Feature Matching Algorithm Research Articles

A real-time matching algorithm using sparse matrix

Aiming at the shortcomings of the traditional image feature matching algorithm, which is computationally expensive and time-consuming, this paper presents a real-time feature matching algorithm. Firstly, the algorithm constructs sparse matrices by Laplace operator and the Laplace weighted is carried out. Then, the feature points are detected by the FAST feature point detection algorithm. The SURF algorithm is used to assign the direction and descriptor to the feature for rotation invariance, and then the Gaussian pyramid is used to make it scalable invariant. Secondly, the match pair is extracted by the violent matching method, and the matching pair is purified by Hamming distance and symmetry method. Finally, the RANSAC algorithm is used to get the optimal matrix, and the affine invariance check is used to match the result. The algorithm is compared with the classical feature point matching algorithm, which proves that the method has high real-time performance under the premise of guaranteeing the matching precision.

Progressive Feature Matching: Incremental Graph Construction and Optimization

We present a novel feature matching algorithm that systematically utilizes the geometric properties of image features such as position, scale, and orientation, in addition to the conventional descriptor vectors. In challenging scenes, in which repetitive structures and large view changes are present, it is difficult to find correct correspondences using conventional approaches that only use descriptors, as the descriptor distances of correct matches may not be the least among the candidates. The feature matching problem is formulated as a Markov random field (MRF) that uses descriptor distances and relative geometric similarities together. Assuming that the layout of the nearby features does not considerably change, we propose the bidirectional transfer measure to gauge the geometric consistency between the pairs of feature correspondences. The unmatched features are explicitly modeled in the MRF to minimize their negative impact. Instead of solving the MRF on the entire features at once, we start with a small set of confident feature matches, and then progressively expand the MRF with the remaining candidate matches. The proposed progressive approach yields better feature matching performance and faster processing time. Experimental results show that the proposed algorithm provides better feature correspondences in many challenging scenes, i.e., more matches with higher inlier ratio and lower computational cost than those of the state-of-the-art algorithms. The source code of our implementation is open to the public.

Image feature extraction algorithm in big data environment

The purpose of this article is to explore effective image feature extraction algorithms in the context of big data, and to mine their potential information from complex image data. Based on the BRISK and SIFT algorithms, this paper proposes an image feature extraction and matching algorithm based on BRISK corner points. By combining the SIFT scale space and the BRISK algorithm, a new scale space construction method is proposed. The BRISK algorithm extracts the corner invariant features. Then, by using the improved feature matching method and eliminating the mismatching algorithm, the exact matching of the images is realized. A large number of experimental verifications were performed in the standard test Mikolajczyk image database and aerial image database. The experimental results show that the improved algorithm in this paper is an effective image matching algorithm. The highest accuracy of actual aerial image matching can reach 85.19%, and it can realize the actual aerial image matching that BRISK and SIFT algorithms cannot complete. The improved algorithm in this paper has the advantages of higher matching accuracy and strong robustness.

Toward Unconstrained Palmprint Recognition on Consumer Devices: A Literature Review

As a biometric palmprints have been largely under-utilized, but they offer some advantages over fingerprints and facial biometrics. Recent improvements in imaging capabilities on handheld and wearable consumer devices have re-awakened interest in the use fo palmprints. The aim of this paper is to provide a comprehensive review of state-of-the-art methods for palmprint recognition including Region of Interest extraction methods, feature extraction approaches and matching algorithms along with overview of available palmprint datasets in order to understand the latest trends and research dynamics in the palmprint recognition field.

Image Feature Matching Via Parallax Mapping for Close Range Photogrammetric Application

Image feature matching is an important step in close range photogrammetric applications, and implementing a fast, accurate and robust feature-based image matching technique is a challenging task. To solve the problems of traditional image feature matching algorithms, such as their low accuracy and long processing time, we present a parallax mapping-based matching (PMM) method that is able to improve the computation efficiency, accuracy and robustness of feature-based image matching for close range photogrammetric applications. First, the disparity of the initial corresponding points is calculated, and the mismatches are initially removed via local disparity clustering. Then, the local coordinates of the matching points are constrained by an image division grid. To ensure the correctness of the matching points, the fast polynomial transform is used for as a quadratic constraint. The method can extract high accuracy matching points from the original coarse matching points with low accuracy, and also preserve the true matching points to the greatest extent. Using a variety of experimental datasets and current mainstream feature extraction algorithms, we designed and compared commonly used feature-based image matching algorithms. The experimental results show that the proposed method is simple but effective, can meet the real-time calculation requirements, and outperforms the current state-of-the-art methods.

Digital Image Falsification Detection System for Effective Data Communication

In this proposed system a digital imagefalsification can be identified using the combination of both adaptive over block based segmentation, feature keypointbased feature extraction algorithms(Scale Invariant Feature Transform (SIFT) and Speeded Up Robust Features (SURF)) and forgery region extraction algorithm. The proposed falsification detection algorithm comprises both block based falsification detection algorithm (adaptive over block based segmentation and block feature matching algorithm) and the keypoint based falsification detection algorithm(forgery region extraction algorithm). Adaptive over block based Segmentation algorithm adaptively segments the input digital image into separate(non overlapped) blocks in irregular manner. Scale Invariant Feature Transform (SIFT) algorithm and Speeded Up Robust Features (SURF) algorithms are used to draw out features from the segmentedblocks as a block features. Then the extracted features are matched with the feature points of other segmented block. If the feature key points are matched with any other feature point presents in the segmented blocks, then the matched feature points are marked as Labeled key Points (LKP), which can be doubted as a forged regions. Finally, the Forgery Region Extraction algorithm can be used to detect the forged region from the input digital image based on the extracted labeled feature points. The experimental outcomesdisplay that the novelfalsification detection system can accomplished the requirements compared with the existing digital imagefalsification detection methods.

An efficient copy move forgery detection using deep learning feature extraction and matching algorithm

The image forgery activities are on the rise because of the development of various image editing tools. Such activities are done by attackers with intentions of defaming people and websites or for gaining monetary advantage, extortion etc. Image forgeries are carried out through various ways, among one is the copy-move forgery. The basic process of copy-move image forgery is copying the objects present in an image and create the new image by using the copied objects or placing the copied object on the same image on a different location, hence the need for a forgery detection system to protect the authenticity of images. The existing forgery detection techniques detect the tampered regions with less efficiency because of the large size and lower contrast of the images. This article proposes an efficient technique for detecting the copy-move forged image based on deep learning. The proposed algorithm initializes the tampered image as the input for our system to detect the tampered region. Our system includes processes like segmentation, feature extraction, dense depth reconstruction, and finally identifying the tampered areas. The proposed deep learning based system can save on computational time and detect the duplicated regions with more accuracy.

RIFT: Multi-modal Image Matching Based on Radiation-variation Insensitive Feature Transform.

Traditional feature matching methods, such as scale-invariant feature transform (SIFT), usually use image intensity or gradient information to detect and describe feature points; however, both intensity and gradient are sensitive to nonlinear radiation distortions (NRD). To solve this problem, this paper proposes a novel feature matching algorithm that is robust to large NRD. The proposed method is called radiation-variation insensitive feature transform (RIFT). There are three main contributions in RIFT. First, RIFT uses phase congruency (PC) instead of image intensity for feature point detection. RIFT considers both the number and repeatability of feature points and detects both corner points and edge points on the PC map. Second, RIFT originally proposes a maximum index map (MIM) for feature description. The MIM is constructed from the log-Gabor convolution sequence and is much more robust to NRD than traditional gradient map. Thus, RIFT not only largely improves the stability of feature detection but also overcomes the limitation of gradient information for feature description. Third, RIFT analyses the inherent influence of rotations on the values of the MIM and realises rotation invariance. We use six different types of multi-modal image datasets to evaluate RIFT, including optical-optical, infrared-optical, synthetic aperture radar (SAR)-optical, depth-optical, map-optical, and day-night datasets. Experimental results show that RIFT is superior to SIFT and SAR-SIFT on multi-modal images. To the best of our knowledge, RIFT is the first feature matching algorithm that can achieve good performance on all the abovementioned types of multi-modal images. The source code of RIFT and the multi-modal image datasets are publicly available1.

A real-time matching algorithm using sparse matrix

Aiming at the shortcomings of the traditional image feature matching algorithm, which is computationally expensive and time-consuming, this paper presents a real-time feature matching algorithm. Firstly, the algorithm constructs sparse matrices by Laplace operator and the Laplace weighted is carried out. Then, the feature points are detected by the FAST feature point detection algorithm. The SURF algorithm is used to assign the direction and descriptor to the feature for rotation invariance, and then the Gaussian pyramid is used to make it scalable invariant. Secondly, the match pair is extracted by the violent matching method, and the matching pair is purified by Hamming distance and symmetry method. Finally, the RANSAC algorithm is used to get the optimal matrix, and the affine invariance check is used to match the result. The algorithm is compared with the classical feature point matching algorithm, which proves that the method has high real-time performance under the premise of guaranteeing the matching precision.

Micro-Distortion Detection of Lidar Scanning Signals Based on Geometric Analysis

When detecting micro-distortion of lidar scanning signals, current hardwires and algorithms have low compatibility, resulting in slow detection speed, high energy consumption, and poor performance against interference. A geometric statistics-based micro-distortion detection technology for lidar scanning signals was proposed. The proposed method built the overall framework of the technology, used TCD1209DG (made by TOSHIBA, Tokyo, Japan) to implement a linear array CCD (charge-coupled device) module for photoelectric conversion, signal charge storage, and transfer. Chip FPGA was used as the core component of the signal processing module for signal preprocessing of TCD1209DG output. Signal transmission units were designed with chip C8051, FT232, and RS-485 to perform lossless signal transmission between the host and any slave. The signal distortion feature matching algorithm based on geometric statistics was adopted. Micro-distortion detection of lidar scanning signals was achieved by extracting, counting, and matching the distorted signals. The correction of distorted signals was implemented with the proposed method. Experimental results showed that the proposed method had faster detection speed, lower detection energy consumption, and stronger anti-interference ability, which effectively improved micro-distortion correction.

An Improved SIFT Algorithm for Monocular Vision Positioning

In view of the high real-time and accuracy requirements of the monocular hand-eye vision system in the positioning process, and in the case that the existing image matching algorithm can not meet these two requirements well at the same time, this paper improves the SIFT feature matching algorithm based on local features. First, the corner points determined in the Harris operator are used instead of the key points determined by the SIFT algorithm as feature points in the template image and the image to be matched. Then, a 32-dimensional feature description vector is constructed for each of the selected feature points through a Gaussian circular window. In the registration phase, the Euclidean distance is used as a measure function to match the 32-dimensional feature descriptors. Finally, 100 template images acquired by the monocular hand-eye vision experimental platform are used to test the matching effect of the improved SIFT algorithm, which proves that the improved algorithm has higher improvement in matching time and registration accuracy than the original algorithm. It is applicable to image registration for monocular vision positioning in industrial practice.

Biological fingerprint using scout computed tomographic images for positive patient identification.

Management of patient identification is an important issue that should be addressed to ensure patient safety while using modern healthcare systems. Patient identification errors can be mainly attributed to human errors or system problems. An error-tolerant system, such as a biometric system, should be able to prevent or mitigate potential misidentification occurrences. Herein, we propose the use of scout computed tomography (CT) images for biometric patient identity verification and present the quantitative accuracy outcomes of using this technique in a clinical setting. Scout CT images acquired from routine examinations of the chest, abdomen, and pelvis were used as biological fingerprints. We evaluated the resemblance of the follow-up with the baseline image by comparing the estimates of the image characteristics using local feature extraction and matching algorithms. The verification performance was evaluated according to the receiver operating characteristic (ROC) curves, area under the ROC curves (AUC), and equal error rates (EER). The closed-set identification performance was evaluated according to the cumulative match characteristic curves and rank-one identification rates (R1). A total of 619 (383 males, 236 females, age range 21-92years) patients who underwent baseline and follow-up chest-abdomen-pelvis CT scans on the same CT system were analyzed for verification and closed-set identification. The highest performances of AUC, EER, and R1 were 0.998, 1.22%, and 99.7%, respectively, in the considered evaluation range. Furthermore, to determine whether the performance decreased in the presence of metal artifacts, the patients were classified into two groups, namely scout images with (255 patients) and without (364 patients) metal artifacts, and the significance test was performed for two ROC curves using the unpaired Delong's test. No significant differences were found between the ROC performances in the presence and absence of metal artifacts when using a sufficient number of local features. Our proposed technique demonstrated that the performance was comparable to that of conventional biometrics methods when using chest, abdomen, and pelvis scout CT images. Thus, this method has the potential to discover inadequate patient information using the available chest, abdomen, and pelvis scout CT image; moreover, it can be applied widely to routine adult CT scans where no significant body structure effects due to illness or aging are present. Our proposed method can obtain accurate patient information available at the point-of-care and help healthcare providers verify whether a patient's identity is matched accurately. We believe the method to be a key solution for patient misidentification problems.

Partial Fingerprint Recognition of Feature Extraction and Improving Accelerated KAZE Feature Matching Algorithm

Nowadays for Personal Identification Numbers (PIN) and passwords an efficient and secure alternative has been used which is called e-security. Due to the various computer frauds like identity theft and computer hacking there is a rapid increase in the financial losses of payment. In present day, the banking sector is accepting the payments through credit cards for every on-line as well as offline transaction which actually encourages the cashless payments. It will be the foremost convenient because of do on-line looking out, bills payments etc. Therefore, there is also increase in the fraud risks that area associated with the misuse of the credit cards as a result of technology development. So we go for biometric security to resolve this problem. The aim of our study is to given security through biometric technology of fingerprint recognition. Minutiae extraction and minutiae matching technique of AKAZE to boost the accuracy and high speed computation.

DMS-SLAM: A General Visual SLAM System for Dynamic Scenes with Multiple Sensors.

Presently, although many impressed SLAM systems have achieved exceptional accuracy in a real environment, most of them are verified in the static environment. However, for mobile robots and autonomous driving, the dynamic objects in the scene can result in tracking failure or large deviation during pose estimation. In this paper, a general visual SLAM system for dynamic scenes with multiple sensors called DMS-SLAM is proposed. First, the combination of GMS and sliding window is used to achieve the initialization of the system, which can eliminate the influence of dynamic objects and construct a static initialization 3D map. Then, the corresponding 3D points of the current frame in the local map are obtained by reprojection. These points are combined with the constant speed model or reference frame model to achieve the position estimation of the current frame and the update of the 3D map points in the local map. Finally, the keyframes selected by the tracking module are combined with the GMS feature matching algorithm to add static 3D map points to the local map. DMS-SLAM implements pose tracking, closed-loop detection and relocalization based on static 3D map points of the local map and supports monocular, stereo and RGB-D visual sensors in dynamic scenes. Exhaustive evaluation in public TUM and KITTI datasets demonstrates that DMS-SLAM outperforms state-of-the-art visual SLAM systems in accuracy and speed in dynamic scenes.

Feature-Based Registration for 3D Eddy Current Pulsed Thermography

Measurement and quantification of defects are the key challenges for eddy current pulsed thermography (ECPT), localization and detection of surface, sub-surface defects, and the quantification of the defects under complex geometry in particular. To address this issue, this paper proposed a 3D eddy current pulsed thermography system by integration the ECPT system with an RGB-D (3D point cloud with RGB texture information) camera. The thermal image is mapped with the RGB-D image via matched features from the thermal and visible image. In order to establish reliable key-point matches for multi-spectrum image registration, a new shape constrained scale-invariant feature transform (SCSIFT) descriptor is proposed, which adds global shape information to SIFT descriptor. The experimental study has validated that the developed feature matching algorithm for the mapping of the thermal image with RGB-D image. The newly developed 3D ECPT system provides quantified data, including 3D heat distribution and the 3D spatial relationship between defect position, the excitation coil, and the whole specimen, which shows its potential of quantitative evaluation of the defect characteristics.

Retaining Privileged Information for Multi-Task Learning.

Knowledge transfer has been of great interest in current machine learning research, as many have speculated its importance in modeling the human ability to rapidly generalize learned models to new scenarios. Particularly in cases where training samples are limited, knowledge transfer shows improvement on both the learning speed and generalization performance of related tasks. Recently, Learning Using Privileged Information (LUPI) has presented a new direction in knowledge transfer by modeling the transfer of prior knowledge as a Teacher-Student interaction process. Under LUPI, a Teacher model uses Privileged Information (PI) that is only available at training time to improve the sample complexity required to train a Student learner for a given task. In this work, we present a LUPI formulation that allows privileged information to be retained in a multi-task learning setting. We propose a novel feature matching algorithm that projects samples from the original feature space and the privilege information space into a joint latent space in a way that informs similarity between training samples. Our experiments show that useful knowledge from PI is maintained in the latent space and greatly improves the sample efficiency of other related learning tasks. We also provide an analysis of sample complexity of the proposed LUPI method, which under some favorable assumptions can achieve a greater sample efficiency than brute force methods.

Feedback Unilateral Grid-Based Clustering Feature Matching for Remote Sensing Image Registration

In feature-based image matching, implementing a fast and ultra-robust feature matching technique is a challenging task. To solve the problems that the traditional feature matching algorithm suffers from, such as long running time and low registration accuracy, an algorithm called feedback unilateral grid-based clustering (FUGC) is presented which is able to improve computation efficiency, accuracy and robustness of feature-based image matching while applying it to remote sensing image registration. First, the image is divided by using unilateral grids and then fast coarse screening of the initial matching feature points through local grid clustering is performed to eliminate a great deal of mismatches in milliseconds. To ensure that true matches are not erroneously screened, a local linear transformation is designed to take feedback verification further, thereby performing fine screening between true matching points deleted erroneously and undeleted false positives in and around this area. This strategy can not only extract high-accuracy matching from coarse baseline matching with low accuracy, but also preserves the true matching points to the greatest extent. The experimental results demonstrate the strong robustness of the FUGC algorithm on various real-world remote sensing images. The FUGC algorithm outperforms current state-of-the-art methods and meets the real-time requirement.

Performance and Analysis of Feature Tracking Approaches in Laser Speckle Instrumentation.

This paper investigates the application of feature tracking algorithms as an alternative data processing method for laser speckle instrumentation. The approach is capable of determining both the speckle pattern translation and rotation and can therefore be used to detect the in-plane rotation and translation of an object simultaneously. A performance assessment of widely used feature detection and matching algorithms from the computer vision field, for both translation and rotation measurements from laser speckle patterns, is presented. The accuracy of translation measurements using the feature tracking approach was found to be similar to that of correlation-based processing with accuracies of 0.025–0.04 pixels and a typical precision of 0.02–0.09 pixels depending upon the method and image size used. The performance for in-plane rotation measurements are also presented with rotation measurement accuracies of <0.01° found to be achievable over an angle range of ±10° and of <0.1° over a range of ±25°, with a typical precision between 0.02 and 0.08° depending upon method and image size. The measurement range is found to be limited by the failure to match sufficient speckles at larger rotation angles. An analysis of each stage of the process was conducted to identify the most suitable approaches for use with laser speckle images and areas requiring further improvement. A quantitative approach to assessing different feature tracking methods is described, and reference data sets of experimentally translated and rotated speckle patterns from a range of surface finishes and surface roughness are presented. As a result, three areas that lead to the failure of the matching process are identified as areas for future investigation: the inability to detect the same features in partially decorrelated images leading to unmatchable features, the variance of computed feature orientation between frames leading to different descriptors being calculated for the same feature, and the failure of the matching processes due to the inability to discriminate between different features in speckle images.

Score Level and Rank Level Fusion for Kinect-Based Multi-Modal Biometric System

Abstract Computational intelligence firmly made its way into the areas of consumer applications, banking, education, social networks, and security. Among all the applications, biometric systems play a significant role in ensuring an uncompromised and secure access to resources and facilities. This article presents a first multimodal biometric system that combines KINECT gait modality with KINECT face modality utilizing the rank level and the score level fusion. For the KINECT gait modality, a new approach is proposed based on the skeletal information processing. The gait cycle is calculated using three consecutive local minima computed for the distance between left and right ankles. The feature distance vectors are calculated for each person’s gait cycle, which allows extracting the biometric features such as the mean and the variance of the feature distance vector. For Kinect face recognition, a novel method based on HOG features has been developed. Then, K-nearest neighbors feature matching algorithm is applied as feature classification for both gait and face biometrics. Two fusion algorithms are implemented. The combination of Borda count and logistic regression approaches are used in the rank level fusion. The weighted sum method is used for score level fusion. The recognition accuracy obtained for multi-modal biometric recognition system tested on KINECT Gait and KINECT Eurocom Face datasets is 93.33% for Borda count rank level fusion, 96.67% for logistic regression rank-level fusion and 96.6% for score level fusion.

An Indoor Scene Classification Method for Service Robot Based on CNN Feature

Indoor scene classification plays a vital part in environment cognition of service robot. With the development of deep learning, fine-tuning CNN (Convolutional Neural Network) on target datasets has become a popular way to solve classification problems. However, this method cannot obtain satisfying indoor scene classification results because of overfitting when scene training datasets are insufficient. To solve this problem, an indoor scene classification method is proposed in this paper, which utilizes CNN feature of scene images to generate scene category features to classify scenes by a novel feature matching algorithm. The novel feature matching algorithm can further improve the speed of scene classification. In addition, overfitting is eliminated by our method even though the training data is limited. The presented method was evaluated on two benchmark scene datasets, Scene 15 dataset and MIT 67 dataset, acquiring 96.49% and 81.69% accuracy, respectively. The experiment results showed that our method was superior to other scene classification methods in terms of accuracy, speed, and robustness. To further evaluate our method, test experiments on unknown scene images from SUN 397 dataset had been done, and the models based on different training datasets obtained 94.34% and 79.80% test accuracy severally, which proved that the proposed method owned good performance in indoor scene classification.