Scale Invariant Feature Transform Image Research Articles

Advanced framework for epilepsy detection through image-based EEG signal analysis.

Recurrent and unpredictable seizures characterize epilepsy, a neurological disorder affecting millions worldwide. Epilepsy diagnosis is crucial for timely treatment and better outcomes. Electroencephalography (EEG) time-series data analysis is essential for epilepsy diagnosis and surveillance. Complex signal processing methods used in traditional EEG analysis are computationally demanding and difficult to generalize across patients. Researchers are using machine learning to improve epilepsy detection, particularly visual feature extraction from EEG time-series data. This study examines the application of a Gramian Angular Summation Field (GASF) approach for the analysis of EEG signals. Additionally, it explores the utilization of image features, specifically the Scale-Invariant Feature Transform (SIFT) and Oriented FAST and Rotated BRIEF (ORB) techniques, for the purpose of epilepsy detection in EEG data. The proposed methodology encompasses the transformation of EEG signals into images based on GASF, followed by the extraction of features utilizing SIFT and ORB techniques, and ultimately, the selection of relevant features. A state-of-the-art machine learning classifier is employed to classify GASF images into two categories: normal EEG patterns and focal EEG patterns. Bern-Barcelona EEG recordings were used to test the proposed method. This method classifies EEG signals with 96% accuracy using SIFT features and 94% using ORB features. The Random Forest (RF) classifier surpasses state-of-the-art approaches in precision, recall, F1-score, specificity, and Area Under Curve (AUC). The Receiver Operating Characteristic (ROC) curve shows that Random Forest outperforms Support Vector Machine (SVM) and k-Nearest Neighbors (k-NN) classifiers. The suggested method has many advantages over time-series EEG data analysis and machine learning classifiers used in epilepsy detection studies. A novel image-based preprocessing pipeline using GASF for robust image synthesis and SIFT and ORB for feature extraction is presented here. The study found that the suggested method can accurately discriminate between normal and focal EEG signals, improving patient outcomes through early and accurate epilepsy diagnosis.

Terahertz data analytics-based bonding interface damage characterization in a multilayer structural composites under cyclic loading

Adhesively-bonded composite structures are under various environmental loads during their service life. Therefore, it is imperative to monitor the evolution of the bonding interfaces under loading to evaluate the bonding properties of the composite structures. A terahertz (THz) quantitative characterization method is proposed based on the scale invariant feature transform (SIFT) image matching algorithm. The terahertz data for the bonding interface before and after loading were obtained using a terahertz time-domain spectroscopy system along with the flight time imaging of the bonding interface. The imaging results of the bonding interface before and after loading were matched by SIFT image processing technology, and the THz flight time difference was obtained using differential calculations to characterize the thickness change of the bonding interface. Furthermore, the initiation and development of interface damage were studied, and the changes in the bonding interface thickness and debonding damage state under the cyclic loading tests were analyzed, providing information on the growth of the damaged area and damage severity. The results show that the proposed method can ultimately realize the characterization of the thickness changes and the evolution of the debonding damages at the interface of the bonded composite structures under cyclic stress, thus circumventing the shortcomings of the conventional damage-evolution characterization methods. The findings can also provide helpful insights into the effect of stress load on the bonding interface damage evolution for the studied system.

Super-Pixel Guided Low-Light Images Enhancement with Features Restoration.

Dealing with low-light images is a challenging problem in the image processing field. A mature low-light enhancement technology will not only be conductive to human visual perception but also lay a solid foundation for the subsequent high-level tasks, such as target detection and image classification. In order to balance the visual effect of the image and the contribution of the subsequent task, this paper proposes utilizing shallow Convolutional Neural Networks (CNNs) as the priori image processing to restore the necessary image feature information, which is followed by super-pixel image segmentation to obtain image regions with similar colors and brightness and, finally, the Attentive Neural Processes (ANPs) network to find its local enhancement function on each super-pixel to further restore features and details. Through extensive experiments on the synthesized low-light image and the real low-light image, the experimental results of our algorithm reach 23.402, 0.920, and 2.2490 for Peak Signal to Noise Ratio (PSNR), Structural Similarity (SSIM), and Natural Image Quality Evaluator (NIQE), respectively. As demonstrated by the experiments on image Scale-Invariant Feature Transform (SIFT) feature detection and subsequent target detection, the results of our approach achieve excellent results in visual effect and image features.

Motor Fault Diagnosis Using Image Visual Information and Bag of Words Model

In order to solve the tough issue that is difficult to extract the representative fault features of the hybrid vibration signals from the various industrial applications, a motor fault diagnosis method based on image visual information and bag of words model (BoW) are proposed in this paper. Based on the redundancy information of raw signals, the mapping which is between the original fault signal and the visual information is obtained by the methods of SDP (Symmetrized Dot Pattern) image and dense SIFT (Scale Invariant Feature Transform) features. The bag of visual word (BoVW) and pyramid histogram intersection kernel support vector machine (PHIK-SVM) are applying to complete the fault diagnosis and state recognition of related motors. The test results reveal that the diagnostic accuracy of four fault states could reach 99.50%, moreover, the diagnostic accuracy of different operating conditions under each fault could reach 91.83% as well. Compared with the traditional methods, the proposed method is able to obtain the detailed characteristics of various motors from the perspective of visual knowledge, furthermore, it is more robust and without complex data processing.

SIFT Image Feature Extraction for an Efficient Image Registration

This paper presents an image registration algorithm based on SIFT (Scale Invariant Feature Transform).The obtained descriptors and key points by the SIFT confirms that, the algorithm is very robust to scaling, noise, translation and rotation. At the beginning, the key points are extracted from the image. Later to Match the obtained points, dot products between the unit vectors are calculated. Finally, transformation matrix is obtained by applying RANSAC algorithm. Experimental results shows that the algorithm extracts the better key points, which can be used for used for image registration applications.

Group enhancement for matching of multi-view image with overlap fuzzy feature

When an object is affected by illumination and noise, traditional methods of image feature group enhancement are mismatched and the accuracy of feature group enhancement is poor. Therefore, a feature group enhancement method for three-dimensional images with overlap fuzzy based on Scale-invariant feature transform (SIFT) algorithm is proposed. Firstly, the scale space of multi-view images is constructed. Next, extreme points are detected and screened to determine the main direction of key points. An image SIFT that is used to describe a sub-feature vector to prevent noise and edge response is generated. Then, overlap fuzzy features of multi-view image are internally and externally normalized. Features are highlighted and the effects of illumination are eliminated by measuring the similarity. Finally, different weights are given to overlap fuzzy features of multi-view images to achieve matching and feature group enhancement. Experimental results show that the proposed method achieves the matching and feature group enhancement process under different illumination conditions and noise environment. Furthermore, the proposed method improves feature group enhancement efficiency and feature group enhancement accuracy.

An efficient content based image retrieval system using BayesNet and K-NN

In the progression of web and multi-media, substantial measure of pictures is created and appropriated, to viably store and offer such vast measure of bulky database is a big issue. In this way, Content Based Image Retrieval (CBIR) techniques are used to retrieve images from the massive database based on the desired information. In this proposed work, we are considering two local image feature extraction methods, namely, SIFT and ORB. Scale Invariant Feature Transform (SIFT) is used for detecting features and feature descriptor of an image. Oriented Fast Rotated and BRIEF (ORB) uses FAST (Features from Accelerated Segment Test) key point detector and binary BRIEF (Binary Robust Independent Elementary Features) descriptor of an image. K-Means clustering algorithm is also used in the present paper for analyzing the data, which generates number of clusters using the descriptor vector. Locality Preserving Projection (LPP) is employed to reduce the length of the feature vector to enhance the performance of image retrieval system. For classification, we have considered two classifiers, namely, BayesNet and K-Nearest Neighbours (K-NN). Wang image dataset has been used for experimentation work. We have accomplished the highest precision rate of 88.9% using proposed CBIR system.

FPGA-Based Hardware Design for Scale-Invariant Feature Transform

This paper proposes a novel hardware design method of scale-invariant feature transform (SIFT) algorithm for implementation on field-programmable gate array (FPGA). To reduce the computing costs, Gaussian kernels are calculated offline for use in Gaussian filters. To eliminate low-contrast points, the inverse of a Hessian matrix is required for hardware implementation, which results in poor performance because dividers are needed. To solve this problem, this paper presents a new mathematical derivation model to implement the low-contrast detection, avoiding the use of any dividers. For the implementation of the normalization module, a large number of dividers are required by traditional methods, which adversely affects the computational efficiency. This paper presents a new architecture using only one divider to implement the normalization function in hardware. Thanks to the parallel processing architecture proposed to design the image pyramid, SIFT detection, and SIFT descriptor, the computational efficiency of the SIFT algorithm is significantly improved. As a result of the proposed design method, the requirement of logic elements in the FPGA hardware is greatly reduced and system frequency is significantly increased. Experimental results show that the proposed hardware architecture outperforms existing techniques in terms of resource usage and computational efficiency for real-time image processing.

An Automatic Measurement Method for Absolute Depth of Objects in Two Monocular Images Based on SIFT Feature

Recovering depth information of objects from two-dimensional images is one of the very important and basic problems in the field of computer vision. In view of the shortcomings of existing methods of depth estimation, a novel approach based on SIFT (the Scale Invariant Feature Transform) is presented in this paper. The approach can estimate the depths of objects in two images which are captured by an un-calibrated ordinary monocular camera. In this approach, above all, the first image is captured. All of the camera parameters remain unchanged, and the second image is acquired after moving the camera a distance d along the optical axis. Then image segmentation and SIFT feature extraction are implemented on the two images separately, and objects in the images are matched. Lastly, an object’s depth can be computed by the lengths of a pair of straight line segments. In order to ensure that the most appropriate pair of straight line segments are chosen, and also reduce computation, convex hull theory and knowledge of triangle similarity are employed. The experimental results show our approach is effective and practical.

On-Road Car Detection System Research for Corsswalk Safety of the Blind

본 연구에서는 시각장애인의 보행안정성 향상을 위해 도로 위를 이동하는 자동차의 영상만을 입력 받아 자동차를 검출하는 방법을 제안한다. 입력 영상은 제약 조건이 있다. 도로 위에서 아래 방향을 비스듬히 내려 보는 고정된 시야를 가져야한다는 점이다. 주어진 영상 중 도로 영역만을 이용하기 위해 동적인 관심영역을 검출해 적용한다. 동적으로 관심영역을 검출하기 위해 캐니엣지 탐지를 이용한 후 허프 변환을 응용해 분할 허프 변환 방법으로 구현하였다. 관심영역 내에서 차량 검출을 위해 모션 히스토리 이미지(Motion History Image) 추출 방법, SIFT(Scale-Invariant Feature Transform) 알고리즘, 히스토그램 분석 등 다양한 영상처리 방법을 적용한 실험결과, 평가 및 한계점을 서론에 제시했다. 이를 해결하기 위해서 GMM(Gaussian Mixture Model)을 응용해 단순한 물체 탐지가 아닌, 차량 검출에 최적화하는 방법을 제시한다. 본 연구에서는 GMM 알고리 즘을 응용한 차량 검출 GMM(Vehicle Detection-GMM) 알고리즘을 이용해 차량 검출 시스템을 구현했다. 실험 결과 정확률, 재현율, F1 측정값이 GMM은 각각 15%, 60%, 24%인데 비해 차량검출 GMM은 각각 75%, 60%, 67%로 그 성능을 입증할 수 있었다. 그 결과를 바탕으로 제안한 알고리즘이 기존의 알고리즘보다 우수함을 입증하였다.In this paper we propose car detection system using only video image as the input image that is composed of car moving on the road. It is for the people who is visually handicapped. There is a constraint condition that is the input image has downward obliquely from road and fixed view. To use only region of road, we use dynamic ROI detection using Canny edge detection and separated type hough transform based on Hough transform. To do car detection in ROI, we analyze and evaluate confines of motion history image(MHI) method, SIFT(Scale-Invariant Feature Transform) algorithm and histogram analysis in the introduction. These method has the critical point. So, we proposed to use VD-GMM(Vehicle Detection-GMM) based on GMM(Gaussian Mixture Model) for the car detection system. GMM is just moving object detection but including several geometric detection method, it could detect the car. In the experiment, we measure precision, recall and F1 rate for GMM and VD-GMM. GMM has 15%, 60%, 24% and VD-GMM has 75%, 60%, 67% for each value. Using this result, we could prove VD-GMM is better than GMM for the car detection in the conclusion.

차량검출 GMM 2.0을 적용한 도로 위의 차량 검출 시스템 구축

This paper presents a vehicle detection system using the video as a input image what has moving of vehicles.. Input image has constraints. it has to get fixed view and downward view obliquely from top of the road. Road detection is required to use only the road area in the input image. In introduction, we suggest the experiment result and the critical point of motion history image extraction method, SIFT(Scale_Invariant Feature Transform) algorithm and histogram analysis to detect vehicles. To solve these problem, we propose using applied Gaussian Mixture Model(GMM) that is the Vehicle Detection GMM(VDGMM). In addition, we optimize VDGMM to detect vehicles more and named VDGMM 2.0. In result of experiment, each precision, recall and F1 rate is 9%, 53%, 15% for GMM without road detection and 85%, 77%, 80% for VDGMM2.0 with road detection.

Improved SIFT image registration algorithm on characteristic statistical distributions and consistency constraint

In the process of SIFT (Scale Invariant Feature Transform) image registration algorithm; the principal orientation is affected by the dispersion of histogram. Besides; the feature descriptor section of conventional sift does not make full use of local feature information. As to these problems; an improved sift algorithm on characteristic statistical Distributions and consistency constraint will be presented in this paper. Firstly; DoG scale space feature point detection method is adopted to extract key points. Then; in the process of principal orientation generation; our method selects line with maximum dispersion. Furthermore; this method generates feature descriptor based on characteristic statistical Distributions in polar coordinate. Finally; a new matching method based on consistency constraint will be introduced. In experiments; we test the performances of our propose method. The experimental results demonstrate the feasibility and effectiveness of our approach.

A study on fast SIFT image mosaic algorithm based on compressed sensing and wavelet transform

Considering the disadvantages of massive calculation and slow speed of traditional Scale Invariant Feature Transform (SIFT) algorithm, we propose an improved image mosaic method which combines Wavelet Transform (WT) and Compressed Sensing (CS) algorithm. The method works as follows. Firstly, images are transformed with wavelet and compressed using compressed sensing technology. Then, image feature points are extracted in combination with SIFT algorithm. Finally, Sequential Similarity Detection Algorithm (SSDA) with adaptive threshold is used to fast search of image matching to find out an optimal stitching line, and a panoramic image is obtained. Experimental results demonstrate that the method realizes fast image matching, efficiently overcomes the shortcomings of heavy computation and low efficiency in the process of extracting image features, and guarantees matching accuracy and stitching efficiency, which meets the real-time requestments in machine vision system. This algorithm can be applied to image matching and stitching in the field of digital image security.

Entropy-Based and Weighted Selective SIFT Clustering as an Energy Aware Framework for Supervised Visual Recognition of Man-Made Structures

Using local invariant features has been proven by published literature to be powerful for image processing and pattern recognition tasks. However, in energy aware environments, these invariant features would not scale easily because of their computational requirements. Motivated to find an efficient building recognition algorithm based on scale invariant feature transform (SIFT) keypoints, we present in this paper uSee, a supervised learning framework which exploits the symmetrical and repetitive structural patterns in buildings to identify subsets of relevant clusters formed by these keypoints. Once an image is captured by a smart phone, uSee preprocesses it using variations in gradient angle- and entropy-based measures before extracting the building signature and comparing its representative SIFT keypoints against a repository of building images. Experimental results on 2 different databases confirm the effectiveness of uSee in delivering, at a greatly reduced computational cost, the high matching scores for building recognition that local descriptors can achieve. With only 14.3% of image SIFT keypoints, uSee exceeded prior literature results by achieving an accuracy of 99.1% on the Zurich Building Database with no manual rotation; thus saving significantly on the computational requirements of the task at hand.

Flow velocity measurement and analysis based on froth image SIFT features and Kalman filter for froth flotation

The flow velocity of flotation froth involves important information about the concentrate grade and the mineral recovery. It is significant to maintain the flow velocity of the froth at proper levels to achieve a good production performance in the machine vision-based process monitoring and control. However, the accurate velocity field measurement for the heavily deformed and seriously fragile froth bubbles is still a great challenge. Scale-invariant feature transform (SIFT) feature-based image matching provides an effective registration method for deformed objects, but most of the processing time would be wasted on the feature extraction and matching in irrelevant regions of the image pairs, which is unsuitable for online process monitoring. The Kalman filter is an effective tool to predict the next positions of the subblocks in the froth image sequences. Taking advantage of the merits of the SIFT and the Kalman filtering, an online froth velocity field measurement method based on the SIFT features and an improved Kalman filtering is presented in this paper. This method can obtain the accurate velocity field of various kinds of froth bubbles flowing to the scraper in the flotation cells, even including the bubbles with serious collapse and heavy deformation. The accuracy of the subblock registration is evaluated by a deformation model. After a long period of observation in a bauxite flotation plant, the relationship between the froth flow velocity and the production performance indices is analyzed and discussed. Finally, a kind of conclusive operation advice based on the relationship between the froth velocity and the flotation performance is established. The velocity measurement and the operation guidelines for the flotation operation and automatic control lay a foundation for the establishment of a flotation optimal control system based on machine vision monitoring.

Automatic Image Registration Through Image Segmentation and SIFT

Automatic image registration (AIR) is still a present challenge for the remote sensing community. Although a wide variety of AIR methods have been proposed in the last few years, there are several drawbacks which avoid their common use in practice. The recently proposed scale invariant feature transform (SIFT) approach has already revealed to be a powerful tool for the obtention of tie points in general image processing tasks, but it has a limited performance when directly applied to remote sensing images. In this paper, a new AIR method is proposed, based on the combination of image segmentation and SIFT, complemented by a robust procedure of outlier removal. This combination allows for an accurate obtention of tie points for a pair of remote sensing images, being a powerful scheme for AIR. Both synthetic and real data have been considered in this work for the evaluation of the proposed methodology, comprising medium and high spatial resolution images, and single-band, multispectral, and hyperspectral images. A set of measures which allow for an objective evaluation of the geometric correction process quality has been used. The proposed methodology allows for a fully automatic registration of pairs of remote sensing images, leading to a subpixel accuracy for the whole considered data set. Furthermore, it is able to account for differences in spectral content, rotation, scale, translation, different viewpoint, and change in illumination.