Speeded Up Robust Features Research Articles

Implementation of Augmented Reality at Interactive Food Menu Using the Speed Up Robust Features (SURF) Algorithm

— Promotion is an attempt to notify or offer a product or service with the aim of attracting potential customers to buy or consume it, with the promotion, producers or distributors expect an increase in sales figures. In this study researchers used Augmented Reality technology for interactive media promotion of food menus by adding 3D multimedia elements. The method used in this study uses the Natural Feature Tracking method with the Speed Up Robust Features (SURF) algorithm, which detects local features in marker images that are resistant to rotation, scale and blurring. The results showed that the keypoint functions to render 3D objects. Search for keypoints is interrupted due to distance, light intensity and slope of the marker. Test results to see the distance between the camera and the marker as far as 60 cm. Medium light intensity that can detect markers, the average time of object speed can be displayed is 3.026 seconds and the marker slope limit is 30 °. This is because the keypoint readings at the position and time limit from keypoint readings clearly, keypoint readings clearly produce 3D objects can be displayed. This research uses the Android platform as the foundation of this Augmented Reality technology application. So that by displaying 3D food menu items in restaurants it is expected to be a means of promotion to attract consumers.

Image Copy-Move Forgery Detection Based on Fused Features and Density Clustering

Image copy-move forgery is a common simple tampering technique. To address issues such as high time complexity in most copy-move forgery detection algorithms and difficulty detecting forgeries in smooth regions, this paper proposes an image copy-move forgery detection algorithm based on fused features and density clustering. Firstly, the algorithm combines two detection methods, speeded up robust features (SURF) and accelerated KAZE (A-KAZE), to extract descriptive features by setting a low contrast threshold. Then, the density-based spatial clustering of applications with noise (DBSCAN) algorithm removes mismatched pairs and reduces false positives. To improve the accuracy of forgery localization, the algorithm uses the original image and the image transformed by the affine matrix to compare similarities in the same position in order to locate the forged region. The proposed method was tested on two datasets (Ardizzone and CoMoFoD). The experimental results show that the method effectively improved the accuracy of forgery detection in smooth regions, reduced computational complexity, and exhibited strong robustness against post-processing operations such as rotation, scaling, and noise addition.

An improved crow search optimization with Bi-LSTM model for identification and classification of COVID-19 infection from chest X-Ray images

Deep learning has become an effective detection method as coronavirus disease 2019 (COVID-19) incidences are increasing quickly. Nevertheless, finding the best accurate models for describing COVID-19 patients is difficult since comparing the outcomes of different data kinds and collecting procedures is difficult. X-ray scans from patients with verified COVID-19 illnessand healthy people were combined to produce a dataset. The dataset's noisy, duplicated, and inappropriate characteristics harm the effectiveness of classification algorithms utilizedin deep learning. As a result, the data should be pre-processed, and essential parts should be chosen to minimize the dimension of datasets by choosing the most crucial qualities while improving classification accuracy. Speed Up-Robust Feature (SURF) method is applied for the feature extraction from the dataset. The required features are selected after feature extraction based on Crow Search Optimization (CSO). The Bi-LSTM mechanism completes the classification procedure at the final stage. Quality metrics like accuracy, recall,precision, and F1-score are contrasted with some other cutting-edge classifiers. The findings demonstrate the effectiveness of the suggested paradigm for COVID-19 identification and classification, demonstrating high specificity, high sensitivity, and low computing complexity.

Condition Monitoring and Analysis Method of Smart Substation Equipment Based on Deep Learning in Power Internet of Things

An accurate perception of the state of smart substation equipment is a strong guarantee for the reliable operation of the large power grid. This article proposes using deep learning for the device condition monitoring and analysis method in a power internet of things cloud edge collaboration mode. The speeded up robust features (SURF) feature detector is used at the edge of the network to accurately collect the interest points from the image data set, providing a reliable and complete sample data set support for the cloud-based deep learning network. Adding the attention mechanism module to the cloud improves the Yolov5 network model, enhance feature extraction, and increase the monitoring and analysis capabilities of the equipment. The simulation results show that the proposed method has achieved a recall rate of 91.21% and an accuracy rate of 90.54% for insulator fault evaluation indicators.

Classification of COVID-19 Chest X-Ray Images Based on Speeded Up Robust Features and Clustering-Based Support Vector Machines

Abstract Due to the worldwide deficiency of medical test kits and the significant time required by radiology experts to identify the new COVID-19, it is essential to develop fast, robust, and intelligent chest X-ray (CXR) image classification system. The proposed method consists of two major components: feature extraction and classification. The Bag of image features algorithm creates visual vocabulary from two training data categories of chest X-ray images: Normal and COVID-19 patients’ datasets. The algorithm extracts salient features and descriptors from CXR images using the Speeded Up Robust Features (SURF) algorithm. Machine learning with the Clustering-Based Support Vector Machines (CB-SVMs) multiclass classifier is trained using SURF features to classify the CXR image categories. The careful collection of ground truth Normal and COVID-19 CXR datasets, provided by worldwide expert radiologists, has certainly influenced the performance of the proposed CB-SVMs classifier to preserve the generalization capabilities. The high classification accuracy of 99 % demonstrates the effectiveness of the proposed method, where the accuracy is assessed on an independent test sets.

A Recognition Method of Ceramic Microcosmic Images Based on SURF and Blockchain

<p>Ceramics have gradually occupied a more significant proportion in the art market and daily life in recent years. Therefore, the identification and anti-counterfeiting of ceramics have become more important with the continuous improvement of counterfeit ceramics. However, it is difficult for traditional ceramic identification and anti-counterfeiting technology to make instant, accurate and efficient identifications. Hence, based on the speed-ed up robust feature (SURF) algorithm, this paper proposes to take the microscopic surface features of ceramic images as the unique identifier for ceramic. In addition, blockchain was combined with distributed storage to ensure the security and reliability of these micro-characteristic data. At any time, ceramic images to be identified can be compared and verified with these images stored on the blockchain, and hence to determine the authenticity of the ceramics. Experimental results show that the proposed method has a high recognition rate and good robustness to problems. Compared with the traditional feature extraction methods, the efficiency and accuracy of proposed algorithm have been improved. The matching similarity rate between most imitations and genuine products using the proposed algorithm will not exceed 15%, thus accurately identifying imitations to achieve the anti-counterfeiting of ceramics.</p> <p> </p>

Research on the algorithm of image feature detection and matching

In-depth research on feature detection technology affects people's modern life. Modern artificial intelligence can act as the eyes of human beings and efficiently filter out effective information from complex pictures. Corner detection has now evolved into a tool for efficient image scanning. People's increasingly stringent requirements for image processing continue to promote the birth of new technologies. Corner detection methods have been improved and perfected, and have experienced detectors such as Harris, FAST, Scalriant Feature Transform (SIFT), Speeded Up Robust Feature (SURF), Binary Robust Invariant Scalable Keypoints (BRISK), KAZE, AKAZE and Oriented FAST and Rotated BRIEF (ORB). In the face of many mainstream detectors, the main research purpose of this paper is to rely on Python and Computer vision to study the detection efficiency of various detectors in different environments. In this experiment, thirteen groups of pictures were selected, and after being flipped, complicated, and blurred respectively, they were detected by different detectors to obtain the results. Finally, by comparing the feature detection points, detection time and other factors, this study found that the ORB detector can be competent in most situations and is currently the fastest and stable feature point detection and extraction algorithm. On the other hand, the BRISK detector can handle highly blurred images more efficiently.

Automatic Point Cloud Colorization of Ground-Based LiDAR Data Using Video Imagery without Position and Orientation System

With the continuous development of three-dimensional city modeling, traditional close-range photogrammetry is limited by complex processing procedures and incomplete 3D depth information, making it unable to meet high-precision modeling requirements. In contrast, the integration of light detection and ranging and cameras in mobile measurement systems provides a new and highly effective solution. Currently, integrated mobile measurement systems commonly require cameras, lasers, position and orientation system and inertial measurement units; thus, the hardware cost is relatively expensive, and the system integration is complex. Therefore, in this paper, we propose a ground mobile measurement system only composed of a LiDAR and a GoPro camera, providing a more convenient and reliable way to automatically obtain 3D point cloud data with spectral information. The automatic point cloud coloring based on video images mainly includes four aspects: (1) Establishing models for radial distortion and tangential distortion to correct video images. (2) Establishing a registration method based on normalized Zernike moments to obtain the exterior orientation elements. The error of the result is only 0.5–1 pixel, which is far higher than registration based on a collinearity equation. (3) Establishing relative orientation based on essential matrix decomposition and nonlinear optimization. This involves uniformly using the speeded-up robust features algorithm with distance restriction and random sample consensus to select corresponding points. The vertical parallax of the stereo image pair model is less than one pixel, indicating that the accuracy is high. (4) A point cloud coloring method based on Gaussian distribution with central region restriction is adopted. Only pixels within the central region are considered valid for coloring. Then, the point cloud is colored based on the mean of the Gaussian distribution of the color set. In the colored point cloud, the textures of the buildings are clear, and targets such as windows, grass, trees, and vehicles can be clearly distinguished. Overall, the result meets the accuracy requirements of applications such as tunnel detection, street-view modeling and 3D urban modeling.

EEDD: Edge-Guided Energy-Based PCB Defect Detection

Printed circuit board (PCB) defect detection is critical for ensuring the safety of electronic devices, especially in the space industry. Non-reference-based methods, typically the deep learning methods, suffer from a large amount of annotated data requirements and poor interpretability. In contrast, conventional reference-based methods achieve higher detection accuracy by comparing with a template image but rely on precise image alignment and face the challenge of fine defects detection. To solve the problem, we propose a novel Edge-guided Energy-based PCB Defect Detection method (EEDD). We focus on the salient edge characteristic of PCB images and regard the functional defects as contour differences and then propose a novel energy measurement method for PCB contour anomaly detection. We introduce the energy transformation using the edge information of the template and test image, then Speeded-Up Robust Features method (SURF) is used for image alignment, and finally achieve defect detection by measuring the energy anomaly score pixel by pixel with the proposed energy-based defect localization and contour flood fill methods. Our method excels in detecting multi-scale defects, particularly tiny defects, and is robust against interferences such as non-finely aligned images and edge spurs. Experiments on the DeepPCB-A dataset and our high-resolution PCB dataset (HDPCB) show that the proposed method outperforms state-of-the-art methods in PCB defect-detection tasks.

A blind watermarking approach based on hybrid Imperialistic Competitive Algorithm and SURF points for color Images’ authentication

Currently, we are in the area of the digital big data world. Every day, people share billions of images over Internet from various sources. Ensuring images’ authorship rights and illegal modification and/or reproductions become a challenge. Their protection must meet current and secure development needs of multimedia applications. In this paper, we propose an efficient watermarking scheme based on combining Imperialistic Competitive Algorithm (ICA), Speed Up Robust Features (SURF) points and Discrete Cosine Transform (DCT). The high complexity and inappropriate embedding area could lead to weak performance of watermarking schemas. To address these problems, an ideal watermarking embedding area was proposed using ICA to provide an optimized cost and complexity. The watermark was embedded into the DCT coefficients of the selected embedding areas. The watermark was extracted in a blind way to ensure color image’ authentication. Experimental findings demonstrate that the proposed approach achieves promising performance in terms of robustness and imperceptibility in almost cases. The average PSNR exceeds 61db regarding the imperceptibility. For the robustness measured by the correlation coefficients between the original watermark and the extracted is close to 1 in almost cases.

Brain tumor segmentation and classification using optimized U-Net

ABSTRACT This paper presents an optimization-driven classifier for classifying the brain tumour considering MRI. Here, the pre-operative and post-operative MRI is subjected to pre-processing, which is performed using filtering and Region of Interest (RoI) extraction techniques. The pre-processed output is fed to segmentation wherein the U-Net model is adapted for generating the segments. Then, the extraction of histogram features is done and the classification of tumours is done by U-Net, which is trained using the proposed Poor Bird Swarm Optimization algorithm (PRBSA). Here, PRBSA is the integration of the Poor and rich optimization (PRO) algorithm and Bird Swarm Algorithm (BSA). At last, the classified output is considered for pixel change detection, which is carried out using speeded-up robust features (SURF). The proposed PRBSA-based U-Net offered improved performance with the highest accuracy of 94%, highest sensitivity of 93.7%, and highest specificity of 94%.

Gender Recognition of Human from Face Images Using Multi-Class Support Vector Machine (SVM) Classifiers

In the realm of robotics and interactive systems, gender recognition is a crucial problem. Considering the several uses it has in security, web search, human-computer interactions, etc., gender recognition from facial photos has garnered a lot of attention. The need to use and enhance gender recognition techniques is felt more strongly today due to a significant development in the design of facial recognition systems. Relatively speaking to other approaches, the progress gained in this area thus far is not exceptional. Thus, a novel method has been adopted in this study to improve accuracy in comparison to earlier research. To create the best rate of accuracy and efficiency in the suggested method of this research, we choose a minimal set of characteristics. Testing on the FERET and UTK-Face datasets reveals that our suggested algorithm has a lower degree of inaccuracy. In this article, the input image of the person's face is pre-processed to extract the right features from the face once the person's face has been recognized. Gender separation is achieved using Multi-class Support Vector Machine (SVM) Classifiers after features from normalized images have been extracted using Histogram Oriented Gradient (HOG), Gabor Filters, and Speeded Up Robust Features (SURF), as well as their combination to select the most appropriate feature from them as input for gender classification. As a feature reduction feature, the Principal Component Analysis (PCA) algorithm is also employed. Using the proposed approach, 98.75% gender recognition precision has been accomplished on the FERET database and a runtime performance of 0.4 Sec. on the UTK-Face database, 97.43% gender recognition accuracy has been accomplished and a runtime performance of 0.5 Sec.

Vibration data‐driven machine learning architecture for structural health monitoring of steel frame structures

AbstractA vibration data‐based machine learning architecture is designed for structural health monitoring (SHM) of a steel plane frame structure. This architecture uses a Bag‐of‐Features algorithm that extracts the speeded‐up robust features (SURF) from the time‐frequency scalogram images of the registered vibration data. The discriminative image features are then quantised to a visual vocabulary using K‐means clustering. Finally, a support vector machine (SVM) is trained to distinguish the undamaged and multiple damage cases of the frame structure based on the discriminative features. The potential of the machine learning architecture is tested for an unseen dataset that was not used in training as well as with some datasets from entirely new damages close to existing (i.e., trained) damage classes. The results are then compared with those obtained using three other combinations of features and learning algorithms—(i) histogram of oriented gradients (HOG) feature with SVM, (ii) SURF feature with k‐nearest neighbours (KNN) and (iii) HOG feature with KNN. In order to examine the robustness of the approach, the study is further extended by considering environmental variabilities along with the localisation and quantification of damage. The experimental results show that the machine learning architecture can effectively classify the undamaged and different joint damage classes with high testing accuracy that indicates its SHM potential for such frame structures.

Machine learning-based multimodal MRI texture analysis for assessing renal function and fibrosis in diabetic nephropathy: a retrospective study.

Diabetic nephropathy (DN) has become a major public health burden in China. A more stable method is needed to reflect the different stages of renal function impairment. We aimed to determine the possible practicability of machine learning (ML)-based multimodal MRI texture analysis (mMRI-TA) for assessing renal function in DN. For this retrospective study, 70 patients (between 1 January 2013 and 1 January 2020) were included and randomly assigned to the training cohort (n1 = 49) and the testing cohort (n2 = 21). According to the estimated glomerular filtration rate (eGFR), patients were assigned into the normal renal function (normal-RF) group, the non-severe renal function impairment (non-sRI) group, and the severe renal function impairment (sRI) group. Based on the largest coronal image of T2WI, the speeded up robust features (SURF) algorithm was used for texture feature extraction. Analysis of variance (ANOVA) and relief and recursive feature elimination (RFE) were applied to select the important features and then support vector machine (SVM), logistic regression (LR), and random forest (RF) algorithms were used for the model construction. The values of area under the curve (AUC) on receiver operating characteristic (ROC) curve analysis were used to assess their performance. The robust T2WI model was selected to construct a multimodal MRI model by combining the measured BOLD (blood oxygenation level-dependent) and diffusion-weighted imaging (DWI) values. The mMRI-TA model achieved robust and excellent performance in classifying the sRI group, non-sRI group, and normal-RF group, with an AUC of 0.978 (95% confidence interval [CI]: 0.963, 0.993), 0.852 (95% CI: 0.798, 0.902), and 0.972 (95% CI: 0.995, 1.000), respectively, in the training cohort and 0.961 (95% CI: 0.853, 1.000), 0.809 (95% CI: 0.600, 0.980), and 0.850 (95% CI: 0.638, 0.988), respectively, in the testing cohort. The model built from multimodal MRI on DN outperformed other models in assessing renal function and fibrosis. Compared to the single T2WI sequence, mMRI-TA can improve the performance in assessing renal function.

Spatiotemporal Detection and Localization of Object Removal Video Forgery with Multiple Feature Extraction and Optimized Residual Network

Video forgery detection and localization is one of the most important issue due to the advanced editing software that provides strengthen to tools for manipulating the videos. Object based video tampering destroys the originality of the video. The main aim of the video forensic is to eradicate the forgeries from the original video that are useful in various applications. However, the research on detecting and localizing the object based video forgery with advanced techniques still remains the open and challenging issue. Many of the existing techniques have focused only on detecting the forged video under static background that cannot be applicable for detecting the forgery in tampered video. In addition to this, conventional techniques fail to extract the essential features in order to investigate the depth of the video forgery. Hence, this paper brings a novel technique for detecting and localizing the forged video with multiple features. The steps involved in this research are keyframe extraction, pre-processing, feature extraction and finally detection and localization of forged video. Initially, keyframe extraction uses the Gaussian mixture model (GMM) to extract frames from the forged videos. Then, the pre-processing stage is manipulated to convert the RGB frame into a grayscale image. Multi-features need to be extracted from the pre-processed frames to study the nature of the forged videos. In our proposed study, speeded up robust features (SURF), principal compound analysis histogram oriented gradients (PCA-HOG), model based fast digit feature (MBFDF), correlation of adjacent frames (CAF), the prediction residual gradient (PRG) and optical flow gradient (OFG) features are extracted. The dataset used for the proposed approach is collected from REWIND of about 40 forged and 40 authenticated videos. With the help of the DL approach, video forgery can be detected and localized. Thus, this research mainly focuses on detecting and localization of forged video based on the ResNet152V2 model hybrid with the bidirectional gated recurrent unit (Bi-GRU) to attain maximum accuracy and efficiency. The performance of this approach is finally compared with existing approaches in terms of accuracy, precision, F-measure, sensitivity, specificity, false-negative rate (FNR), false discovery rate (FDR), false-positive rate (FPR), Mathew’s correlation coefficient (MCC) and negative predictive value (NPV). The proposed approach assures the performance of 96.17% accuracy, 96% precision, 96.14% F-measure, 96.58% sensitivity, 96.5% specificity, 0.034 FNR, 0.04 FDR, 0.034 FPR, 0.92 MCC and 96% NPV, respectively. Along with is, the mean square error (MSE) and peak-to-signal-noise ratio (PSNR) for the GMM model attained about 104 and 27.95, respectively.

Binary Neighborhood Coordinate Descriptor for Circuit Board Defect Detection

Due to the periodicity of circuit boards, the registration algorithm based on keypoints is less robust in circuit board detection and is prone to misregistration problems. In this paper, the binary neighborhood coordinate descriptor (BNCD) is proposed and applied to circuit board image registration. The BNCD consists of three parts: neighborhood description, coordinate description, and brightness description. The neighborhood description contains the grayscale information of the neighborhood, which is the main part of BNCD. The coordinate description introduces the actual position of the keypoints in the image, which solves the problem of inter-period matching of keypoints. The brightness description introduces the concept of bright and dark points, which improves the distinguishability of BNCD and reduces the calculation amount of matching. Experimental results show that in circuit board image registration, the matching precision rate and recall rate of BNCD is better than that of classic algorithms such as scale-invariant feature transform (SIFT) and speeded up robust features (SURF), and the calculation of descriptors takes less time.

Clustered Redundant Keypoint Elimination SURF Method in MRI Image Registration Based on Alpha-Trimmed Relationship

Purpose: The process of Magnetic Resonance Imaging (MRI) image registration is one of the important branches in MRI image analysis, which is a necessary pre-processing to use the information in these images. The purpose of this paper is to present a new approach for MRI image registration that can maintain the total number of initial matches and have the highest precision.
 Materials and Methods: The Clustered Redundant Keypoint Elimination Method-Scale Invariant Feature Transform (CRKEM-SIFT) algorithm has recently been introduced to eliminate redundancies and upgrade the correspondence precision. The disadvantages of this algorithm include the high execution time and the number of incorrect correspondences. In this paper, to increase the accuracy and speed of MRI image registration, the CRKEM method is first used over the Speeded Up Robust Features (SURF) algorithm. Then, Spatial Relations Correspondence (SRC) and Alpha-Trimmed Spatial Relations Correspondence (ATSRC) methods are suggested to improve correspondences. These suggested methods, unlike conventional methods such as Random Sample Consensus (RANSAC(, which only eliminates incorrect correspondences, detect incorrect correspondences based on spatial relationships and turn them into correct correspondences. Converting incorrect correspondences to correct ones can increase the number of correct correspondences and ultimately increase the precision of correspondences.
 Results: The simulation results show that the suggested CRKEMSURF-ATSRC approach improves the mean by 28.92% in terms of precision and 37.58% in SITMMC compared to those of the SIFT-ARANSAC method.
 Conclusion: The suggested SRC and ATSRC methods use the spatial relations of the initial correspondences to convert the incorrect correspondences into correct ones. The number of initial correspondences is maintained in these suggested approaches. These methods are better than other methods of improving correspondences such as RANSAC, and Graph Transformation Matching (GTM). These suggested methods can be used as a new and efficient approach to improve the correspondence of medical images.

Gesture-to-Text Translation Using SURF for Indian Sign Language

This research paper focuses on developing an effective gesture-to-text translation system using state-of-the-art computer vision techniques. The existing research on sign language translation has yet to utilize skin masking, edge detection, and feature extraction techniques to their full potential. Therefore, this study employs the speeded-up robust features (SURF) model for feature extraction, which is resistant to variations such as rotation, perspective scaling, and occlusion. The proposed system utilizes a bag of visual words (BoVW) model for gesture-to-text conversion. The study uses a dataset of 42,000 photographs consisting of alphabets (A–Z) and numbers (1–9), divided into 35 classes with 1200 shots per class. The pre-processing phase includes skin masking, where the RGB color space is converted to the HSV color space, and Canny edge detection is used for sharp edge detection. The SURF elements are grouped and converted to a visual language using the K-means mini-batch clustering technique. The proposed system’s performance is evaluated using several machine learning algorithms such as naïve Bayes, logistic regression, K nearest neighbors, support vector machine, and convolutional neural network. All the algorithms benefited from SURF, and the system’s accuracy is promising, ranging from 79% to 92%. This research study not only presents the development of an effective gesture-to-text translation system but also highlights the importance of using skin masking, edge detection, and feature extraction techniques to their full potential in sign language translation. The proposed system aims to bridge the communication gap between individuals who cannot speak and those who cannot understand Indian Sign Language (ISL).

Identifying License Plates in Distorted Vehicle Images: Detecting Distorted Vehicle Licence Plates Using a Novel Preprocessing Methods With Hybrid Feature Descriptors

Intelligent transportation systems (ITSs) play a key role in many people’s lives with different aspects. Most of the ITS applications include a system for detecting license plates (LPs) in transportation vehicles. A new framework for such detection systems is introduced in this article. It includes a novel technique for preprocessing, extraction, and detection stages to identify LPs from distorted vehicle images. An efficient preprocessing method is developed in this study. An enhanced, contrast-limited adaptive histogram equalization method for filtering the unwanted LP features is proposed. At the features-extraction stage, strong hybrid features from extended local binary patterns with a median robust pattern descriptor and speeded-up robust feature descriptor are applied to extract complicated features from LP areas. Those hybrid features can enhance the useful information, and the detection system performed well under difficult scenarios. In the detection stage, the trained model by an extreme learning machine (ELM) classifier, with mean-shift algorithm, is used as a detector to decide output results. Performances of the proposed framework were compared with other classifiers using true- and false-positive rates. The system’s performance improvements by the proposed method were also compared with our previous methods and the existing detection methods in the literature. The experiments on an English car LP’s database and other language vehicle images showed that the proposed method made significant improvements to the accuracy and runtime speed for the detection system under difficult image conditions.

MRI texture-based machine learning models for the evaluation of renal function on different segmentations: a proof-of-concept study

BackgroundTo develop and validate an MRI texture-based machine learning model for the noninvasive assessment of renal function.MethodsA retrospective study of 174 diabetic patients (training cohort, n = 123; validation cohort, n = 51) who underwent renal MRI scans was included. They were assigned to normal function (n = 71), mild or moderate impairment (n = 69), and severe impairment groups (n = 34) according to renal function. Four methods of kidney segmentation on T2-weighted images (T2WI) were compared, including regions of interest covering all coronal slices (All-K), the largest coronal slices (LC-K), and subregions of the largest coronal slices (TLCO-K and PIZZA-K). The speeded-up robust features (SURF) and support vector machine (SVM) algorithms were used for texture feature extraction and model construction, respectively. Receiver operating characteristic (ROC) curve analysis was used to evaluate the diagnostic performance of models.ResultsThe models based on LC-K and All-K achieved the nonsignificantly highest accuracy in the classification of renal function (all p values > 0.05). The optimal model yielded high performance in classifying the normal function, mild or moderate impairment, and severe impairment, with an area under the curve of 0.938 (95% confidence interval [CI] 0.935–0.940), 0.919 (95%CI 0.916–0.922), and 0.959 (95%CI 0.956–0.962) in the training cohorts, respectively, as well as 0.802 (95%CI 0.800–0.807), 0.852 (95%CI 0.846–0.857), and 0.863 (95%CI 0.857–0.887) in the validation cohorts, respectively.ConclusionWe developed and internally validated an MRI-based machine-learning model that can accurately evaluate renal function. Once externally validated, this model has the potential to facilitate the monitoring of patients with impaired renal function.