This study introduces a multi-scale digital rock modeling method by integrating three-dimensional micro-CT images acquired at two distinct resolutions and two-dimensional SEM images. Plunger-shaped core samples and their corresponding sub-samples were scanned at resolutions of 13.99 μm/voxel and 2.99 μm/voxel, respectively. The scale-invariant feature transform (SIFT) image registration technique was employed to accurately align the two sets of grayscale CT images. Correlation curves between the grayscale value in low-resolution CT images and various mineral contents were established based on the aligned regions, and utilized to construct multi-scale digital rock models. Intragranular pores, unresolvable by the micro-CT images, were identified using SEM imaging, enabling the incorporation of fine-scale features into the models. The resulting multi-scale digital rock models exhibited bulk porosity values that closely matched laboratory helium porosity measurements. Additionally, the elastic moduli calculated by the differential effective medium (DEM) model and the finite element method (FEM) demonstrated good correspondence with experimental results. These results validate the proposed multi-scale digital rock modeling method as an effective approach for accurately characterizing the porosity and mineral components of tight sandstone reservoirs. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
28. COph100: A comprehensive fundus image registration dataset from infants constituting the "RIDIRP" database.
- Author
-
Hu, Yan, Gong, Mingdao, Qiu, Zhongxi, Liu, Jiabao, Shen, Hongli, Yuan, Mingzhen, Zhang, Xiaoqing, Li, Heng, Lu, Hai, and Liu, Jiang
- Subjects
DATABASES ,RETINAL imaging ,DISEASE progression ,INFANT diseases ,INFANTS ,IMAGE registration - Abstract
Retinal image registration is vital for diagnostic therapeutic applications within the field of ophthalmology. Existing public datasets, focusing on adult retinal pathologies with high-quality images, have limited number of image pairs and neglect clinical challenges. To address this gap, we introduce COph100, a novel and challenging dataset known as the Comprehensive Ophthalmology Retinal Image Registration dataset for infants with a wide range of image quality issues constituting the public "RIDIRP" database. COph100 consists of 100 eyes, each with 2 to 9 examination sessions, amounting to a total of 491 image pairs carefully selected from the publicly available dataset. We manually labeled the corresponding ground truth image points and provided automatic vessel segmentation masks for each image. We have assessed COph100 in terms of image quality and registration outcomes using state-of-the-art algorithms. This resource enables a robust comparison of retinal registration methodologies and aids in the analysis of disease progression in infants, thereby deepening our understanding of pediatric ophthalmic conditions. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
29. A Line Feature-Based Rotation Invariant Method for Pre- and Post-Damage Remote Sensing Image Registration.
- Author
-
Zhao, Yalun, Chen, Derong, and Gong, Jiulu
- Abstract
The accurate registration of pre- and post-damage images plays a vital role in the change analysis of the target area and the subsequent work of damage effect assessment. However, due to the impact of shooting time and damaged areas, there are large background and regional differences between pre- and post-damage remote sensing images, and the existing image registration methods do not perform well. In this paper, a line feature-based rotation invariant image registration method is proposed for pre- and post-damage remote sensing images. First, we extract and screen straight line segments from the images before and after damage. Then, we design a new method to calculate the main direction of each line segment and rotate the image based on the current line segment's main direction and the center coordinates. According to the spatial distribution (distance and angle) of the reference line segment relative to the remaining line segments, a line feature descriptor vector is constructed and matched for each line segment on the rotated image. Since the main edge contour can preserve more invariant features, this descriptor can be better applied to the registration of pre- and post-damage remote sensing images. Finally, we cross-pair the midpoints and endpoints of the matched line segments to improve the accuracy of subsequent affine transformation parameter calculations. In remote sensing images with large background and regional differences, the average registration precision of our method is close to 100%, and the root mean square error is about 1 pixel. At the same time, the rotation invariance of our method is verified by rotating the test images. In addition, the results of the comparative experiments show that the registration precision and error of the proposed method are better than those of the existing typical representative algorithms. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
30. Virtual Gram staining of label-free bacteria using dark-field microscopy and deep learning.
- Author
-
Işıl, Çağatay, Koydemir, Hatice Ceylan, Eryilmaz, Merve, de Haan, Kevin, Pillar, Nir, Mentesoglu, Koray, Unal, Aras Firat, Rivenson, Yair, Chandrasekaran, Sukantha, Garner, Omai B., and Ozcan, Aydogan
- Subjects
- *
LISTERIA innocua , *IMAGE registration , *DEEP learning , *ESCHERICHIA coli , *MICROSCOPY , *GRAM'S stain - Abstract
Gram staining has been a frequently used staining protocol in microbiology. It is vulnerable to staining artifacts due to, e.g., operator errors and chemical variations. Here, we introduce virtual Gram staining of label-free bacteria using a trained neural network that digitally transforms dark-field images of unstained bacteria into their Gram-stained equivalents matching bright-field image contrast. After a one-time training, the virtual Gram staining model processes an axial stack of dark-field microscopy images of label-free bacteria (never seen before) to rapidly generate Gram staining, bypassing several chemical steps involved in the conventional staining process. We demonstrated the success of virtual Gram staining on label-free bacteria samples containing Escherichia coli and Listeria innocua by quantifying the staining accuracy of the model and comparing the chromatic and morphological features of the virtually stained bacteria against their chemically stained counterparts. This virtual bacterial staining framework bypasses the traditional Gram staining protocol and its challenges, including stain standardization, operator errors, and sensitivity to chemical variations. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
31. MRgRT real-time target localization using foundation models for contour point tracking and promptable mask refinement.
- Author
-
Blöcker, Tom, Lombardo, Elia, Marschner, Sebastian N, Belka, Claus, Corradini, Stefanie, Palacios, Miguel A, Riboldi, Marco, Kurz, Christopher, and Landry, Guillaume
- Subjects
- *
MAGNETIC resonance imaging , *ARTIFICIAL intelligence , *DEEP learning , *EUCLIDEAN distance , *IMAGE registration - Abstract
Objective. This study aimed to evaluate two real-time target tracking approaches for magnetic resonance imaging (MRI) guided radiotherapy (MRgRT) based on foundation artificial intelligence models. Approach. The first approach used a point-tracking model that propagates points from a reference contour. The second approach used a video-object-segmentation model, based on segment anything model 2 (SAM2). Both approaches were evaluated and compared against each other, inter-observer variability, and a transformer-based image registration model, TransMorph, with and without patient-specific (PS) fine-tuning. The evaluation was carried out on 2D cine MRI datasets from two institutions, containing scans from 33 patients with 8060 labeled frames, with annotations from 2 to 5 observers per frame, totaling 29179 ground truth segmentations. The segmentations produced were assessed using the Dice similarity coefficient (DSC), 50% and 95% Hausdorff distances (HD50 / HD95), and the Euclidean center distance (ECD). Main results. The results showed that the contour tracking (median DSC 0.92 ± 0.04 and ECD 1.9 ± 1.0 mm) and SAM2-based (median DSC 0.93 ± 0.03 and ECD 1.6 ± 1.1 mm) approaches produced target segmentations comparable or superior to TransMorph w/o PS fine-tuning (median DSC 0.91 ± 0.07 and ECD 2.6 ± 1.4 mm) and slightly inferior to TransMorph w/ PS fine-tuning (median DSC 0.94 ± 0.03 and ECD 1.4 ± 0.8 mm). Between the two novel approaches, the one based on SAM2 performed marginally better at a higher computational cost (inference times 92 ms for contour tracking and 109 ms for SAM2). Both approaches and TransMorph w/ PS fine-tuning exceeded inter-observer variability (median DSC 0.90 ± 0.06 and ECD 1.7 ± 0.7 mm). Significance. This study demonstrates the potential of foundation models to achieve high-quality real-time target tracking in MRgRT, offering performance that matches state-of-the-art methods without requiring PS fine-tuning. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
32. Quantifying the spatial distribution of the accumulated dose uncertainty using the novel delta index.
- Author
-
van den Dobbelsteen, Madelon, Hackett, Sara L, Bosma, Lando S, van Doormaal, Renate J A, van Asselen, Bram, and Fast, Martin F
- Subjects
- *
STEREOTACTIC radiotherapy , *IMAGE registration - Abstract
Objective. Inter- and intra-fractional anatomical changes during a radiotherapy treatment can cause differences between the initially planned dose and the delivered dose. The total delivered dose can be accumulated over all fractions by using deformable image registration (DIR). However, there is uncertainty in this process which should be accounted for. The aim of this study is to propose a novel metric estimating the spatial distribution of the accumulated dose uncertainty and to evaluate its performance for multi-fraction online adaptive treatments. Approach. We postulate a new metric, the delta (δ) index, to estimate the uncertainties associated with the dose accumulation process. This metric is calculated for each voxel and takes into account the spatial uncertainty in DIR and local dose differences. For the spatial uncertainty of the DIR, the distance discordance metric was used. The accumulated dose and the δ index were determined for ten lung stereotactic body radiation therapy patients. The δ index was complemented by a more understandable metric, the δ index passing rate, which is the percentage of points satisfying the passing criteria in a region. Main results. The spatial distribution of the δ index and the δ index passing rates showed that voxels failing the criteria were predominantly in lower-dose regions. The mean percentage of voxels passing the criterion increased from 65% to 78%, for threshold doses of 20% and 90% of the prescription doses, respectively. Significance. The δ index was postulated to quantify the spatial distribution of the uncertainties associated with the dose accumulation process. The metric gives an intuitive understanding of the reliability of accumulated dose distributions and derived DVH metrics. The performance of the δ index was evaluated for multi-fraction online adaptive treatments, where a case of sub-optimal image registration was identified by the metric. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
33. Research on wave measurement and simulation experiments of binocular stereo vision based on intelligent feature matching.
- Author
-
Wu, Junjie, Chen, Shizhe, Liu, Shixuan, Song, Miaomiao, Wang, Bo, Zhang, Qingyang, Wu, Yushang, Lei, Zhuo, Zhang, Jiming, Yan, Xingkui, and Miao, Bin
- Subjects
BINOCULAR vision ,PYRAMIDS ,IMAGE registration ,OCEAN ,ALGORITHMS ,STEREO vision (Computer science) ,PROTOTYPES - Abstract
Waves are crucial in ocean observation and research. Stereo vision-based wave measurement, offering non-contact, low-cost, and intelligent processing, is an emerging method. However, improving accuracy remains a challenge due to wave complexity. This paper presents a novel approach to measure wave height, period, and direction by combining deep learning-based stereo matching with feature matching techniques. To improve the discontinuity and low accuracy in disparity maps from traditional wave image matching algorithms, this paper proposes the use of a high-precision stereo matching method based on Pyramid Stereo Matching Network (PSM-Net).A 3D reconstruction method integrating Scale-Invariant Feature Transform (SIFT) with stereo matching was also introduced to overcome the limitations of template matching and interleaved spectrum methods, which only provide 2D data and fail to capture the full 3D motion of waves. This approach enables accurate wave direction measurement. Additionally, a six-degree-of-freedom platform was proposed to simulate waves, addressing the high costs and attenuation issues of traditional wave tank simulations. Experimental results show the prototype system achieves a wave height accuracy within 5%, period accuracy within 4%, and direction accuracy of ±2°, proving the method's effectiveness and offering a new approach to stereo vision-based wave measurement. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
34. Intraoperative Augmented Reality for Vitreoretinal Surgery Using Edge Computing.
- Author
-
Ye, Run Zhou and Iezzi, Raymond
- Abstract
Purpose: Augmented reality (AR) may allow vitreoretinal surgeons to leverage microscope-integrated digital imaging systems to analyze and highlight key retinal anatomic features in real time, possibly improving safety and precision during surgery. By employing convolutional neural networks (CNNs) for retina vessel segmentation, a retinal coordinate system can be created that allows pre-operative images of capillary non-perfusion or retinal breaks to be digitally aligned and overlayed upon the surgical field in real time. Such technology may be useful in assuring thorough laser treatment of capillary non-perfusion or in using pre-operative optical coherence tomography (OCT) to guide macular surgery when microscope-integrated OCT (MIOCT) is not available. Methods: This study is a retrospective analysis involving the development and testing of a novel image-registration algorithm for vitreoretinal surgery. Fifteen anonymized cases of pars plana vitrectomy with epiretinal membrane peeling, along with corresponding preoperative fundus photographs and optical coherence tomography (OCT) images, were retrospectively collected from the Mayo Clinic database. We developed a TPU (Tensor-Processing Unit)-accelerated CNN for semantic segmentation of retinal vessels from fundus photographs and subsequent real-time image registration in surgical video streams. An iterative patch-wise cross-correlation (IPCC) algorithm was developed for image registration, with a focus on optimizing processing speeds and maintaining high spatial accuracy. The primary outcomes measured were processing speed in frames per second (FPS) and the spatial accuracy of image registration, quantified by the Dice coefficient between registered and manually aligned images. Results: When deployed on an Edge TPU, the CNN model combined with our image-registration algorithm processed video streams at a rate of 14 FPS, which is superior to processing rates achieved on other standard hardware configurations. The IPCC algorithm efficiently aligned pre-operative and intraoperative images, showing high accuracy in comparison to manual registration. Conclusions: This study demonstrates the feasibility of using TPU-accelerated CNNs for enhanced AR in vitreoretinal surgery. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
35. Non-Rigid Cycle Consistent Bidirectional Network with Transformer for Unsupervised Deformable Functional Magnetic Resonance Imaging Registration.
- Author
-
Wang, Yingying, Feng, Yu, and Zeng, Weiming
- Abstract
Background: In neuroscience research about functional magnetic resonance imaging (fMRI), accurate inter-subject image registration is the basis for effective statistical analysis. Traditional fMRI registration methods are usually based on high-resolution structural MRI with clear anatomical structure features. However, this registration method based on structural information cannot achieve accurate functional consistency between subjects since the functional regions do not necessarily correspond to anatomical structures. In recent years, fMRI registration methods based on functional information have emerged, which usually ignore the importance of structural MRI information. Methods: In this study, we proposed a non-rigid cycle consistent bidirectional network with Transformer for unsupervised deformable functional MRI registration. The work achieves fMRI registration through structural MRI registration, and functional information is introduced to improve registration performance. Specifically, we employ a bidirectional registration network that implements forward and reverse registration between image pairs and apply Transformer in the registration network to establish remote spatial mapping between image voxels. Functional and structural information are integrated by introducing the local functional connectivity pattern, the local functional connectivity features of the whole brain are extracted as functional information. The proposed registration method was experimented on real fMRI datasets, and qualitative and quantitative evaluations of the quality of the registration method were implemented on the test dataset using relevant evaluation metrics. We implemented group ICA analysis in brain functional networks after registration. Functional consistency was evaluated on the resulting t-maps. Results: Compared with non-learning-based methods (Affine, Syn) and learning-based methods (Transmorph-tiny, Cyclemorph, VoxelMorph x2), our method improves the peak t-value of t-maps on DMN, VN, CEN, and SMN to 18.7, 16.5, 16.6, and 17.3 and the mean number of suprathreshold voxels (p < 0.05, t > 5.01) on the four networks to 2596.25, and there is an average improvement in peak t-value of 23.79%, 12.74%, 12.27%, 7.32%, and 5.43%. Conclusions: The experimental results show that the registration method of this study improves the structural and functional consistency between fMRI with superior registration performance. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
36. A vessel bifurcation liver CT landmark pair dataset for evaluating deformable image registration algorithms.
- Author
-
Zhang, Zhendong, Criscuolo, Edward Robert, Hao, Yao, McKeown, Trevor, and Yang, Deshan
- Subjects
- *
IMAGE processing , *INSTITUTIONAL review boards , *COMPUTED tomography , *IMAGE registration , *RESEARCH personnel , *LIVER - Abstract
Purpose: Evaluating deformable image registration (DIR) algorithms is vital for enhancing algorithm performance and gaining clinical acceptance. However, there is a notable lack of dependable DIR benchmark datasets for assessing DIR performance except for lung images. To address this gap, we aim to introduce our comprehensive liver computed tomography (CT) DIR landmark dataset library. This dataset is designed for efficient and quantitative evaluation of various DIR methods for liver CTs, paving the way for more accurate and reliable image registration techniques. Acquisition and validation methods: Forty CT liver image pairs were acquired from several publicly available image archives and authors' institutions under institutional review board (IRB) approval. The images were processed with a semi‐automatic procedure to generate landmark pairs: (1) for each case, liver vessels were automatically segmented on one image; (2) landmarks were automatically detected at vessel bifurcations; (3) corresponding landmarks in the second image were placed using two deformable image registration methods to avoid algorithm‐specific biases; (4) a comprehensive validation process based on quantitative evaluation and manual assessment was applied to reject outliers and ensure the landmarks' positional accuracy. This workflow resulted in an average of ∼56 landmark pairs per image pair, comprising a total of 2220 landmarks for 40 cases. The general landmarking accuracy of this procedure was evaluated using digital phantoms and manual landmark placement. The landmark pair target registration errors (TRE) on digital phantoms were 0.37 ± 0.26 and 0.55 ± 0.34 mm respectively for the two selected DIR algorithms used in our workflow, with 97% of landmark pairs having TREs below 1.5 mm. The distances from the calculated landmarks to the averaged manual placement were 1.27 ± 0.79 mm. Data format and usage notes: All data, including image files and landmark information, are publicly available at Zenodo (https://zenodo.org/records/13738577). Instructions for using our data can be found on our GitHub page at https://github.com/deshanyang/Liver‐DIR‐QA. Potential applications: The landmark dataset generated in this work is the first collection of large‐scale liver CT DIR landmarks prepared on real patient images. This dataset can provide researchers with a dense set of ground truth benchmarks for the quantitative evaluation of DIR algorithms within the liver. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
37. Super‐resolution reconstruction of time‐resolved four‐dimensional computed tomography (TR‐4DCT) with multiple breathing cycles based on TR‐4DMRI.
- Author
-
Liu, Yilin, Nie, Xingyu, Ahmad, Asala, Rimner, Andreas, and Li, Guang
- Subjects
- *
MAGNETIC resonance imaging , *VECTOR fields , *IMAGE registration , *IMAGE reconstruction , *MEDICAL dosimetry , *IMAGE reconstruction algorithms - Abstract
Background: Respiratory motion irregularities in lung cancer patients are common and can be severe during multi‐fractional (∼20 mins/fraction) radiotherapy. However, the current clinical standard of motion management is to use a single‐breath respiratory‐correlated four‐dimension computed tomography (RC‐4DCT or 4DCT) to estimate tumor motion to delineate the internal tumor volume (ITV), covering the trajectory of tumor motion, as a treatment target. Purpose: To develop a novel multi‐breath time‐resolved (TR) 4DCT using the super‐resolution reconstruction framework with TR 4D magnetic resonance imaging (TR‐4DMRI) as guidance for patient‐specific breathing irregularity assessment, overcoming the shortcomings of RC‐4DCT, including binning artifacts and single‐breath limitations. Methods: Six lung cancer patients participated in the IRB‐approved protocol study to receive multiple T1w MRI scans, besides an RC‐4DCT scan on the simulation day, including 80 low‐resolution (lowR: 5 × 5 × 5 mm3) free‐breathing (FB) 3D cine MRFB images in 40 s (2 Hz) and a high‐resolution (highR: 2 × 2 × 2 mm3) 3D breath‐hold (BH) MRBH image for each patient. A CT (1 × 1 × 3 mm3) image was selected from 10‐bin RC‐4DCT with minimal binning artifacts and a close diaphragm match (<1 cm) to the MRBH image. A mutual‐information‐based Freeform deformable image registration (DIR) was used to register the CT and MRBH via the opposite directions (namely F1: CTSource→MRTargetBH${\mathrm{C}}{{{\mathrm{T}}}_{{\mathrm{Source}}}} \to {\mathrm{MR}}_{{\mathrm{Target}}}^{{\mathrm{BH}}}$ and F2: CTTarget←MRSourceBH${\mathrm{C}}{{{\mathrm{T}}}_{{\mathrm{Target}}}} \leftarrow {\mathrm{MR}}_{{\mathrm{Source}}}^{{\mathrm{BH}}}$) to establish CT‐MR voxel correspondences. An intensity‐based enhanced Demons DIR was then applied for MRSourceBH→MRTargetFB${\mathrm{MR}}_{{\mathrm{Source}}}^{{\mathrm{BH}}} \to {\mathrm{MR}}_{{\mathrm{Target}}}^{{\mathrm{FB}}}$, in which the original MRBH was used in D1: CTSource→(MRSourceBH→MRTargetFB)Target${\mathrm{C}}{{{\mathrm{T}}}_{{\mathrm{Source}}}} \to {{({\mathrm{MR}}_{{\mathrm{Source}}}^{{\mathrm{BH}}} \to {\mathrm{MR}}_{{\mathrm{Target}}}^{{\mathrm{FB}}})}_{{\mathrm{Target}}}}$, while the deformed MRBH was used in D2:(CTTarget←MRSourceBH)Source→MRTargetFB${{(\text{C}{{\text{T}}_{\text{Target}}}\leftarrow \text{MR}_{\text{Source}}^{\text{BH}})}_{\text{Source}}}\to \text{MR}_{\text{Target}}^{\text{FB}}$. The deformation vector fields (DVFs) obtained from each DIR were composed to apply to the deformed CT (D1) and original CT (D2) to reconstruct TR‐4DCT images. A digital 4D‐XCAT phantom at the end of inhalation (EOI) and end of exhalation (EOE) with 2.5 cm diaphragmatic motion and three spherical targets (ϕ = 2, 3, 4 cm) were first tested to reconstruct TR‐4DCT. For each of the six patients, TR‐4DCT images at the EOI, middle (MID), and EOE were reconstructed with both D1 and D2 approaches. TR‐4DCT image quality was evaluated with mean distance‐to‐agreement (MDA) at the diaphragm compared with MRFB, tumor volume ratio (TVR) referenced to MRBH, and tumor shape difference (DICE index) compared with the selected input CT. Additionally, differences in the tumor center of mass (|∆COMD1–D2|), together with TVR and DICE comparison, was assessed in the D1 and D2 reconstructed TR‐4DCT images. Results: In the phantom, TR‐4DCT quality is assessed by MDA = 2.0 ± 0.8 mm at the diaphragm, TVR = 0.8 ± 0.0 for all tumors, and DICE = 0.83 ± 0.01, 0.85 ± 0.02, 0.88 ± 0.01 for ϕ = 2, 3, 4 cm tumors, respectively. In six patients, the MDA in diaphragm match is –1.6 ± 3.1 mm (D1) and 1.0 ± 3.9 mm (D2) between the reconstructed TR‐4DCT and lowR MRFB among 18 images (3 phases/patient). The tumor similarity is TVR = 1.2 ± 0.2 and DICE = 0.70 ± 0.07 for D1 and TVR = 1.4 ± 0.3 (D2) and DICE = 0.73 ± 0.07 for D2. The tumor position difference is |∆COMD1–D2| = 1.2 ± 0.8 mm between D1 and D2 reconstructions. Conclusion: The feasibility of super‐resolution reconstruction of multi‐breathing‐cycle TR‐4DCT is demonstrated and image quality at the diaphragm and tumor is assessed in both the 4D‐XCAT phantom and six lung cancer patients. The similarity of D1 and D2 reconstruction suggests consistent and reliable DIR results. Clinically, TR‐4DCT has the potential for breathing irregularity assessment and dosimetry evaluation in radiotherapy. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
38. Research on identification and extraction of crop plants in plateau mountainous areas based on multi-dimensional features.
- Author
-
Yin, Linjiang, Zhou, Zhongfa, Zhao, Weiquan, Liao, Yanmei, Huang, Denghong, and Li, Wei
- Subjects
- *
STANDARD deviations , *PLANT identification , *POINT cloud , *IMAGE registration , *CROPS - Abstract
To address poor crop extraction results in mountainous regions using single-feature data in previous research, this study employed a quadcopter to capture aerial orthophoto imagery and image-matching point cloud data from a pitaya cultivation site in the rugged mountainous terrain of southwestern China. The authors identified three critical features: the visible-band difference vegetation index (VDVI), excess green – excess red (ExG-ExR), and canopy height model (CHM) and then integrated them to build a multi-dimensional feature dataset, namely VDVI+CHM and ExG-ExR+CHM. Through a rule-based object-oriented technique, they conducted identification extraction specifically for pitayas plants. The study yielded impressive extraction accuracies, with VDVI, ExG-ExR, CHM segmentation, VDVI+CHM, and ExG-ExR+CHM achieving overall accuracies of 92.34%, 91.05%, 89.08%, 97.56%, and 96.86%, respectively. Furthermore, to validate the accuracy of the extraction results, a regression analysis was conducted to compare the actual canopy area of the pitayas plants determined through human-computer interaction with the extraction results. The root mean square error (RMSE) for VDVI+CHM and ExG-ExR+CHM were found to be 18 dm2 and 25 dm2, respectively, while the coefficient of determination (R2) was 0.81 and 0.67, respectively. Notably, the comparative analysis revealed that VDVI + CHM, which fused multi-dimensional features, exhibited the highest recognition accuracy, demonstrating that integrating multi-dimensional plant features effectively enhanced the accuracy of pitaya plant identification and extraction. By overcoming the limitations of single spectral or spatial structural features, this approach provides valuable insights into the identification and extraction of characteristic economic crops in mountainous regions. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
39. TROG: a fast and robust scene-matching algorithm for geo-referenced images.
- Author
-
Yang, Hongrui, Zhu, Qiju, Mei, Chunbo, Yang, Pengxiang, Gu, Hao, and Fan, Zhenhui
- Subjects
- *
FAST Fourier transforms , *DRONE aircraft , *INERTIAL navigation systems , *REMOTE-sensing images , *IMAGE registration - Abstract
In a GNSS-denied/challenged environment, the scene-matching navigation system (SMNS) is a vital autonomous technology for unmanned aerial vehicles (UAV). This paper proposes a novel template-matching framework for multimodal images since UAV navigation requires precision and real-time performance while utilizing onboard computers with low computational power. Specifically, first, the local descriptor is extracted to form a pixel-wise feature representation of an image. Then, the Fast Fourier Transform is applied to measure the similarity based on the feature representation. In the feature extraction part, a gradient-like pixel-level feature descriptor is designed, which is reconstructed by weighting it according to the gradient-like angles, named the three-dimensional reconstruction oriented gradient-like (TROG) descriptor. An optimized similarity measurement template is introduced in the matching part, which improves the traditional feature-based similarity measurement algorithm defined using Fast Fourier Transform (FFT) in the frequency domain. This strategy eliminates redundant computations during the matching process. To verify the effectiveness of the proposed algorithm, satellite imagery data from Google Earth are used as a reference images, and sensed images (including optical, IR, SAR, and Hyperspectral) are captured by UAV and satellites for image matching to testify to the registration accuracy, robustness, and computational efficiency. The experiment demonstrates that TROG is accurate, robust, and attains high real-time performance, making it applicable to UAV navigation and positioning. Additionally, field-flight experiments evaluate scene-matching navigation under satellite-denied conditions and low computational power conditions for UAVs, demonstrating that our scene-matching navigation system can achieve precise positioning with a positioning error of less than 1.637 m, which is comparable to satellite/inertial navigation systems. The experimental results from outdoor flight experiments highlight the value of our proposed algorithm in engineering applications under satellite denial conditions. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
40. SAR image matching using an improved SIFT-based anisotropic diffusion algorithm.
- Author
-
Gupta, Pratham, Modi, Preeti, Paul, Sourabh, and Gupta, Saurav
- Subjects
- *
SYNTHETIC aperture radar , *IMAGE registration , *GABOR filters , *ALGORITHMS , *SPECKLE interference - Abstract
In this paper, we propose a new image matching algorithm for the synthetic aperture radar (SAR) images with significant local as well global geometric differences. The noise handling capability of descriptor and an appropriate feature-matching technique are the crucial factors in SAR image matching as these images are highly influenced by speckle noise. To address these issues, an effective SAR image matching scheme is proposed using an improved scale-invariant feature transform (SIFT)-based anisotropic diffusion. This algorithm constructs SIFT scale layers based on anisotropic diffusion which removes the influence of speckle noise. Then, a local feature-matching algorithm is proposed to take care of the local deformations between SAR images. Experiments on multiple sets of SAR images indicate that the proposed method is competent to provide better matching performance. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
41. MGCNet: Multi-granularity consensus network for remote sensing image correspondence pruning.
- Author
-
Zhuang, Fengyuan, Liu, Yizhang, Li, Xiaojie, Zhou, Ji, Chen, Riqing, Wei, Lifang, Yang, Changcai, and Ma, Jiayi
- Subjects
- *
REMOTE sensing , *IMAGE registration , *SOURCE code , *COMMUNITY organization , *NEIGHBORHOODS , *POSE estimation (Computer vision) - Abstract
Correspondence pruning aims to remove false correspondences (outliers) from an initial putative correspondence set. This process holds significant importance and serves as a fundamental step in various applications within the fields of remote sensing and photogrammetry. The presence of noise, illumination changes, and small overlaps in remote sensing images frequently result in a substantial number of outliers within the initial set, thereby rendering the correspondence pruning notably challenging. Although the spatial consensus of correspondences has been widely used to determine the correctness of each correspondence, achieving uniform consensus can be challenging due to the uneven distribution of correspondences. Existing works have mainly focused on either local or global consensus, with a very small perspective or large perspective, respectively. They often ignore the moderate perspective between local and global consensus, called group consensus, which serves as a buffering organization from local to global consensus, hence leading to insufficient correspondence consensus aggregation. To address this issue, we propose a multi-granularity consensus network (MGCNet) to achieve consensus across regions of different scales, which leverages local, group, and global consensus to accomplish robust and accurate correspondence pruning. Specifically, we introduce a GroupGCN module that randomly divides the initial correspondences into several groups and then focuses on group consensus and acts as a buffer organization from local to global consensus. Additionally, we propose a Multi-level Local Feature Aggregation Module that adapts to the size of the local neighborhood to capture local consensus and a Multi-order Global Feature Module to enhance the richness of the global consensus. Experimental results demonstrate that MGCNet outperforms state-of-the-art methods on various tasks, highlighting the superiority and great generalization of our method. In particular, we achieve 3.95% and 8.5% mAP 5 ° improvement without RANSAC on the YFCC100M dataset in known and unknown scenes for pose estimation, compared to the second-best models (MSA-LFC and CLNet). Source code: https://github.com/1211193023/MGCNet. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
42. A Secure Authentication Indexed Choice-Based Graphical Password Scheme for Web Applications and ATMs.
- Author
-
Zarif, Sameh, Moawad, Hadier, Amin, Khalid, Alharbi, Abdullah, Elkilani, Wail S., Tang, Shouze, and Wagdy, Marian
- Subjects
INDEX numbers (Economics) ,WEB-based user interfaces ,ELECTRONIC equipment ,CLOUD computing ,RANDOM numbers ,IMAGE registration ,BIOMETRIC identification ,COMPUTER passwords - Abstract
Authentication is the most crucial aspect of security and a predominant measure employed in cybersecurity. Cloud computing provides a shared electronic device resource for users via the internet, and the authentication techniques used must protect data from attacks. Previous approaches failed to resolve the challenge of making passwords secure, memorable, usable, and time-saving. Graphical Password (GP) is still not widely utilized in reality because consumers suffer from multiple login stages. This paper proposes an Indexed Choice-Based Graphical Password (ICGP) scheme for improving the authentication part. ICGP consists of two stages: registration and authentication. At the registration stage, the user registers his/her data user name a number called Index Number (IN), and chooses an image from a grid of images. After completing the registration, ICGP gives the user a random unique number (UNo) to be a user ID. At the authentication stage, the user chooses a different image from the grid based on the random appearance of the registered image dimensions on the grid plus the registered Index Number. ICGP password is a combination of three factors; user's name, UNo, and any image. According to the experiments, the proposed ICGP has achieved great improvements when compared to prior methods. The ICGP has increased the possible password numbers from 9.77e + 6 to 3.74e + 30, the password space from 1.20e + 34 to 1.37e + 84, and decreased the password entropy from 7.16e − 7 to 8.26e − 30. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
43. Toward Complex-query Referring Image Segmentation: A Novel Benchmark.
- Author
-
Ji, Wei, Li, Li, Fei, Hao, Liu, Xiangyan, Yang, Xun, Li, Juncheng, and Zimmermann, Roger
- Subjects
IMAGE registration ,IMAGE segmentation ,ALGORITHMS ,SCRIPTS ,GENOMES - Abstract
Referring Image Segmentation (RIS) has been extensively studied over the past decade, leading to the development of advanced algorithms. However, there has been a lack of research investigating how existing algorithms should be benchmarked with complex language queries, which include more informative descriptions of surrounding objects and backgrounds (e.g., the black car vs. the black car is parking on the road and beside the bus). Given the significant improvement in the semantic understanding capability of large pre-trained models, it is crucial to take a step further in RIS by incorporating complex language that resembles real-world applications. To close this gap, building upon the existing RefCOCO and Visual Genome datasets, we propose a new RIS benchmark with complex queries, namely RIS-CQ. The RIS-CQ dataset is of high quality and large scale, which challenges the existing RIS with enriched, specific, and informative queries, and enables a more realistic scenario of RIS research. Besides, we present a niche targeting method to better task the RIS-CQ, called Dual-Modality Graph Alignment (DuMoGa) model, which outperforms a series of RIS methods. To provide a valuable foundation for future advancements in the field of RIS with complex queries, we release the datasets, pre-processing and synthetic scripts, and the algorithm implementations at https://github.com/lili0415/DuMoGa. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
44. Towards automated remote sizing and hot steel manufacturing with image registration and fusion.
- Author
-
Lin, Yueda, Wang, Peng, Wang, Zichen, Ali, Sardar, and Mihaylova, Lyudmila
- Subjects
IMAGE fusion ,COMPUTER vision ,STEEL manufacture ,CAMERA calibration ,ARTIFICIAL intelligence ,IMAGE registration - Abstract
Image registration and fusion are challenging tasks needed in manufacturing, including in high-quality steel production for inspection, monitoring and safe operations. To solve some of these challenging tasks, this paper proposes computer vision approaches aiming at monitoring the direction of motion of hot steel sections and remotely measuring their dimensions in real time. Automated recognition of the steel section direction is performed first. Next, a new image registration approach is developed based on extrinsic features, and it is combined with frequency domain image fusion ofoptical images. The fused image provides information about the size of high-quality hot steel sections remotely. While the remote sizing approach keeps operators informed of the section dimensions in real time, the mill stands can be configured to provide quality assurance. The performance of the developed approaches is evaluated over real data and achieves accuracy above 95%. The proposed approaches have the potential to introduce an enhanced level of autonomy in manufacturing and provide advanced digitised solutions in steel manufacturing plants. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
45. Registration algorithm for printed images incorporating feature registration and deformation optimization: Registration algorithm for printed images...: Y. Chen et al.
- Author
-
Chen, Yan, Zhang, Libin, Zhan, Hongwu, and Xu, Fang
- Abstract
The registration of printed images and the original image before printing is the key step of high precision quality detection of printed image. In the printing process and the process of collecting printed images, rigid deformation, elastic deformation and brightness difference between the original image and the printed image are inevitably caused to the printed image. In order to improve the registration accuracy of printed images and deal with various deformations and color differences that may occur during the printing process, this paper proposes an innovative algorithm that combines feature registration and deformation optimization. The algorithm first uses the SIFT feature extraction algorithm to achieve global registration, and then combines the Active Demons deformation estimation algorithm to optimize the local deformation to correct the rigid and elastic deformation of the printed image. However, the deformation estimation algorithm is limited by the premise of the same brightness. Therefore, this paper performs superpixel segmentation on the original image before printing, and then introduces a nonlinear brightness compensation mechanism, thus overcoming the brightness constraint of the deformation estimation algorithm. In order to improve the registration efficiency, a reduction factor is adaptively introduced in the global registration stage, and the local deformation optimization registration stage cancels the iteration by designing the value of the normalization factor. The experimental results show that compared with SIFT, Active Demons and SIFT-ActiveDemons algorithms, the innovative fusion registration algorithm in this paper has the highest registration accuracy and can effectively correct the elastic deformation of printed images. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
46. Virtual MOLLI Target: Generative Adversarial Networks Toward Improved Motion Correction in MRI Myocardial T1 Mapping.
- Author
-
Pan, Nai‐Yu, Huang, Teng‐Yi, Yu, Jui‐Jung, Peng, Hsu‐Hsia, Chuang, Tzu‐Chao, Lin, Yi‐Ru, Chung, Hsiao‐Wen, and Wu, Ming‐Ting
- Subjects
GENERATIVE adversarial networks ,IMAGE registration ,BONFERRONI correction ,MULTIPLE comparisons (Statistics) ,CARDIAC imaging - Abstract
Background: The modified Look‐Locker inversion recovery (MOLLI) sequence is commonly used for myocardial T1 mapping. However, it acquires images with different inversion times, which causes difficulty in motion correction for respiratory‐induced misregistration to a given target image. Hypothesis: Using a generative adversarial network (GAN) to produce virtual MOLLI images with consistent heart positions can reduce respiratory‐induced misregistration of MOLLI datasets. Study Type: Retrospective. Population: 1071 MOLLI datasets from 392 human participants. Field Strength/Sequence: Modified Look‐Locker inversion recovery sequence at 3 T. Assessment: A GAN model with a single inversion time image as input was trained to generate virtual MOLLI target (VMT) images at different inversion times which were subsequently used in an image registration algorithm. Four VMT models were investigated and the best performing model compared with the standard vendor‐provided motion correction (MOCO) technique. Statistical Tests: The effectiveness of the motion correction technique was assessed using the fitting quality index (FQI), mutual information (MI), and Dice coefficients of motion‐corrected images, plus subjective quality evaluation of T1 maps by three independent readers using Likert score. Wilcoxon signed‐rank test with Bonferroni correction for multiple comparison. Significance levels were defined as P < 0.01 for highly significant differences and P < 0.05 for significant differences. Results: The best performing VMT model with iterative registration demonstrated significantly better performance (FQI 0.88 ± 0.03, MI 1.78 ± 0.20, Dice 0.84 ± 0.23, quality score 2.26 ± 0.95) compared to other approaches, including the vendor‐provided MOCO method (FQI 0.86 ± 0.04, MI 1.69 ± 0.25, Dice 0.80 ± 0.27, quality score 2.16 ± 1.01). Data Conclusion: Our GAN model generating VMT images improved motion correction, which may assist reliable T1 mapping in the presence of respiratory motion. Its robust performance, even with considerable respiratory‐induced heart displacements, may be beneficial for patients with difficulties in breath‐holding. Level of Evidence: 3 Technical Efficacy: Stage 1 [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
47. Comparison of feature-based algorithms for large-scale satellite image matching.
- Author
-
Naserizadeh, Fatemeh and Jafari, Ali
- Subjects
ALGORITHMS ,FEATURE extraction ,REMOTE-sensing images ,IMAGE registration ,IMAGE recognition (Computer vision) - Abstract
Using different algorithms to extract, describe, and match features requires knowing their capabilities and weaknesses in various applications. Therefore, it is a basic need to evaluate algorithms and understand their performance and characteristics in various applications. In this article, classical local feature extraction and description algorithms for large-scale satellite image matching are discussed. Eight algorithms, SIFT, SURF, MINEIGEN, MSER, HARRIS, FAST, BRISK, and KAZE, have been implemented, and the results of their evaluation and comparison have been presented on two types of satellite images. In previous studies, comparisons have been made between local feature algorithms for satellite image matching. However, the difference between the comparison of algorithms in this article and the previous comparisons is in the type of images used, which both reference and query images are large-scale, and the query image covers a small part of the reference image. The experiments were conducted in three criteria: time, repeatability, and accuracy. The results showed that the fastest algorithm was Surf, and in terms of repeatability and accuracy, Surf and Kaze got the first rank, respectively. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
48. A feature‐based pavement image registration method for precise pavement deterioration monitoring.
- Author
-
Yang, Zhongyu, Mohammadi, Mohsen, Wang, Haolin, and Tsai, Yi‐Chang (James)
- Subjects
- *
IMAGE registration , *TRANSPORTATION departments , *IMAGING systems , *TRANSPORTATION agencies , *PAVEMENTS - Abstract
Over the past decade, pavement imaging systems, particularly 3D laser technology, have been widely adopted by transportation agencies for network‐level pavement condition evaluations. State Highway Agencies, including Georgia Department of Transportation (DOT), Florida DOT, and Texas DOT, have been collecting pavement images for over 5 years. However, these multi‐year pavement images have not been fully utilized for analyzing detailed pavement deterioration. One challenge is the accurate and efficient registration of multi‐temporal pavement images. This study pioneers the use of feature‐based methods to address this challenge. It evaluates various feature‐based image registration methods, including both state‐of‐the‐art and novel combinations of feature detectors and descriptors. These methods are rigorously assessed using hybrid “step‐by‐step” and “end‐to‐end” performance evaluation metrics, with a ground reference dataset containing 100 pavement image pairs featuring diverse crack types and varying year gaps. The results confirm the feasibility of using feature‐based techniques to register multi‐temporal pavement images. A novel combination of the AKAZE detector and the Binary Robust Independent Elementary Features (BRIEF) descriptor was identified as the best‐performing method, successfully registering 96 out of 100 image pairs. This advancement enables pavement engineers to accurately monitor pavement deterioration using multi‐temporal images. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
49. DeBo: Contrast enhancement for image registration using binary differential evolution and bat optimization.
- Author
-
Akram, Muhammad Adeel, Akram, Tallha, Javed, Umer, Rafiq, Muhammad, Naz, Mehvish, and He, Di
- Subjects
- *
DIFFERENTIAL evolution , *FEATURE extraction , *IMAGE intensifiers , *BATS , *RECORDING & registration , *IMAGE registration - Abstract
Image registration has demonstrated its significance as an essential tool for target recognition, classification, tracking, and damage assessment during natural catastrophes. The image registration process relies on the identification of numerous reliable features; thus, low resolutions, poor lighting conditions, and low image contrast substantially diminish the number of dependable features available for registration. Contrast stretching enhances image quality, facilitating the object detection process. In this study, we proposed a hybrid binary differential evolution and BAT optimization model to enhance contrast stretching by optimizing a decision variables in the transformation function. To validate its efficiency, the proposed approach is utilized as a preprocessor before feature extraction in image registration. Cross-comparison of detected features of enhanced images verses the original images during image registration validate the improvements in the image registration process. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
50. Correction of systematic image misalignment in direct georeferencing of UAV multispectral imagery.
- Author
-
Pak, Hui Ying, Lin, Weisi, and Law, Adrian Wing-Keung
- Subjects
- *
IMAGE registration , *DRONE aircraft , *BODIES of water , *ALTITUDES , *EXPERTISE - Abstract
Mosaicking of Unmanned Aerial Vehicles (UAV) imagery over featureless water bodies has been known to be challenging, and poses a significant impediment to water monitoring applications. Techniques such as Structure-from-motion typically fail under such conditions due to the lack of distinctive features in the scene, and direct georeferencing is currently the only practical solution, albeit lower georeferencing accuracy is expected. However, hardware issues, particularly the typical time delay between the GPS unit and the image capture, can lead to systematic image misalignment and further reducing the accuracy. The systematic image misalignment arises as the recording of the geographical coordinates by the GPS unit may not precisely correspond to the exact moment of image exposure, and the image exposure may not always occur at the mid-exposure time. Hardware solutions can mitigate this issue but require technical expertise and resources. Alternatively, software solutions can address the problem without necessitating any hardware modifications. This study introduces an open-source solution for the correction of the systematic image alignment by accounting for the time delay and distance discrepancy between the measurements of the GPS coordinates and the image capture. The method was validated with field UAV surveys conducted in this study under various flight configurations (different flight altitudes and overlap ratios), and effective image alignment was obtained using the proposed open-source solution which reduced the georeferencing error by around 67.7%. Specifically, a georeferencing error of RMSE = 1.409 m and $\sigma $σ = 0.6356 m was achieved without the use of any ground control points (GCPs). Finally, as demonstrated in this study, low flight altitudes (e.g. 15 m) should be discouraged for such conditions as georeferencing errors could amplify due to the limited accuracy of the GPS, resulting in visual artefacts. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.