False Matches Research Articles

A review on parameterized string matching algorithms

Identification of candidate genes and nucleotides are basic uses of the Bioinformatics research. Biology that deals with molecule has functional as well as structural behavior imparting need of well-furnished techniques to distinguish the molecules. Parameterized matching is one of those techniques which deal in identifying molecules having different functional and structural behavior. The word “Parameterized” represent the characters or symbols in the form of parameters. It implies that the sequence of characters forming text and pattern are matched if and only if the bijective mapping is formed between them. Exponential increase in the size of data sets leads the requirement to solve this matching problem in sub-linear time. This paper displays the review of single pattern parameterized pattern matching algorithms using q-grams having linear time complexities. It also discusses about the best algorithm that has less number of false matches. The comparisons done are based on certain criteria's presenting pros and cons of the algorithms.

Nonrigid synthetic aperture radar and optical image coregistration by combining local rigid transformations using a Kohonen network.

This study proposes a new algorithm for nonrigid coregistration of synthetic aperture radar (SAR) and optical images. The proposed algorithm employs point features extracted by the binary robust invariant scalable keypoints algorithm and a new method called weighted bidirectional matching for initial correspondence. To refine false matches, we assume that the transformation between SAR and optical images is locally rigid. This property is used to refine false matches by assigning scores to matched pairs and clustering local rigid transformations using a two-layer Kohonen network. Finally, the thin plate spline algorithm and mutual information are used for nonrigid coregistration of SAR and optical images.

Multi-State Self-Learning Template Library Updating Approach for Multi-Camera Human Tracking in Complex Scenes

In multi-camera video tracking, the tracking scene and tracking-target appearance can become complex, and current tracking methods use entirely different databases and evaluation criteria. Herein, for the first time to our knowledge, we present a universally applicable template library updating approach for multi-camera human tracking called multi-state self-learning template library updating (RS-TLU), which can be applied in different multi-camera tracking algorithms. In RS-TLU, self-learning divides tracking results into three states, namely steady state, gradually changing state, and suddenly changing state, by using the similarity of objects with historical templates and instantaneous templates because every state requires a different decision strategy. Subsequently, the tracking results for each state are judged and learned with motion and occlusion information. Finally, the correct template is chosen in the robust template library. We investigate the effectiveness of the proposed method using three databases and 42 test videos, and calculate the number of false positives, false matches, and missing tracking targets. Experimental results demonstrate that, in comparison with the state-of-the-art algorithms for 15 complex scenes, our RS-TLU approach effectively improves the number of correct target templates and reduces the number of similar templates and error templates in the template library.

Robust feature matching for geospatial images via an affine‐invariant coordinate system

AbstractFeature matching is a crucial stage for many photogrammetric and remote sensing applications. This paper proposes a novel and robust feature‐matching method based on a normalised barycentric coordinate system (NBCS), which is superior to a Cartesian system for this task. A scale‐invariant feature transform (SIFT) is performed to provide initial matches containing both correct matches (inliers) and false matches (outliers), with a focus on model estimation from contaminated observations (matches with outliers). An affine‐invariant coordinate system called NBCS is defined based on ratios of areas. The two feature points of a correct match have the same coordinates under NBCS while false correspondences do not. This principle is adapted into a hypothesise‐and‐verify framework. The proposed method is robust, efficient and effective. Extensive experiments on real geospatial image pairs show that it significantly outperforms six other state‐of‐the‐art approaches. The source code and datasets used in this paper have been made public.

A THREE-DIMENSIONAL SIMULATION AND VISUALIZATION SYSTEM FOR UAV PHOTOGRAMMETRY

Abstract. Nowadays UAVs has been widely used for large-scale surveying and mapping. Compared with manned aircraft, UAVs are more cost-effective and responsive. However, UAVs are usually more sensitive to wind condition, which greatly influences their positions and orientations. The flight height of a UAV is relative low, and the relief of the terrain may result in serious occlusions. Moreover, the observations acquired by the Position and Orientation System (POS) are usually less accurate than those acquired in manned aerial photogrammetry. All of these factors bring in uncertainties to UAV photogrammetry. To investigate these uncertainties, a three-dimensional simulation and visualization system has been developed. The system is demonstrated with flight plan evaluation, image matching, POS-supported direct georeferencing, and ortho-mosaicing. Experimental results show that the presented system is effective for flight plan evaluation. The generated image pairs are accurate and false matches can be effectively filtered. The presented system dynamically visualizes the results of direct georeferencing in three-dimensions, which is informative and effective for real-time target tracking and positioning. The dynamically generated orthomosaic can be used in emergency applications. The presented system has also been used for teaching theories and applications of UAV photogrammetry.

FPGA-based architecture of a real-time SIFT matcher and RANSAC algorithm for robotic vision applications

A fundamental problem in computer vision is finding correspondences between features in pairs of similar images. By comparing feature descriptors instead of pixel intensities, the matching capability is significantly increased. Keypoints extracted by Scale-Invariant Feature Transform (SIFT) provide superior matching ability, however, a small proportion of false corresponcences is always inevitable. The exemption of false matches is achieved using robust fitting algorithms, with RANSAC (random sample consensus) being a popular one. SIFT and RANSAC are computationally demanding and time consuming algorithms. When the target application operates in real-time, conventional approaches based on personal computers usually fail to meet the requirements. In this paper, an FPGA-based architecture for real-time SIFT matching and RANSAC algorithm is presented. The proposed scheme is applied to identify the correspondences between point features across consecutive video frames and reject the false matches. The architecture is verified using the DE2i-150 development board. Using Cyclone IV technology, the system supports a processing rate of 40fps for VGA resolution and therefore meets real-time requirements.

Fast Pattern Matching in Compressed Text using Wavelet Tree

ABSTRACTWith the recent increase in the size of data, compression has become essential tool for handling massive data. Compression is usually more helpful in handling huge data over the networks, large text collections, and storing massive biological data. It is also useful in searching a pattern (of any kind) inside the huge data set. Compressed pattern matching (CPM) is the task of performing string matching in a compressed text without decompressing it. In this type of matching, pattern may or may not be compressed. This paper presents an efficient algorithm (WBTC_WT) for matching a pattern directly inside the compressed text. The proposed algorithm uses the tagged sub optimal code category of algorithm called word-based tagged code (WBTC) and a self-indexed data structure called wavelet tree. WBTC is used for encoding the text and wavelet tree provides fast searching over the compressed text. WBTC_WT removes the problem of false matches, encountered in some of the previous approaches and is able to match arbitrary portion of text without decompressing it. The proposed algorithm is implemented, analyzed, and compared with existing approaches on huge data set. From the simulation results, it is found that our algorithm outperforms the existing algorithms in most of the cases.

Research on Underwater Navigation Algorithm Based on SIFT Matching Algorithm

Autonomous Underwater Vehicle (AUV) is currently used to side scan sonar, doppler velocimetry and inertial navigation devices and other equipment-based integrated navigation program navigation. The side scan sonar can generate the underwater acoustical image in real time and match it with the feature database through the image matching algorithm to filter the navigation data. Aiming at the characteristics of underwater acoustic image data, the method of drawing underwater acoustic image is described. In order to integrate the feature matching of the underwater acoustic image into the integrated navigation, this paper introduces the SIFT feature matching algorithm to improve the characteristics of the underwater acoustic image and introduces the discriminant condition based on the least squares method. After the matching criterion is introduced, the improved SIFT feature matching algorithm is greatly improved when the landmark matching is achieved, and the occurrence of false matching is avoided. Finally, the real experimental data obtained by the side-scan sonar equipment are verified by the algorithm, and the satisfactory results are obtained.

3DHoPD: A Fast Low-Dimensional 3-D Descriptor

Three-dimensional feature descriptors are heavily employed in various 3-D perception applications to find keypoint correspondences between two point clouds. The availability of mobile devices equipped with depth sensors compels the developed applications to be both memory and computationally efficient. Toward this, in this letter, we present 3DHoPD, a new low-dimensional 3-D feature descriptor that is extremely fast to compute. The novelty lies in compactly encoding the “3-D” keypoint position by transforming it to a new 3-D space, where the keypoints arising from similar 3-D surface patches lie close to each other. Then, we propose histograms of point distributions (HoPD) to capture the neighborhood structure, thus forming 3DHoPD (3D+HoPD). We propose a tailored feature descriptor matching technique, wherein the “3-D” keypoint position in the new 3-D space is used to remove false positive matches, effectively reducing the search space by 90%, and then, the exact match is found using the “HoPD” descriptor. Experimental evaluation on multiple publicly available datasets shows that 3DHoPD is robust to noise and offers stable and competitive keypoint matching performance to the existing state-of-the-art 3-D descriptors with similar dimensionality across datasets, while requiring dramatically low-computational time (10 $\times$ faster). The source code and additional experimental results are available at https://sites.google.com/site/3dhopd/

Robust image matching with cascaded outliers removal

Finding feature correspondences between a pair of images is a fundamental problem in computer vision for 3D reconstruction and target recognition. In practice, for feature based matching methods, there is often having a higher percentage of incorrect matches and decreasing the matching accuracy, which is not suitable for subsequent processing. In this paper, we develop a novel algorithm to find good and more correspondences. Firstly, detecting SURF keypoints and extracting SURF descriptors; Then Obtain the initial matches based on the Euclidean distance of SURF descriptors; Thirdly, remove false matches by sparse representation theory, at the same time, exploiting the information of SURF keypoints, such as scale and orientation, forming the geometrical constraints to further delete incorrect matches; Finally, adopt Delaunay triangulation to refine the matches and get the final matches. Experimental results on real-world image matching datasets demonstrate the effectiveness and robustness of our proposed method.

Probabilistic linking to enhance deterministic algorithms and reduce linkage errors in hospital administrative data

BackgroundThe pseudonymisation algorithm used to link together episodes of care belonging to the same patient in England [Hospital Episode Statistics ID (HESID)] has never undergone any formal evaluation to determine...

Maximizing feature detection in aerial unmanned aerial vehicle datasets

This paper compares several feature detectors applied to imagery from an unmanned aerial vehicle to find the best detection algorithm when applied to datasets that vary in translation and have little or no image overlap. Metrics of inliers and reconstruction accuracy of feature detectors are considered with respect to three-dimensional reconstruction results. The image matching results are tested experimentally, and an approach to detecting false matches is outlined. Results showed that although the detectors varied in the number of keypoints generated, a large number of inliers does not necessarily translate into more points in the final point cloud reconstruction and that the process of comparing a large quantity of redundant keypoints may outweigh the advantage of having the extra points. The results also showed that despite the development of keypoint detectors and descriptors, none of them consistently demonstrated a substantial improvement in the quality of structure from motion reconstruction when applied to a wide range of disparate urban and rural images.

Constructing cancellable template with synthetic minutiae

Security measures have to be taken to protect the privacy of biometric data. Cancellablebiometrics is proposed as an effective mechanism of using and protectingbiometrics. The authors propose a new approach of constructing cancellablefingerprint template by mapping real minutiae to randomly generated minutiae ina synthetic template. The synthetic minutiae are selected based on thek-nearest neighbour method. One synthetic neighbour of eachreal minutia is utilised to construct the verification template (VT). Since thesynthetic template is determined by a user-specific PIN and a random salt, theproposed method is in fact a two-factor authentication scheme. Multiple VTs canbe generated easily by applying different PINs and salts to a real template. Toprove the validity of the scheme, testing is carried out on three databases. Afew factors affecting matching are also investigated. The results show that theconstructed templates satisfy the requirements of cancellable biometrics. Falsenon-match rate and False matching rate with the transformed templates can bemuch lower than those with the original templates by properly selecting the sizeof the synthetic templates and the ordinal number of the nearest neighbours. Theproposed approach can also be utilised for multi-generation templatetransformation.

Toward online education for fingerprint recognition: A proof-of-concept web platform

ABSTRACTRecent advances in information and communication technology (ICT) have pushed education systems into the online paradigm. Although fingerprint recognition has received considerable attention from researchers, the concept of creating online or distance education systems for fingerprint recognition systems is a valid problem that requires further investigation. This article addresses the problem and presents a web platform for online education of a fingerprint recognition system. This study focused on the technical design and implementation of the web platform solely as a proof of concept to illustrate the possibility of creating distance education for fingerprint recognition. The developed platform offers students a way to gain knowledge about the full range of fingerprint recognition system technology. The significance of using a web platform stems from the need to supplement students’ theoretical knowledge with practical hands-on experience with information security in general and with fingerprint recognition in particular. Demonstrations such as fingerprint image enhancement and fingerprint feature extraction are included in the current platform prototype. Plots of fingerprint recognition performance curves such as false match rate (FMR) and false non-match rate (FNMR) as functions of the matching threshold curve, the receiver operating characteristic (ROC) curve, and the detection error trade-off (DET) curve are plotted as part of the platform. From a technical viewpoint, the platform was successfully implemented; however, its educational impact needs further evaluation.

Automatic Registration of Images to Untextured Geometry Using Average Shading Gradients

Many existing approaches for image-to-geometry registration assume that either a textured 3D model or a good initial guess of the 3D pose is available to bootstrap the registration process. In this paper we consider the registration of photographs to 3D models even when no texture information is available. This is very challenging as we cannot rely on texture gradients, and even shading gradients are hard to estimate since the lighting conditions are unknown. To that end, we propose average shading gradients, a rendering technique that estimates the average gradient magnitude over all lighting directions under Lambertian shading. We use this gradient representation as the building block of a registration pipeline based on matching sparse features. To cope with inevitable false matches due to the missing texture information and to increase robustness, the pose of the 3D model is estimated in two stages. Coarse pose hypotheses are first obtained from a single correct match each, subsequently refined using SIFT flow, and finally verified. We apply our algorithm to registering images of real-world objects to untextured 3D meshes of limited accuracy. Moreover, we show that registration can be performed even for paintings despite lacking photo-realism.

A hyperspectral vessel image registration method for blood oxygenation mapping.

Blood oxygenation mapping by the means of optical oximetry is of significant importance in clinical trials. This paper uses hyperspectral imaging technology to obtain in vivo images for blood oxygenation detection. The experiment involves dorsal skin fold window chamber preparation which was built on adult (8–10 weeks of age) female BALB/c nu/nu mice and in vivo image acquisition which was performed by hyperspectral imaging system. To get the accurate spatial and spectral information of targets, an automatic registration scheme is proposed. An adaptive feature detection method which combines the local threshold method and the level-set filter is presented to extract target vessels. A reliable feature matching algorithm with the correlative information inherent in hyperspectral images is used to kick out the outliers. Then, the registration images are used for blood oxygenation mapping. Registration evaluation results show that most of the false matches are removed and the smooth and concentrated spectra are obtained. This intensity invariant feature detection with outliers-removing feature matching proves to be effective in hyperspectral vessel image registration. Therefore, in vivo hyperspectral imaging system by the assistance of the proposed registration scheme provides a technique for blood oxygenation research.

The feasibility of endoscopy-CT image registration in the head and neck without prospective endoscope tracking.

PurposeEndoscopic examinations are frequently-used procedures for patients with head and neck cancer undergoing radiotherapy, but radiation treatment plans are created on computed tomography (CT) scans. Image registration between endoscopic video and CT could be used to improve treatment planning and analysis of radiation-related normal tissue toxicity. The purpose of this study was to explore the feasibility of endoscopy-CT image registration without prospective physical tracking of the endoscope during the examination.MethodsA novel registration technique called Location Search was developed. This technique uses physical constraints on the endoscope’s view direction to search for the virtual endoscope coordinates that maximize the similarity between the endoscopic video frame and the virtual endoscopic image. Its performance was tested on phantom and patient images and compared to an established registration technique, Frame-To-Frame Tracking.ResultsIn phantoms, Location Search had average registration errors of 0.55 ± 0.60 cm for point measurements and 0.29 ± 0.15 cm for object surface measurements. Frame-To-Frame Tracking achieved similar results on some frames, but it failed on others due to the virtual endoscope becoming lost. This weakness was more pronounced in patients, where Frame-To-Frame tracking could not make it through the nasal cavity. On successful patient video frames, Location Search was able to find endoscope positions with an average distance of 0.98 ± 0.53 cm away from the ground truth positions. However, it failed on many frames due to false similarity matches caused by anatomical structural differences between the endoscopic video and the virtual endoscopic images.ConclusionsEndoscopy-CT image registration without prospective physical tracking of the endoscope is possible, but more development is required to achieve an accuracy suitable for clinical translation.

On the integral use of foundational concepts in verifying validity during skull-photo superimposition

Often cited reliability test on video superimposition method integrated scaling face-images in relation to skull-images, tragus-auditory meatus relationship in addition to exocanthion-Whitnall’s tubercle relationship when orientating the skull-image and wipe mode imaging in addition to mix mode imaging when obtaining skull-face image overlay and evaluating the goodness of match. However, a report that found higher false positive matches in computer assisted superimposition method transited from the above foundational concepts and relied on images of unspecified sizes that are lesser than ‘life-size’, frontal plane landmarks in the skull- and face- images alone for orientating the skull-image and mix images alone for evaluating the goodness of match. Recently, arguing the use of ‘life-size’ images as ‘archaic’, the authors who tested the reliability in the computer assisted superimposition method have denied any method transition. This article describes that the use of images of unspecified sizes at lesser than ‘life-size’ eliminates the only possibility to quantify parameters during superimposition which alone enables dynamic skull orientation when overlaying a skull-image with a face-image in an anatomically acceptable orientation. The dynamic skull orientation process mandatorily requires aligning the tragus in the 2D face-image with the auditory meatus in the 3D skull-image for anatomically orientating the skull-image in relation to the posture in the face-image, a step not mentioned by the authors describing the computer assisted superimposition method. Furthermore, mere reliance on mix type images during image overlay eliminates the possibility to assess the relationship between the leading edges of the skull- and face-image outlines as also specific area match among the corresponding craniofacial organs during superimposition. Indicating the possibility of increased false positive matches as a consequence of the above method transitions, the need for testing the reliability in the superimposition method adopting concepts that are considered safe is stressed.

Robust pattern decoding in shape-coded structured light

Decoding is a challenging and complex problem in a coded structured light system. In this paper, a robust pattern decoding method is proposed for the shape-coded structured light in which the pattern is designed as grid shape with embedded geometrical shapes. In our decoding method, advancements are made at three steps. First, a multi-template feature detection algorithm is introduced to detect the feature point which is the intersection of each two orthogonal grid-lines. Second, pattern element identification is modelled as a supervised classification problem and the deep neural network technique is applied for the accurate classification of pattern elements. Before that, a training dataset is established, which contains a mass of pattern elements with various blurring and distortions. Third, an error correction mechanism based on epipolar constraint, coplanarity constraint and topological constraint is presented to reduce the false matches. In the experiments, several complex objects including human hand are chosen to test the accuracy and robustness of the proposed method. The experimental results show that our decoding method not only has high decoding accuracy, but also owns strong robustness to surface color and complex textures.

The Development and Application of Random Match Probabilities to Firearm and Toolmark Identification.

The field of firearms and toolmark analysis has encountered deep scrutiny of late, stemming from a handful of voices, primarily in the law and statistical communities. While strong scrutiny is a healthy and necessary part of any scientific endeavor, much of the current criticism leveled at firearm and toolmark analysis is, at best, misinformed and, at worst, punditry. One of the most persistent criticisms stems from the view that as the field lacks quantified random match probability data (or at least a firm statistical model) with which to calculate the probability of a false match, all expert testimony concerning firearm and toolmark identification or source attribution is unreliable and should be ruled inadmissible. However, this critique does not stem from the hard work of actually obtaining data and performing the scientific research required to support or reject current findings in the literature. Although there are sound reasons (described herein) why there is currently no unifying probabilistic model for the comparison of striated and impressed toolmarks as there is in the field of forensic DNA profiling, much statistical research has been, and continues to be, done to aid the criminal justice system. This research has thus far shown that error rate estimates for the field are very low, especially when compared to other forms of judicial error. The first purpose of this paper is to point out the logical fallacies in the arguments of a small group of pundits, who advocate a particular viewpoint but cloak it as fact and research. The second purpose is to give a balanced review of the literature regarding random match probability models and statistical applications that have been carried out in forensic firearm and toolmark analysis.