Content‐based image authentication by feature point clustering and matching

Identifying the manufacturer and the type of cardiac implantable electronic devices (CIEDs) is important in emergent clinical settings. Recent studies have illustrated that artificial neural network models can successfully recognize CIEDs from chest X-ray images. However, all existing methods require a vast amount of medical data to train the classification model. Here, we have proposed a novel method to retrieve an identical CIED image from an image database by employing the feature point matching algorithm. A total of 653 unique X-ray images from 456 patients who visited our pacemaker clinic between April 2012 and August 2020 were collected. The device images were manually square-shaped, and was thereafter resized to 224 × 224 pixels. A scale-invariant feature transform (SIFT) algorithm was used to extract the keypoints from the query image and reference images. Paired feature points were selected via brute-force matching, and the average Euclidean distance was calculated. The image with the shortest average distance was defined as the most similar image. The classification performance was indicated by accuracy, precision, recall, and F1-score for detecting the manufacturers and model groups, respectively. The average accuracy, precision, recall, and F-1 score for the manufacturer classification were 97.0%, 0.97, 0.96, and 0.96, respectively. For the model classification task, the average accuracy, precision, recall, and F-1 score were 93.2%, 0.94, 0.92, and 0.93, respectively, all of which were higher than those of the previously reported machine learning models. Feature point matching is useful for identifying CIEDs from X-ray images.

ABSTRACTReliable feature point matching is a pivotal step in the integrated 3D reconstruction of aerial and ground images. Nonetheless, the substantial viewpoint and scale differences between aerial and ground images introduce significant challenges in feature point matching. To address this issue, this study presents a robust matching method for feature points from these two types of images, employing partitioned attention aggregation along with a coarse‐to‐fine hierarchical matching approach, enabling efficient matching of large‐scale aerial‐ground images even with hardware limitations. In the coarse matching phase, region segmentation is carried out on the ground image based on its depth map, which is computed using a monocular depth estimation network. Subsequently, a graph neural network serves as an intermediary for information exchange between features, and partitioned attention aggregation is performed while adhering to the constraints imposed by the segmented image regions. During this process, feature points are grouped to form distinct subgraphs, enhancing the structural similarity between corresponding graphs when there are significant depth and viewpoint changes. This also reduces redundant connections within graph neural networks, leading to efficient feature matching. Corresponding local patches are generated from the full‐sized aerial‐ground images using the initial matches, and further feature point extraction and matching from these patches yield accurate point matches. The experimental results indicate the proposed method performs better than state‐of‐the‐art matching methods. Specifically, compared with the best‐performing method among the comparative ones, our method enhances the average number of correct matches and the average matching precision by approximately 6‐fold and 36%, respectively.

Image stitching is an important technology in machine vision inspection whose algorithms focus on the detection and match of feature points. For the solar panel images achieved by machine vision, it's found that the available image stitching algorithms failed to detect enough valid feature points, which led to a large number of incorrect matching points. Here, we improve an algorithm to locate feature points and find dense match points. The proposed algorithm is based on SIFT. The improved algorithm (I-SIFT) can locate the position of feature points in every solar panel images, reducing the effect of invalid feature points on the experiment. Euclidean distance is used to preliminarily ensure the matching points, and then the relative horizontal position of every matching points is used to eliminate the mismatching points caused by the space similarity of the feature points, so that the matching accuracy is improved. Then the improved algorithm is used in the traditional Harris, SIFT and SURF stitching algorithm. The experimental results show that the success rate of I-SIFT algorithm can exceed 95% and the computation time has decreased by nearly 95% than that of the traditional algorithm. In conclusion, the improved algorithm implements accurately and rapidly stitching for solar panel images.

Road visual navigation relies on accurate road models. This study was aimed at proposing an improved scale-invariant feature transform (SIFT) algorithm for recovering depth information from farmland road images, which would provide a reliable path for visual navigation. The mean image of pixel value in five channels (R, G, B, S and V) were treated as the inspected image and the feature points of the inspected image were extracted by the Canny algorithm, for achieving precise location of the feature points and ensuring the uniformity and density of the feature points. The mean value of the pixels in 5×5 neighborhood around the feature point at an interval of 45o in eight directions was then treated as the feature vector, and the differences of the feature vectors were calculated for preliminary matching of the left and right image feature points. In order to achieve the depth information of farmland road images, the energy method of feature points was used for eliminating the mismatched points. Experiments with a binocular stereo vision system were conducted and the results showed that the matching accuracy and time consuming for depth recovery when using the improved SIFT algorithm were 96.48% and 5.6 s, respectively, with the accuracy for depth recovery of –7.17%-2.97% in a certain sight distance. The mean uniformity, time consuming and matching accuracy for all the 60 images under various climates and road conditions were 50%-70%, 5.0-6.5 s, and higher than 88%, respectively, indicating that performance for achieving the feature points (e.g., uniformity, matching accuracy, and algorithm real-time) of the improved SIFT algorithm were superior to that of conventional SIFT algorithm. This study provides an important reference for navigation technology of agricultural equipment based on machine vision. Keywords: scale-invariant feature transform (sift), feature matching, canny operator, energy method of feature point, farmland road, depth recovery, visual navigation DOI: 10.25165/j.ijabe.20191204.4821 Citation: Yao L J, Hu D, Yang Z D, Li H B, Qian M B. Depth recovery for unstructured farmland road image using an improved SIFT algorithm. Int J Agric & Biol Eng, 2019; 12(4): 141–147.

At present, there are many methods to realize the matching of specified images with features, and the basic components include image feature point detection, feature description, and image matching. Based on this background, this article has done different research and exploration around these three aspects. The image feature point detection method is firstly studied, which commonly include image edge information-based feature detection method, corner information-based detection method, and various interest operators. However, all of the traditional detection methods are involved in problems of large computation burden and time consumption. In order to solve this problem, a feature detection method based on image grayscale information-FAST operator is used in this paper, which is combined with decision tree theory to effectively improve the speed of extracting image feature points. Then, the feature point description method BRIEF operator is studied, which is a local expression of detected image feature points based on descriptors. Since the descriptor does not have rotation invariance, the detection operator is endowed by a direction that is proposed in this paper, and then the local feature description is conducted on the feature descriptor to generate a binary string array containing direction information. Finally, the feature matching machine learning method is analyzed, and the nearest search method is used to find the nearest feature point pair in Euclidean distance, of which the calculation burden is small. The simulation results show that the proposed nearest neighbor search and matching machine learning algorithm has higher matching accuracy and faster calculation speed compared with the classical feature matching algorithm, which has great advantages in processing a large number of array images captured by the light field camera.

Non-rigid registration finds many applications such as photogrammetry, motion tracking, model retrieval, and object recognition. In this paper we propose a novel convex hull aided registration method (CHARM) to match two point sets subject to a non-rigid transformation. First, two convex hulls are extracted from the source and target respectively. Then, all points of the point sets are projected onto the reference plane through each triangular facet of the hulls. From these projections, invariant features are extracted and matched optimally. The matched feature point pairs are mapped back onto the triangular facets of the convex hulls to remove outliers that are outside any relevant triangular facet. The rigid transformation from the source to the target is robustly estimated by the random sample consensus (RANSAC) scheme through minimizing the distance between the matched feature point pairs. Finally, these feature points are utilized as the control points to achieve non-rigid deformation in the form of thin-plate spline of the entire source point set towards the target one. The experimental results based on both synthetic and real data show that the proposed algorithm outperforms several state-of-the-art ones with respect to sampling, rotational angle, and data noise. In addition, the proposed CHARM algorithm also shows higher computational efficiency compared to these methods.

As the front end of visual simultaneous localization and mapping (vSLAM), the feature points matching of the visual odometry (VO) provides important robot pose judgment, while there are mismatches in the feature points matching due to inaccurate information obtained from cameras. In the process of feature points matching, VO initializes the matching of feature points through two adjacent frames of pictures, as SLAM runs, the cumulative error will gradually increase, resulting in mapping and positioning results inaccurate. Aiming to reduce the feature points matching error during initialization, an evidential fusion method for feature points matching is put forward. On the basis of descriptor similarity in Oriented FAST and Rotated BRIEF SLAM (ORB-SLAM) and pixel similarity around feature points, we treat the similarity index as an evidence, and take Belief Jensen-Shannon (BJS) divergence to measure distance between different evidences. The proposed evidential method considers the uncertainties brought by different indexes in accord with the feature points matching, and obtains suitable matching points reducing false matches through the combination of evidences. BJS divergence measure is carried out to measure the discrepancy and conflict degree among the evidences. After that, the reliability of evidence could be obtained to modify the information volume of the evidences. Finally, an example of feature points matching shows that the evidential method is feasible for feature points matching.

In order to reduce the proportion of outliers in feature point matching, we propose a feature point matching optimization algorithm based on a wasserstein distance and apply the algorithm to the grid cell model. The wasserstein distance is introduced to calculate the similarity of the distribution of feature points in the grids around each pair of matching points, and the outer points are eliminated by the similarity. We compare the algorithm with the robust algorithm in OpenCV, and the experimental results show that the precision of our algorithm is higher than robust, and the recall is smaller. We open source our implementations at https://github.com/liuzhenboo/Optimization-of-Feature-Point-Matching-Algorithm-Based-on-Wasserstein-Distance.

Most of the existing visual SLAM schemes rely solely on point or line features to estimate camera trajectory. In some scenes such as texture missing or motion blurring, it’s difficult to find a sufficient number of reliable features, resulting in low positioning accuracy. To extract more features, an RPL-SLAM solution is proposed to extract point features and line features respectively. Ulteriorly, the depth information of RGBD image is used to restore the 3D information of point and line features, improving the accuracy of camera track positioning. RPL-SLAM scheme mainly includes three modules: tracking, local mapping and loop detection. Tracking module extends the application of line feature on the basis of point feature extraction and matching. A SLD line segment extraction algorithm which can eliminate the micro segments and a DBM segment matching algorithm based on word bag are proposed respectively. These two algorithms improve the matching efficiency while ensuring the matching accuracy, and effectively track and locate the camera of each frame. In the local mapping and loop detection module, the Plucker coordinates are applied to express the spatial line and define the re-projection error of the straight line, so that the back-end optimization error model of point-line fusion is unified to solve the instability problem in optimization. RPL-SLAM is tested on TUM RGBD and ICL-NUIM data set respectively, and compared with ORB-SLAM2. The result shows that RPL-SLAM can effectively improve the accuracy of pose estimation and map reconstruction while maintaining real-time performance by fusing point-line features with depth images.

Extracting the fuzzy feature of the mobile video image can effectively improve the low illumination image quality. Traditional methods are used to construct fuzzy feature indexes of mobile terminal video images, and the detailed information of video images is divided, but the bidirectional matching of feature points is ignored, which leads to low extraction accuracy. Therefore, this paper proposes a method for extracting fuzzy features of mobile terminal video images based on SURF-based virtual reality technology. First, perform video image grayscale extraction on the input mobile terminal video image, and detect the closed area in the mobile terminal video image as the radiation invariant area of the terminal video image. Secondly, Hessian matrix is used to detect the feature points of the image, and the non-maximum suppression method and interpolation operation are used to find and locate the extreme value points. Then, the main direction of feature points was determined, and SURF description operator was used for matching to obtain initial matching point pairs. Finally, the obtained fuzzy feature one-way matching result of the video image is matched in two directions, the closest distance ratio is used to match the feature points, and the full constraint condition is used to filter out the wrong matching point pairs, thereby completing the mobile terminal video image fuzzy feature extraction. The experimental results show that the proposed algorithm is effective in feature extraction and matching, stability and speed. The misrecognition rate of the algorithm in this paper is 0.101, and the time used is only 0.41 s, which fully meets the real-time requirements.

The mismatch of geometric parameters in a nanotomography system bears a significant impact on the reconstructed images. Moreover, projection image noise is increased due to limitations of the X-ray power source. The accuracy of the existing self-calibration method, which uses only the grayscale information of the projected image, is easily affected by noise and leads to reduced accuracy. This paper proposes a geometric parameter self-calibration method based on feature matching of mirror projection images. Firstly, the fast extraction and matching feature points in the mirror projection image are performed by speeded-up robust features (SURF). The feature triangle is then designed according to the stable position of the system’s rotation axis to further filter the feature points. In turn, the influence of the mismatched points on the calculation accuracy is reduced. Finally, the straight line where the rotation axis is located is fitted by the midpoint coordinates of the filtered feature points, thereby realizing geometric parameter calibration of the system. Simulation and actual data from the experimental results show that the proposed method effectively realizes the calibration of geometric parameters, and the blurring and ghosting caused by geometric artifacts are corrected. Compared with existing methods, the image clarity can be improved by up to 14.4%.

There remain many difficult problems in computer vision research such as object recognition, three dimensional reconstruction, object tracking, etc. And the basis of solving these problems relies on image matching. The scale invariant feature transform (SIFT) algorithm has been widely used for image matching application. The SIFT algorithm can successfully extract the most descriptive feature points in given input images taken under different viewpoints. However, the performance of the original SIFT algorithm degrades under the influence of noise. We propose to modify the SIFT algorithm to produce better invariant feature points for image matching under noise. We also propose to employ the Earth mover's distance (EMD) as the measurement of similarity between two descriptors. We present extensive experiment results to demonstrate the performance of the proposed methods in image matching under noise.

The classic feature point image stitching algorithm is time-consuming in feature extraction, and an image sparse matrix method is proposed to determine the feature points. This method first uses Laplace operator to extract the image gradient and set the threshold to obtain the sparse matrix of image segmentation, then using features from accelerated segment test (FAST) detection algorithm for feature point. Finally, the speeded-up robust features (SURF) descriptor is given to increase the stability of the feature points. This method solves the problem of time-consuming feature extraction, making the real-time image mosaic possible. In the process of image mosaic, this paper presents a method using Kalman filter to predict the overlap region, thus reducing the computational complexity. In addition, because there is always a mismatch between feature points matching, this paper proposes a method using perceptual hashing to refine the matching pair, which solves the error caused by mismatching for the next image registration and improves the registration accuracy. Experimental results show that the proposed algorithm improves the speed and precision of image mosaic.

The classic feature point image stitching algorithm is time-consuming in feature extraction, and an image sparse matrix method is proposed to determine the feature points. This method first uses Laplace operator to extract the image gradient and set the threshold to obtain the sparse matrix of image segmentation, then using features from accelerated segment test (FAST) detection algorithm for feature point. Finally, the speeded-up robust features (SURF) descriptor is given to increase the stability of the feature points. This method solves the problem of time-consuming feature extraction, making the real-time image mosaic possible. In the process of image mosaic, this paper presents a method using Kalman filter to predict the overlap region, thus reducing the computational complexity. In addition, because there is always a mismatch between feature points matching, this paper proposes a method using perceptual hashing to refine the matching pair, which solves the error caused by mismatching for the next image registration and improves the registration accuracy. Experimental results show that the proposed algorithm improves the speed and precision of image mosaic.

In this study, we propose a digital domain TDI-CMOS dynamic imaging method based on minimum search domain alignment, which consists of five steps: image-motion vector computation, image jitter estimation, feature pair matching, global displacement estimation, and TDI accumulation. To solve the challenge of matching feature point pairs in dark and low-contrast images, our method first optimizes the size and position of the search box using an image motion compensation mathematical model and a satellite platform jitter model. Then, the feature point pairs that best match the extracted feature points of the reference frame are identified within the search box of the target frame. After that, a kernel density estimation algorithm is proposed for calculating the displacement probability density of each feature point pair to fit the actual displacement between two frames. Finally, we align and superimpose all the frames in the digital domain to generate a delayed integral image. Experimental results show that this method greatly improves the alignment speed and accuracy of dark and low-contrast images during dynamic imaging. It effectively mitigates the effects of image motion and jitter from the spatial camera, and the fitted global image motion error is kept below 0.01 pixels, which is compensated to improve the MTF coefficient of the image motion and jitter link to 0.68, thus improving the imaging quality of TDI.