Scale Invariant Feature Transform Research Articles

Distinguishable keypoint detection and matching for optical satellite images with deep convolutional neural networks

As a required step in optical remote sensing applications, image matching identifies correspondences to estimate the relationship between two images. To address this task, feature-based algorithms, such as Scale-Invariant Feature Transform (SIFT), use detectors to identify keypoints and then apply descriptors to represent these keypoints as feature vectors. Thereby, these vectors from different images are matched by Euclidean distance to produce matching points as correspondences. Deep learning networks are widely used in the design of detectors and descriptors due to their powerful representation capabilities. However, previous methods oriented to repeatability tend to be of low localization accuracy. To solve this problem, we define optimal keypoints as “detected, repeatable, reasonable, and distinguishable” (DRRD). Based on this idea, we introduce a DRRD framework for remote sensing optical image matching. Specifically, we designed a deep-learning-based descriptor network which is trained in a self-supervised manner with a novel adaptive mix content triplet (AMCT) loss function. We established a training procedure for remote sensing images using a multi-spectral image dataset. The proposed method obtained 1694 correct correspondences from 8192 detected keypoints in multi-temporal image matching tasks and a sub-pixel accuracy in the image rectification experiments. Comparison experiments show that the proposed DRRD framework outperforms other state-of-the-art methods.

Robust descriptor for key-point detection and matching in color images with radial distortion

Constructing descriptors for key points in image matching is a crucial task in computer vision, visual tracking, and pattern recognition. Highly rated descriptors such as scale-invariant feature transform (SIFT) and speeded up robust features (SURF) utilize the grayscale gradient information of the square regions around the key points. Nevertheless, these famous descriptors fail to take advantage of the image color information. Furthermore, their performances will be severely degraded for distorted images and the error due to rotation of their square windows. To address the problems, we proposed Circular Coordinate Combining Shape–Color Descriptor Under Distortion Based SURF (CSCD-SURF) that achieves competitive performance for colorful images with distortion contamination and numerical similar structures. The proposed approach can generate scale-space by adaptive filter to rectify distortion and integrate the SURF descriptor and shape–color information into our own custom concentric circular coordinate with flying colors. Experiments with Institut National de Recherche en Infomatique et Automatique dataset and spherical radial distortion-SIFT distorted image datasets prove that the ability of distortion rectification as well as matching performance against rotation, scaling, viewpoints, and blurring is more competitive than the state-of-the-art methods and its computation cost is acceptable.

Human ear identification system using shape and structural features based on SIFT and ANN classifier

People have become more interested in biometrics recognition as technology has advanced. Biometrics is the study of automatic systems for distinguishing people related to physical or behavioural features. Methods for finding favourable biometric traits have acquired more attention in recent years. The ear is among the most consistent biometric traits because it does not alter with aging or emotion. The human ear is an excellent source of data for passive personal authentication. The ear looks to be an excellent potential solution because it is accessible, images are easily obtained, and the ear structure doesn't change over the years. The ear meets a biometric criterion (universality, distinctiveness, durability, and collectability). The biometric field is working hard to develop automated individual identification using ear images. Several face recognition approaches fail in this present COVID-19 outbreak due to the mask-wearing situation. The human ear is attractive data for passive personal authentication because it does not need the individual's involvement to recognize the ear. In this research, we suggested an automatic ear identification system using Scale Invariant Feature Transform (SIFT) and an Artificial Neural Network (ANN).

Copy-move image forgery detection based on evolving circular domains coverage

The aim of this paper is to improve the accuracy of copy-move forgery detection (CMFD) in image forensics by proposing a novel scheme and the main contribution is evolving circular domains coverage (ECDC) algorithm. The proposed scheme integrates both block-based and keypoint-based forgery detection methods. Firstly, the speed-up robust feature (SURF) in log-polar space and the scale invariant feature transform (SIFT) are extracted from an entire image. Secondly, generalized 2 nearest neighbor (g2NN) is employed to get massive matched pairs. Then, random sample consensus (RANSAC) algorithm is employed to filter out mismatched pairs, thus allowing rough localization of counterfeit areas. To present these forgery areas more accurately, we propose the efficient and accurate ECDC algorithm to present them. This algorithm can find satisfactory threshold areas by extracting block features from jointly evolving circular domains, which are centered on matched pairs. Finally, morphological operation is applied to refine the detected forgery areas. Experimental results indicate that the proposed CMFD scheme can achieve better detection performance under various attacks compared with other state-of-the-art CMFD schemes.

Deep Learning-Based MR Imaging for Analysis of Relation between Cerebrospinal Fluid Variation and Communicating Hydrocephalus after Decompressive Craniectomy for Craniocerebral Injury

The aim of this study was to analyze the relationship between cerebrospinal fluid variation and hydrocephalus through deep learning-based (DL-based) magnetic resonance imaging (MRI), in order to improve the postoperative recovery of craniocerebral injury (CI) patients and reduce the deterioration after decompressive craniectomy of the patient. 50 patients with CI who received the diagnosis and treatment at the hospital were chosen as the subjects. The retrospective analysis on patients with CI was conducted herein. First, the general clinical data of the patients were analyzed. Next, the MRI images for brain damage of the patients were collected. After that, the DL-based brain image classification and the artificial intelligence technology were utilized to solve the classification problems with classifiers. Finally, the DL-based convolutional neural network (CNN) was adopted to preprocess the image features, and the offline training and online reconstruction were conducted after the construction of the model. Four groups of databases were selected for deep learning and analyzed in terms of data feature analysis, principal component analysis (PCA), and application of 3D scale-invariant feature transformation (SIFT) operators in image data analysis. The results manifested that, the WHGO descriptor and the area under the curve were the largest. SIFI, PCA, and WHGO had the sensitivity of 87.5%, 88.2%, and 90.1%, the specificity of 91.8%, 90.1%, and 94.2%, and the correct rate of 90.6%, 87.5%, and 92.4%, respectively. The volume content of the cerebrospinal fluid in the subarachnoid space was 77.04% higher than that of cerebrospinal fluid in the ventricle. In conclusion, the intelligent deep learning model proposed in this article was able to assume the measurement of clinical cases and auxiliary diagnosis. This model not only can help doctors save the diagnosis time and enhance the medical efficiency, but also can precisely identify the patient’s lesion area. Therefore, it had substantial application potential in mobile-based clinical practice.

Diagnosis of Pulmonary Nodules on CT Images Using YOLOv4

In this paper, the Scale-Invariant Feature Transform (SIFT) and Fast Library for Approximate Nearest Neighbors (FLANN) based algorithm is used to detect the abnormalities in the National Lung Screening Trial (NLST) CT scans as the exact clinical nodule locations are not provided in the dataset. These identified nodules on NLST CT Scans are then annotated using LabelImg tool. This process consumes time and so furthermore, the automatic nodule detection, You Only Look Once version 4 (YOLOv4) object detection model is implemented. The YOLOv4 object detection model is provided with total of 4187 labelled images in form of training (70%), validation (20%), and test (10%) datasets. Our YOLOv4 model achieves precision of 95%, sensitivity of 81% and mean Average Precision (mAP) of 89.1%.

Face Recognition and Gender Detection Using SIFT Feature Extraction, LBPH, and SVM

Face recognition and name and gender identification are challenging processes, especially when identifying perpetrators and suspects or when used in authentication systems. Machine learning and computer vision technologies are used in many fields, including security, and play an important role in face recognition and gender detection, offering valuable information to officials to rectify a situation in less time. This study used a few machine learning methods in the Labelled Faces in the Wild (LFW) database to examine their facial recognition and gender detection capacities. The LFW dataset was used to train and evaluate the Scale Invariant Feature Transform (SIFT) feature extraction method along with the Support Vector Machine (SVM) classifier and the Local Binary Pattern Histogram (LBPH) method. The result comparison from the current and other studies showed that the proposed LBPH method had higher accuracy in face recognition, while its accuracy in gender detection was very close to the ones of other, relevant studies.

Coverless Video Steganography Based on Audio and Frame Features

The coverless steganography based on video has become a research hot spot recently. However, the existing schemes usually hide secret information based on the single-frame feature of video and do not take advantage of other rich features. In this work, we propose a novel coverless steganography, which makes full use of the audio and frame image features of the video. First, three features are extracted to obtain hash bit sequences, which include DWT (discrete wavelet transform) coefficients and short-term energy of audio and the SIFT (scale-invariant feature transformation) feature of frame images. Then, we build a retrieval database according to the relationship between the generated bit sequences and three features of the corresponding videos. The sender divides the secret information into segments and sends the corresponding retrieval information and carrier videos to the receiver. The receiver can use the retrieval information to recover the secret information from the carrier videos correspondingly. The experimental results show that the proposed method can achieve larger capacity, less time cost, higher hiding success rate, and stronger robustness compared with the existing coverless steganography schemes based on the video.

Method of optimization of the fundamental matrix by technique speeded up robust features application of different stress images

<span>The purpose of determining the fundamental matrix (F) is to define the epipolar geometry and to relate two 2D images of the same scene or video series to find the 3D scenes. The problem we address in this work is the estimation of the localization error and the processing time. We start by comparing the following feature extraction techniques: Harris, features from accelerated segment test (FAST), scale invariant feature transform (SIFT) and speed-up robust features (SURF) with respect to the number of detected points and correct matches by different changes in images. Then, we merged the best chosen by the objective function, which groups the descriptors by different regions in order to calculate ‘F’. Then, we applied the standardized eight-point algorithm which also automatically eliminates the outliers to find the optimal solution ‘F’. The test of our optimization approach is applied on the real images with different scene variations. Our simulation results provided good results in terms of accuracy and the computation time of ‘F’ does not exceed 900 ms, as well as the projection error of maximum 1 pixel, regardless of the modification.</span>

Methods of local features extraction in person authentication task by face thermographic image

The paper presents a methods of image local features extraction research in relation to people authentication problem by face thermogram. As a part of the study, there were formed two datasets for methods training and testing: photographic images and face images in the long-wavelength infrared specter (LWIR) with various factors. The novelty of this study is due to the approach to collecting datasets to verify the accuracy of authentication methods. The dataset was collected with more realistic conditions that affect the quality of authentication, such as changing facial expressions, wearing glasses, medical masks, applying make-up/cosmetics, changing the lighting and temperature conditions of the environment, rotating the head. The methods core is based on the idea of constructing a vector of image features while reducing the dimension and highlighting the boundaries. Likewise, the methods of this group cope well with extracting features task on images and are widely used in the tasks of authentication by 2D face image, as well as in other computer vision tasks. In this paper, four classical methods of local feature extraction are considered: the method of locally binary templates, Gabor wavelets, scale-invariant feature transformation, and Weber’s local descriptor. The classifiers for the feature vectors comparison in this research are SVM and the simplest Perceptron — the basic methods of machine learning. As part of the study, a comparative analysis of each method was carried out in relation to the collected datasets. The methods were trained and tested on a collected face dataset of over 632,000 images of 152 people. As a result of the comparative analysis, it can be concluded that the method of local binary features demonstrates the best result among the considered methods for both types of data: for face thermograms (for SVM — 0,57, for Perceptron — 0,58), for photographic images (for SVM — 0,71, for Perceptron — 0,73). Furthermore, the SIFT method showed similar results: for face thermograms (for SVM — 0,58, for Perceptron — 0,55), for photographic images (for SVM — 0,72, for Perceptron — 0,74). Gabor filters and Weber local descriptor application demonstrate a low accuracy rate in the authentication task by both types of data. The results of the work can be used in access control and management systems to increase the fault tolerance of person authentication. The appliance of the considered methods are effective in the tasks such as processing thermograms for authentication a person by so-called “secondary” signs, for example, by the veins and vessels on face patterns, in cases of facial expressions and appearance changes.

Penerapan Euclidean Distance untuk Deteksi Kemiripan Citra Berbasis Scale Invariant Feature Transform (SIFT)

The similarity of a pair of images can be measured using the distance measurement method from the feature extraction. The feature extraction method used in this research was the Scale Invariant Feature Transform (SIFT). This method is an extraction method that is invariant to changes in scale, rotation, translation and illumination. In this research, each keypoint of test image is matched for its level of similarity with the Euclidean distance method. The similarity of each keypoint of the tested image is matched by Euclidean distance and it will be claimed similar if it has the smallest distance. Next, the corresponding keypoint of the tested image gets recall test by varying parameters of transformation in size, rotation, color, and angle as well as different image. The research results demonstrated that the recall averages of dataset were 100 for similar image test, 95 for size and rotation changes tests, 98 for colour changes test, 97 for angle changes test, and 0 for image test with different objects. Based on the results, SIFT is suitable for detecting the similarity of image object shapes.

Evaluation of a Vein Biometric Recognition System on an Ordinary Smartphone

Nowadays, biometrics based on vein patterns as a trait is a promising technique. Vein patterns satisfy universality, distinctiveness, permanence, performance, and protection against circumvention. However, collectability and acceptability are not completely satisfied. These two properties are directly related to acquisition methods. The acquisition of vein images is usually based on the absorption of near-infrared (NIR) light by the hemoglobin inside the veins, which is higher than in the surrounding tissues. Typically, specific devices are designed to improve the quality of the vein images. However, such devices increase collectability costs and reduce acceptability. This paper focuses on using commercial smartphones with ordinary cameras as potential devices to improve collectability and acceptability. In particular, we use smartphone applications (apps), mainly employed for medical purposes, to acquire images with the smartphone camera and improve the contrast of superficial veins, as if using infrared LEDs. A recognition system has been developed that employs the free IRVeinViewer App to acquire images from wrists and dorsal hands and a feature extraction algorithm based on SIFT (scale-invariant feature transform) with adequate pre- and post-processing stages. The recognition performance has been evaluated with a database composed of 1000 vein images associated to five samples from 20 wrists and 20 dorsal hands, acquired at different times of day, from people of different ages and genders, under five different environmental conditions: day outdoor, indoor with natural light, indoor with natural light and dark homogeneous background, indoor with artificial light, and darkness. The variability of the images acquired in different sessions and under different ambient conditions has a large influence on the recognition rates, such that our results are similar to other systems from the literature that employ specific smartphones and additional light sources. Since reported quality assessment algorithms do not help to reject poorly acquired images, we have evaluated a solution at enrollment and matching that acquires several images subsequently, computes their similarity, and accepts only the samples whose similarity is greater than a threshold. This improves the recognition, and it is practical since our implemented system in Android works in real-time and the usability of the acquisition app is high.

An Accelerated and Flexible SIFT Parallel-Computing Approach Based on the General Multi-Core Platform

Visual retrieval has been a significant technology in the computer vision task. Visual feature descriptors are the key to the visual retrieval. The famous local feature descriptor is called the Scale Invariant Feature Transform (SIFT), which can keep invariant mapping for the scale, rotate and simulate images. To utilize effectively the SIFT feature descriptor for visual matching on different hardware platforms, this paper proposes an accelerated SIFT algorithm based on the SIFT feature computing principle of the general multi-core platform. First, our multi-core task allocation method introduces the WFM theory into task assignment for each core to improve the core computing resource utilization for high-efficient parallel computing. Then, to improve the efficiency of picture matching, we introduce global geometric constraints condition to optimal picture matching for the multi-core parallelization approach. Experimental results show that the proposed approach can save on average 87.31% on the Intel X86 platform, compared to the single-core time. Also, our approach can save on average 33.79% on the Raspberry Pi platform, compared to the single-core time.

Human identification using finger knuckle features

Abstract Many studies refer that the figure knuckle comprises unique features. Therefore, it can be utilized in a biometric system to distinguishing between the peoples. In this paper, a combined global and local features technique has been proposed based on two descriptors, namely: Chebyshev Fourier moments (CHFMs) and Scale Invariant Feature Transform (SIFT) descriptors. The CHFMs descriptor is used to gaining the global features, while the scale invariant feature transform descriptor is utilized to extract local features. Each one of these descriptors has its advantages; therefore, combining them together leads to produce distinct features. Many experiments have been carried out using IIT-Delhi knuckle database to assess the accuracy of the proposed approach. The analysis of the results of these extensive experiments implies that the suggested technique has gained 98% accuracy rate. Furthermore, the robustness against the noise has been evaluated. The results of these experiments lead to concluding that the proposed technique is robust against the noise variation. Keywords: finger knuckle, biometric system, Chebyshev Fourier moments, scale invariant feature transform, IIT-Delhi knuckle database.

SIFT and SURF features based classification of yoga hand mudras using machine learning techniques

Yoga is an unique spiritual discipline of self-development and self-realization that teaches us how to live our lives to the fullest. Yoga's integrative approach brings deep harmony and unwavering balance to body and mind to awaken our dormant capacity for higher consciousness, which is the true purpose of human evolution. The numerous documented physical and mental benefits of yoga have played a large part in the interest in yoga. Due to a lack of datasets and thus the necessity to identify mudra in real time, distinguishing yoga hand mudras seems to be a tough undertaking. The yoga hand mudras are used as input in the proposed study, and the two components Scale Invariant Feature Transform (SIFT) and Speeded Up Robust Features (SURF) are extracted, followed by classification utilising machine learning techniques including Support Vector Machine (SVM) and Random Forest. By comparing the experimental results the performance of SIFT with SVM yields better results.

The Recognition of Microscopic Images of Ceramics Incorporating Blockchain Technology

Having summarized the previous research on ceramic identification and the anti-counterfeiting, the authors propose a ceramic identification system that combines computer vision algorithms with blockchain technology. The system uses irregular pores on microscopic images of ceramic surfaces as image features, and it applies the SIFT(Scale-invariant feature transform) algorithm to extract feature. The images and feature vector sets are then stored by IPFS(Inter-planetary File System). When a consumer needs to authenticate a ceramic product, it is only necessary to take a microscopic image of the specified location, and then the SIFT algorithm will compare the picture with the data stored in the IPFS network, and was previously obtained through the records on a blockchain network, the matching result then determines whether the photographed ceramic is one of those already recorded. Experimental show that the matching results can be used as a strong basis for identifying the origin of ceramic products.

Feature Set for Classification of Man-Made Underwater Objects in Optical and SAS Data

This paper proposes a feature characterization method that can discriminate between man-made and natural objects on the seabed using a pair of SAS and optical images. Feature matching methods, like scale-invariant feature transform (SIFT), usually utilize gradient information to detect feature points, whereas contour-based features often use geometrical descriptors such as roughness, circularity, and solidity. However, due to the different characteristics of sonar and optical imagery, current descriptors cannot be directly applied over sonar-optical image pairs. The clarity of the water (muddy water, concentration of particles that scatter light) for optical images, and the stability of the platform, and reflections from seabed for SAS images are important parameters that distort the two images and make it hard to match between the two image sources. This paper proposes a feature characterization method that can identify man-made objects in underwater optic-SAS image pairs. Two new contour-based feature descriptors are introduced. The first is the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">entropy angle feature</i> , which aims to reflect the entropy of the angles that originate from points on the contour. The second feature is <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">local curve fitting</i> , which characterizes the radial-polar space of the local curve polynomial fitting. The descriptors are designed to characterize man-made objects whose contour is expected to be smoother than natural objects such as rocks. Experimental results on a real, large dataset comprised of 1,519 optic-SAS image pairs, are shown to verify that the proposed method has a high level of classification accuracy and good discrimination between man-made and natural objects.

PLANER OBJECT DETECTION USING SURF AND SIFT METHOD

Object Detection refers to the capability of computer and software to locate objects in an image/scene and identify each object. Object detection is a computer vision technique works to identify and locate objects within an image or video. In this study, we compare and analyze Scale-invariant feature transform (SIFT) and speeded up robust features (SURF) and propose a various geometric transformation. To increase the accuracy, the proposed system firstly performs the separation of the image by reducing the pixel size, using the Scale-invariant feature transform (SIFT). Then the key points are picked around feature description regions. After that we perform one more geometric transformation which is rotation, and is used to improve visual appearance of image. By using this, we perform Speeded Up Robust Features (SURF) feature which highlights the high pixel value of the image. After that we compare two different images and by comparing all features of that object from image, the desired object detected in a scene.

Fast and Reliable Vision-Based Navigation for Real Time Kinematic Applications

Abstract: Automatic Image Matching (AIM) is the term used to identify the automatic detection of corresponding points located on the overlapping areas of multiple images. AIM is extensively used with Mobile Mapping System (MMS) for different engineering applications, such as highway infrastructure mapping, monitoring of road surface quality and markings, telecommunication, emergency response, and collecting data for Geographical Information Systems (GIS). Robotics community and Simultaneous Localization And Mapping (SLAM) based applications are other important areas that require fact and welldistributed AIM for robust vision navigation solutions. Different robust feature detection methods are commonly used for AIM, such as Scale Invariant Feature Transform (SIFT), Principal Component Analysis (PCA)–SIFT and Speeded Up Robust Features (SURF). The performance of such techniques have been widely investigated and compared, showing high capability to provide reliable and precise results. However, these techniques are still limited to be used for real and nearly real time SLAM based applications, such as intelligent Robots and low-cost Unmanned Aircraft Vehicles (UAV) based on vision navigation. The main limitations of these AIM techniques are represented in the relatively long processing time and the random distribution of matched points over the common area between images. This paper works on overcoming these two limitations, providing extremely fast AIM with well- distributed common points for robust real time vision navigation. Digital image pyramid, Epipolar line and 2D transformation have been utilized for limiting the size of search windows significantly and determining the rotating angle and scale level of features, reducing the overall processing time considerably. Using limited number of well-distributed common points has also helped to speed up the automatic matching besides providing robust vision navigation solution. The idea has been tested with terrestrial MMS images, and surveying UAV aerial images. The results reflect the high capability of the followed technique in providing fast and robust AIM for real-time SLAM based applications. Keywords: Automatic Image Matching, Epipolar Line, Image Pyramid, SLAM, Vision Navigation, Real Time, Vision Navigation.

Long-Periodic Analysis of Boresight Misalignment of Ziyuan3-01 Three-Line Camera

The Ziyuan3-01 (ZY3-01) satellite is China’s first civilian stereo surveying and mapping satellite to meet the 1:50,000 scale mapping requirements, and has been operated in orbit for 10 years. The boresight misalignment of the three-line camera (TLC) is an essential factor affecting the geolocation accuracy, which is a principal concern for stereo mapping satellites. However, the relative relationships of TLC are often regarded as fixed for the same ground scene in most traditional geometric calibrations, without considering the on-orbit long-periodic changes. In this paper, we propose a long-periodic method to analyze and estimate the boresight misalignments between three cameras, with the attitude estimation of a nadir (NAD) camera as the benchmark. Offsets and drifts of the three cameras were calculated and calibrated with different compensation models using scale invariant feature transform (SIFT) points as the ground control. Ten simultaneous NAD–Forward (FWD)–Backward (BWD) imagery of the ZY3-01 satellite acquired from 2012 to 2020 were selected to verify the long-periodic changes in TLC boresight misalignments. The results indicate that the boresight alignment angles of ZY3-01 TLC are dynamic during the long-periodic flight, but the structure of TLC is stable for the misalignments of both FWD and BWD within only 7 arc seconds, which can provide a positive reference for subsequent satellite design and long-periodic on-orbit geometric calibration.