Search

Individual recognition of animals is an important aspect of ecological sciences. Photograph‐based individual recognition options are of particular importance since these represent a non‐invasive method to distinguish and identify individual animals. Recent developments and improvements in computer‐based approaches make possible a faster semi‐automated evaluation of large image databases than was previously possible. We tested the Scale Invariant Feature Transform (SIFT) algorithm, which extracts distinctive invariant features of images robust to illumination, rotation or scaling of images. We applied this algorithm to a dataset of 800 tail pattern images from 100 individual Eurasian beavers (Castor fiber) collected as part of the Norwegian Beaver Project (NBP). Images were taken using a single‐lens reflex camera and the pattern of scales on the tail, similar to a human fingerprint, was extracted using freely accessible image processing programs. The focus for individual recognition was not on the shape or the scarring of the tail, but purely on the individual scale pattern on the upper (dorsal) surface of the tail. The images were taken from two different heights above ground, and the largest possible area of the tail was extracted. The available data set was split in a ratio of 80% for training and 20% for testing. Overall, our study achieved an accuracy of 95.7%. We show that it is possible to distinguish individual beavers from their tail scale pattern images using the SIFT algorithm. [ABSTRACT FROM AUTHOR]

Facial Emotion Recognition (FER) is the approach of detecting emotions of humans from facial expressions. Emotions are detected automatically by the human brain and hence, many computer aided techniques are implemented for recognizing emotions. Recognition of natural emotions is an exciting area with a broad range of real time applications like automated tutoring models, smart environments computer–human interaction, driver warning systems, and video and image retrieval. The major goal of this paper is to implement an intelligent model for FER. The proposed model involves few steps: (a) Face extraction (b) Image filtering, (c) Extraction of facial components, (d) Descriptor selection, and (d) Classification. Initially, the face is extracted from the input image by the Viola–Jones method, which is generally employed for the detection of object. Further, the noise of the image is filtered by the Gabor Filtering. Further, the facial components are extracted as features via the Affine-Scale-Invariant Feature Transform (ASIFT), which is the modified version of SIFT method. Since the length of the descriptors generated from ASIFT is high; the number of descriptors is reduced by the optimal descriptor selection approach with the aid of hybrid meta-heuristic algorithm termed as MV-WOA. The extracted descriptors are subjected to Neural Network (NN). As a modification to the existing machine learning algorithms, the number of hidden neurons in the NN is optimized by the proposed WOA+MVO algorithm. By conducting experiments, the results demonstrate that the developed system can perform better the recent traditional approaches for emotion recognition for classifying seven emotions like normal, smile, sad, surprise, anger, fear, and disgust. [ABSTRACT FROM AUTHOR]

Abstract The thickness of the bonding interface changes after the structure has been subjected to tensile load, thereby affecting the strength of the bonding structure. It is necessary to monitor the evolution of the bonding interface thickness under tensile load. Through terahertz time-domain spectroscopy imaging and scale-invariant feature transform image processing, the thickness variation of three interfaces of 150 silicon-based adhesive structures under tensile load were analyzed. It was determined that variation at the edge was larger than that in the middle area. The research results also provide data support for the bonding structure health monitoring systems. [ABSTRACT FROM AUTHOR]

Automated accurate categorization of brain magnetic resonance images (MRI) is very important for disease diagnosis and treatment. In this paper, a new methodology for the detection of abnormality in brain MRI is suggested. The scale-invariant feature transform is first employed to extract features of MRI. Principal component analysis is applied to the extracted features and a minimal set of more essential features is obtained. Lastly, the obtained feature set is categorized as healthy or unhealthy using support vector machine (SVM)-based classification. The parameters of SVM, i.e. C and s are optimized using Gray Wolf Optimization. However external noise and patient/organ movement degrade the quality of MRI, which in turn affect the classification accuracy. Therefore, a hybrid of Savitzky-Golay smoothing filter and speckle reducing anisotropic diffusion filter is used for preprocessing of the source image, which efficiently reduces the noise while preserving edges of the image. It is revealed from the results that proposed technique provides a classification accuracy of 99.61%. Thus the suggested technique may effectively diagnose diseases using MRI. [ABSTRACT FROM AUTHOR]

This paper presents a new technique by support vector machines after extracting the prominent iris features using discrete wavelet transformations, to achieve an optimal classification of energy system disturbances. A framework for iris recognition and protection of the recognition system from fake iris scenes was proposed. The scale-invariant feature transform is set as an algorithm to extract local features (key points) from iris images and their classification method. To elicit the prominent iris features, the test image is first pre-processed. This will facilitate confining and segmenting the region of interest hopefully, reducing the blurring and artifacts, especially those associated with the edges. The textural features can be exploited to partition irises into regions of interest in addition to providing necessary information in the spatial distribution of intensity levels in an iris neighborhood. Next, the detection efficiency of the proposed method is achieved through extracting iris gradients and edges in complex areas and in different orientations. Further, the iris diagonal edges were easily detected after calculating the variance of different blocks in an iris and the additive noise variance in a textured image. The vertical, horizontal, and diagonal iris image gradients with different directions were successfully extracted. These gradients were extracted after adjusting the threshold amplitude obtained from the histograms of these gradients. The average calculations of MAVs, peak signal-tonoise ratios (PSNRs), and mean square errors (MSEs) within the orientation angles (-45°, +45° and 90°) for both vertical and horizontal iris gradients had occurred within the rates of 1.9455--3.1266, 36.388--39.863 dB and 0.0001--0.0026, respectively. [ABSTRACT FROM AUTHOR]

When using drone-based aerial images for panoramic image generation, the unstableness of the shooting angle often deteriorates the quality of the resulting image. To prevent these polluting effects from affecting the stitching process, this study proposes deep learning-based outlier rejection schemes that apply the architecture of the generative adversarial network (GAN) to reduce the falsely estimated hypothesis relating to a transform produced by a given baseline method, such as the random sample consensus method (RANSAC). To organize the training dataset, we obtain rigid transforms to resample the images via the operation of RANSAC for the correspondences produced by the scale-invariant feature transform descriptors. In the proposed method, the discriminator of GAN makes a pre-judgment of whether the estimated target hypothesis sample produced by RANSAC is true or false, and it recalls the generator to confirm the authenticity of the discriminator's inference by comparing the differences between the generated samples and the target sample. We have tested the proposed method for drone-based aerial images and some miscellaneous images. The proposed method has been shown to have relatively stable and good performances even in receiver-operated tough conditions. [ABSTRACT FROM AUTHOR]

[Display omitted] • An image feature based method to assess the quality of speckle patterns for DIC. • The indicator is sensitive to the difference between various speckle patterns. • The method provides guidelines for design of high-quality speckle patterns. A novel method is proposed to assess the quality of speckle patterns for deformation measurement using the digital image correlation (DIC) technique. Different from existing methods that focused on the characteristics of individual speckle or frequency of grayscale values, our approach explores the usage of the image features essential for image registration, which is the basis of DIC. An indicator called density and evenness of features (DEF) is defined, combining the distribution density and evenness of image features. Numerical and real experiments demonstrate that the DEF is sensitive to the quality of various speckle patterns. It can detect the subtle difference between good speckle images leading to small gap in measurement accuracy. The DEF can also provide reliable guidelines to design high-quality transferable speckle patterns, as it shows clear relation to the main controllable parameters in generation of speckle patterns, including speckle duty ratio, image contrast, speckle radius and its dispersion, as well as speckle edge sharpness. [ABSTRACT FROM AUTHOR]

Many stitching studies employ improved scale-invariant feature transform (SIFT) or speeded up robust features (SURFs) stitching algorithms, owing to their excellent robustness against variations in scale and rotations of input images. Traditional SIFT-based stitching algorithms suffer from the limitation of having insufficient feature points that can be extracted and matched from untextured and smooth objects, resulting in stitching failure. To overcome this issue, we propose a system that uses a proposed laser pattern projection (LASPP)-pasted texture technique before feature point extraction and description. The proposed system can extract and describe feature points based on SIFT feature extraction techniques. The progressive sample consistency (PROSAC) algorithm was used to remove false matching points and enhance the accuracy in matching feature points. The experimental results clearly revealed the effect of the pattern projected using LASPP on the stitching results. Furthermore, the efficiency of the proposed system, which employed the PROSAC algorithm, in matching feature points, was compared with that of the traditional system, which used the random sample consensus algorithm. Additionally, the stitching quality of the proposed system was compared with that of other SIFT- and SURF-based stitching systems. [ABSTRACT FROM AUTHOR]

Sign language recognition becomes a popular research field in human–computer interaction. Attention on hand signal analysis helps to make easy communication among computer and human for information sharing. Major focus of the gesture recognition system is to identify and recognise various gestures, by a computer. This study introduces optimisation of both classifier and feature set for static American sign language recognition. Initially, the hand part is segmented from other parts of the image through effective edge and skin colour detection. Thereafter, robust features are obtained using discrete cosine transform, Zernike moment, scale‐invariant feature transform, speeded‐up robust features, histogram of oriented gradients and binary object features from the segmented hand image. From these extracted features, an optimal feature set is selected by social ski driver optimisation algorithm. Deep Elman recurrent neural network classifier is then introduced for recognition purpose. Optimisation is performed on feature sets, derived by fusion of features obtained from the above methods, based on precision, accuracy, F‐measure and recall. Finally, optimised feature set and best classifier are used to recognise the hand gesture for classification purpose. The performance of this proposed method is evaluated and compared with existing literature. [ABSTRACT FROM AUTHOR]

Content‐based image retrieval (CBIR) uses primitive image features for retrieval of similarimages from a dataset. Generally, researchers extract these visual features fromthe whole image. Therefore, the extracted features contain overlappedinformation of texture, colour, and shape features, and it is a criticalchallenge in the field of CBIR. This problem can be overcome by extracting thecolour features from the colour as well as shape and texture features from theintensity dominant part only. In this study, the authors have proposed aniterative algorithm to separate colour and texture dominant part of the imageinto two different images. Here, a combination of edge maps and gradients hasbeen used to achieve separate colour and texture images. Further,scale‐invariant feature transform and 2D dual‐tree complex wavelet transform hasbeen realised to extract unique shape and texture features from the textureimage. Simultaneously, a probability‐based semantic centred annular histogramhas been suggested to extract unique colour features from the colour image.Finally, a novel weighted distance‐based feature comparison scheme has beenproposed for similarity matching and retrieval. All the image retrievalexperiments have been carried out on seven standard datasets and demonstratedsignificant improvements over other state‐of‐arts CBIR systems [ABSTRACT FROM AUTHOR]

Image forgery detection and localisation is one of the principal problems in digital forensics. Copy–paste forgery in digital images is a type of forgery in which an image region is copied and pasted at another location within the same image. In this work, the authors propose a methodology to detect and localise copy‐pasted regions in images based on scale‐invariant feature transform (SIFT). Existing copy‐paste forgery detection in images using SIFT and clustering techniques such as hierarchical agglomerative and density‐based spatial clustering of applications with noise resulted many false pixel detections. They have introduced sensitivity‐based clustering along with SIFT features to identify copy–pasted pixels and disregard the false pixels. Experimental evaluation on public image datasets MICC‐F220, MICC‐F2000 and MICC‐F8 multi shows that the proposed method is showing improved performance in detecting and localising copy‐paste forgeries in images than the existing works. Also the proposed work detects multiple copy–pasted regions in the images and is robust to attacks such as geometrical transformation of copied regions such as scaling and rotation. [ABSTRACT FROM AUTHOR]

Scale-invariant feature transform (SIFT), which represents a general purpose image descriptor, has been extensively used in the field of biometric recognition. Focusing on iris biometrics, numerous SIFT-based schemes have been presented in past years, offering an alternative approach to traditional iris recognition, which are designed to extract discriminative binary feature vectors based on an analysis of pre-processed iris textures. However, the majority of proposed SIFT-based systems fails to maintain the recognition accuracy provided by generic schemes. Moreover, traditional systems outperform SIFT-based approaches with respect to other key system factors, i.e. authentication speed and storage requirement. In this work, we propose a SIFT-based iris recognition system, which circumvents the drawbacks of previous proposals. Prerequisites, derived from an analysis of the nature of iris biometric data, are utilized to construct an improved SIFT-based baseline iris recognition scheme, which operates on normalized enhanced iris textures obtained from near-infrared iris images. Subsequently, different binarization techniques are introduced and combined to obtain binary SIFT-based feature vectors from detected keypoints and their descriptors. On the CASIAv1, CASIAv4-Interval and BioSecure iris database, the proposed scheme maintains the performance of different traditional systems in terms of recognition accuracy as well as authentication speed. In addition, we show that SIFT-based features complement those extracted by traditional schemes, such that a multi-algorithm fusion at score level yields a significant gain in recognition accuracy. [ABSTRACT FROM AUTHOR]

Scale-invariant feature transform (SIFT) is one of the widely used interest point features. It has been successfully applied in various computer vision algorithms like object detection, object tracking, robotic mapping, and large-scale image retrieval. Although SIFT descriptor is highly robust towards scale and rotation variations, the high computational complexity of the SIFT algorithm inhibits its use in applications demanding real-time response and in algorithms dealing with very large-scale databases. In order to be effective for image matching process in near real-time, the Compute Unified Device Architecture (CUDA) application programming interface of a graphics processing unit (GPU) is incorporated to speed up or improve the SIFT method. Experimental results show that the proposed GPU-based SIFT framework is suitable for image application in real time. It can improve the image matching process both in time and accuracy compared with conventional SIFT method. [ABSTRACT FROM AUTHOR]

Abstract Facial expression recognition (FER) plays an important role in the applications of human computer interaction. Given the wide use of convolutional neural networks (CNNs) in automatic video and image classification systems, higher-level features can be automatically learned from hierarchical neural networks with big data. However, learning CNNs require large amount of training data for adequate generalization, while the Scale-invariant feature transform (SIFT) does not need large training samples to generate useful feature. In this paper, we propose a new hybrid feature representation for the recognition of facial expressions from a single image frame that uses a combination of SIFT and deep-learning feature of different level extracted from the CNN model, then adopt the combined features and classify the expression by support vector machines (SVM). The performance of the proposed method has been validated on public CK+ databases. To evaluate the generalization ability of our method, we also performed an experiment on a cross-database environment. Experimental results show that the proposed approach can achieve better classification rates compared with state-of-art CNN methods, which indicate the considerable potential of combining shallow feature with deep-learning feature. [ABSTRACT FROM AUTHOR]

Infrared images acquired by forward-looking infrared camera have a limited field of view that is insufficient to monitor the entire scene with a single frame. To generate images containing the entire scene, infrared images can be assembled using image stitching. However, direct application of traditional image stitching methods has the disadvantage of long delays, large amounts of computation, and high memory storage. We present a real-time stitching method for infrared images. First, modified normalized cross correlation is introduced to find the overlapping area. Therefore, feature detection only needs to operate in overlapping areas. Also, scale-invariant feature transform is modified according to the properties of the infrared image. In addition, we implement the proposed method on an embedded system that is low cost, portable, and highly real-time. Our experimental results show the proposed method has almost the same quality of panorama compared with state-of-the-art methods, but the computation time is reduced significantly. [ABSTRACT FROM AUTHOR]

Visual big data is an essential and significant research topic, due to its diverse applications. In this paper, a new visual detection method for transportation is proposed based on probabilistic latent semantic analysis with visual data. We detect the distinctiveness by integrating three steps as follows: first, representing the co-ocurrence matrix of images, which were vectorized using the bag of visual words (BoVW) framework; then calculating the histograms of the visual words of each class; and finally applying the test images as the visual words. A multilayer perceptron (MLP) is used as the classification method in our system. The visual words are extracted by sampling the patches from the current image. A new topology of the neural network for the BoVW model is proposed, and management of the learning rate by reducing at specific iterations is exploited. The Probabilistic latent semantic analysis (PLSA) is compared to the MLP using the Caltech 256 datasets. The classes used include cars, motorbikes, and horses. The results of the experiment show that the MLP outperforms current methods in predicting transportation objects, and properly approximates the transportation detection function with extracted local features. It shows that the proposed method yields about 4.4% higher accuracy than the conventional PLSA for all classes. [ABSTRACT FROM AUTHOR]

This paper proposes an approach for the full-field surface reconstruction of three-dimensional (3-D) objects. The method uses a fringe projection profilometry system to obtain a 3-D point cloud with a multiview and proposes an objective function that involves all of the parameters of rotation and translation. The feature points of the surface of the object are extracted to determine the initial value of the objective function, which is then optimized to achieve accurate registration of the point clouds. The experimental results demonstrate that the proposed method is accurate and effective. [ABSTRACT FROM AUTHOR]

An efficient method for tracking a target using a single Pan-Tilt-Zoom (PTZ) camera is proposed. The proposed Scale-Invariant Optical Flow (SIOF) method estimates the motion of the target and rotates the camera accordingly to keep the target at the center of the image. Also, SIOF estimates the scale of the target and changes the focal length relatively to adjust the Field of View (FoV) and keep the target appear in the same size in all captured frames. SIOF is a feature-based tracking method. Feature points used are extracted and tracked using Optical Flow (OF) and Scale-Invariant Feature Transform (SIFT). They are combined in groups and used to achieve robust tracking. The feature points in these groups are used within a twist model to recover the 3D free motion of the target. The merits of this proposed method are (i) building an efficient scale-invariant tracking method that tracks the target and keep it in the FoV of the camera with the same size, and (ii) using tracking with prediction and correction to speed up the PTZ control and achieve smooth camera control. Experimental results were performed on online video streams and validated the efficiency of the proposed method SIOF, comparing with OF, SIFT, and other tracking methods. The proposed SIOF has around 36% less average tracking error and around 70% less tracking overshoot than OF. [ABSTRACT FROM AUTHOR]

An online fringe projection profilometry (OFPP) based on scale-invariant feature transform (SIFT) is proposed. Both rotary and linear models are discussed. First, the captured images are enhanced by "retinex" theory for better contrast and an improved reprojection technique is carried out to rectify pixel size while keeping the right aspect ratio. Then the SIFT algorithm with random sample consensus algorithm is used to match feature points between frames. In this process, quick response code is innovatively adopted as a feature pattern as well as object modulation. The characteristic parameters, which include rotation angle in rotary OFPP and rectilinear displacement in linear OFPP, are calculated by a vector-based solution. Moreover, a statistical filter is applied to obtain more accurate values. The equivalent aligned fringe patterns are then extracted from each frame. The equal step algorithm, advanced iterative algorithm, and principal component analysis are eligible for phase retrieval according to whether the object moving direction accords with the fringe direction or not. The three-dimensional profile of the moving object can finally be reconstructed. Numerical simulations and experimental results verified the validity and feasibility of the proposed method. [ABSTRACT FROM AUTHOR]

The active appearance model (AAM), one of the most effective facial feature localization methods, is widely used in frontal facial expression recognition. However, non-frontal facial expression recognition is important in many scenarios. Thus, we propose a new method for facial expression recognition based on AAM-SIFT and adaptive regional weighting. First, multi-pose AAM templates are used for pose estimation and feature point location of the facial expression image. For effective and efficient description of these feature points, a hybrid representation, which integrates gradient direction histograms based on the descriptors of scale-invariant feature transform (SIFT) and AAM, is utilized to form AAM-SIFT features. Meanwhile, according to different expression regions, AAM-SIFT features are divided into different groups and the obtained adaptive weights by means of a regional weighted method based on the fuzzy C-means (FCM) clustering algorithm. Finally, the membership degree computed by FCM, which represents the possibility for each class, is regarded as the input feature vector for support vector machine (SVM) classifier. Extensive experiments on BU-3DFE database with six facial expressions and seven poses demonstrate the effectiveness of different types of weighting strategies and the influence of different features. Comparison with other state-of-art methods illustrates that the proposed method not only improves the recognition rates of the frontal face but also has better robustness for non-frontal facial expressions. © 2015 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc. [ABSTRACT FROM AUTHOR]

Scale-invariant feature transform (SIFT) is an algorithm to detect and describe local features in images. In the last fifteen years, SIFT plays a very important role in multimedia content analysis, such as image classification and retrieval, because of its attractive character on invariance. This paper intends to explore a new path for SIFT research by making use of the findings from neuroscience. We propose a more efficient and compact scale-invariant feature detector and descriptor by simulating visual orientation inhomogeneity in human system. We validate that visual orientation inhomogeneity SIFT (V-SIFT) can achieve better or at least comparable performance with less computation resource and time cost in various computer vision tasks under real world conditions, such as image matching and object recognition. This work also illuminates a wider range of opportunities for integrating the inhomogeneity of visual orientation with other local position-dependent detectors and descriptors. [ABSTRACT FROM AUTHOR]

Passive forensics is increasing in significance due to the availability of various software tools that can be used to alter original content without visible traces and the increasing public awareness of such tampering. Many passive image tamper detection techniques have been proposed in the literature, some of which use feature extraction methods for tamper detection and localization. This work proposes a flexible methodology for detecting cloning in images based on the use of feature detectors. We determine whether a particular match is the result of a cloning event by clustering the matches using k-means clustering and using a support vector machine to classify the clusters. This descriptor-agnostic approach allows us to combine the results of multiple feature descriptors, increasing the potential number of keypoints in the cloned region. Results using maximally stable extremal regions' features, speeded up robust features, and scale-invariant feature transform show a very significant improvement over the state of the art, particularly when different descriptors are combined. A statistical filtering step is also proposed, increasing the homogeneity of the clusters and thereby improving the results. Finally, our methodology uses an adaptive technique for independently selecting the optimal k value for each image, allowing our method to work well when there are multiple cloned regions. We also show that our methodology works well when the training and testing datasets are mismatched. [ABSTRACT FROM AUTHOR]

A novel approach is proposed for the recognition of moving hand gestures based on the representation of hand motions as contour-based similarity images (CBSIs). The CBSI was constructed by calculating the similarity between hand contours in different frames. The input CBSI was then matched with CBSIs in the database to recognize the hand gesture. The proposed continuous hand gesture recognition algorithm can simultaneously divide the continuous gestures into disjointed gestures and recognize them. No restrictive assumptions were considered for the motion of the hand between the disjointed gestures. The proposed algorithm was tested using hand gestures from American Sign Language and the results showed a recognition rate of 91.3% for disjointed gestures and 90.4% for continuous gestures. The experimental results illustrate the efficiency of the algorithm for noisy videos. [ABSTRACT FROM AUTHOR]

This paper presents a biometric identification system based on near‐infrared imaging of dorsal hand veins and matching of the keypoints that are extracted from the dorsal hand vein images by the scale‐invariant feature transform. The whole system is covered in detail, which includes the imaging device used, image processing methods proposed for geometric correction, region‐of‐interest extraction, image enhancement and vein pattern segmentation, as well as image classification by extraction and matching of keypoints. In addition to several constraints introduced to minimise incorrectly matched keypoints, a particular focus is placed on the use of multiple training images of each hand class to improve the recognition performance for a large database with more than 200 hand classes. By organising multiple keypoint sets extracted from multiple training images of each hand class into three sets, namely, the union, the intersection and the exclusion, based on their inter‐class and intra‐class relationships, this study shows the contribution made by each set to the recognition performance and demonstrates the feasibility of achieving 100% correct recognition by combining the three sets, based on the experiments conducted using more than 2000 dorsal hand vein images. [ABSTRACT FROM AUTHOR]

Video-frame registration is a critical step in the video super-resolution process. However, many existing registration methods can handle only small local neighborhood movements or overall affine transformations. This limits the reconstruction of fast moving or significantly deforming objects. We propose a super-resolution registration method for video reconstruction. Considerable effort has been directed toward single-video and multivideo super-resolution methods. We aim to obtain a higher registration accuracy that maximally employs video frames to reconstruct the current frame, particularly for moving or deforming objects. To this end, we provide a content-based registration algorithm based on a propagation matching algorithm and the Lucas-Kanade method. The super-resolution step is implemented using robust iterative minimization. We compare our algorithm to others and demonstrate that our algorithm achieves high registration accuracy and more effectively reconstructs fast moving and significantly deforming objects. [ABSTRACT FROM AUTHOR]

A probabilistic neural-network-based feature-matching algorithm for a stereo image pair is presented in this paper, which will be useful as a constraint initializing method for further dense matching technique. In this approach, scale-invariant feature transform (SIFT) features are used to detect interest points in a stereo image pair. The descriptor which is associated with each keypoint is based on the histogram of the gradient magnitude and direction of gradients. These descriptors are the preliminary input for the matching algorithm. Using disparity range computed by visual inspection, the search area can be restricted for a given stereo image pair. Reduced search area improves the computation speed. Initial probabilities of matches are assigned to the keypoints which are considered as probable matches from the selected search area by Bayesian reasoning. The probabilities of all such matches are improved iteratively using relaxation labeling technique. Neighboring probable matches are exploited to improve the probability of best match using consistency measures. Confidence measures considering the neighborhood, unicity, and symmetry are some validation techniques which are built into the technique presented here for finding accurate matches. The algorithm is found to be effective in matching SIFT features detected in a stereo image pair with greater accuracy, and these accurate correspondences can be used in finding the fundamental matrix which encodes the epipolar geometry between the given stereo image pair. This fundamental matrix can then be used as a constraint for finding inliers that are used in matching methods for deriving dense disparity map. [ABSTRACT FROM PUBLISHER]

• A novel path independent stereo method is proposed. • The IC-GN algorithm with the second order shape function is accelerated on GPU. • An epipolar constraint-aided method is developed for stereo match. • Real-time stereo DIC with high analysis resolution is realized at regular video recording rate. Path independent strategy is introduced into stereo digital image correlation, in which high accuracy is attained through the inverse compositional Gauss-Newton (IC-GN) algorithm with the second and the first order shape functions for stereo matching and temporal matching, respectively. To gain strong adaptibility to large and complex deformation or considerable parallax betweent the two views, two robust methods are developped to estimate the initial guess for the iterative IC-GN algorithm. One is aided by scale invariant feature transform (SIFT) features and the other is aided by epipolar constraint. Powered by parallel computing on GPU, the proposed stereo DIC demonstrates high computation efficiency. Real-time stereo DIC is realized and used to measure the large deformation at common video recording rate (∼24 fps) with high ananlysis resolution (∼6300 points of interest in region of interest). [ABSTRACT FROM AUTHOR]

The smart extraction of key frames is one of the critical technologies for vehicle target recognition in the video streaming environment. Currently, the common algorithms are scale-invariant feature transform (SIFT) or background-difference method. Both algorithms have their own advantages and shortcomings. In this paper, a smart key frame extraction algorithm is proposed by combining the background difference method and SIFT feature matching algorithm, at the same time, the criterion factor K is introduced. The algorithm absorbs the idea of background difference and SIFT feature matching, and divides video frames into mutation frames and non-mutation frames. Hash algorithm is used to distinguish the similarity of two frames and remove redundant frames. The local feature of video sequence is introduced to solve the problem of sharp increasing calculation for inter frame distance. Experimental results show that the improved smart key frame extraction algorithm has a lower missing frame rate and higher accuracy for vehicle target recognition. [ABSTRACT FROM AUTHOR]

ABSTRACT A challenging task that has hampered the fully automatic processing of the digital image correlation (DIC) technique is the initial guess when large deformation and rotation are present. In this paper, a robust scheme combining the concepts of a scale-invariant feature transform (SIFT) algorithm and an improved random sample consensus (iRANSAC) algorithm is employed to conduct an automated fast initial guess for the DIC technique. The scale-invariant feature transform algorithm can detect a certain number of matching points from two images even though the corresponding deformation and rotation are large or the images have periodic and identical patterns. After removing the wrong matches with the improved random sample consensus algorithm, the three pairs of closest and non-collinear matching points serve for the purpose of initial guess calculation. The validity of the technique is demonstrated by both computer simulation and real experiment. [ABSTRACT FROM AUTHOR]

Stereo vision is becoming more and more common in three-dimensional visualization, autonomous vehicle navigation, path finding, object recognition, and other computer vision applications. In this paper, we present an approach for extracting visual landmarks from images acquired by a stereoscopic camera. The scale invariant feature transform (SIFT) technique with self-organizing map is used to detect and recognize visual landmarks. Our methodology is based on winner calculation technique, and the main idea is to keep in the database only distinctive features or landmarks in order to minimize detection time. We will demonstrate that this methodology is more efficient than ordinary SIFT algorithm or speeded up robust features (SURF) matching technique. Improved feature group matching with computation time better than SIFT and the SURF has been observed in the experiments with a variety of stereo image pairs. [ABSTRACT FROM AUTHOR]

In this paper, we address seabed characterization and recognition in sonar images using keypoint-based approaches. Keypoint-based texture recognition has recently emerged as a powerful framework to address invariances to contrast change and geometric distortions. We investigate here to which extent keypoint-based techniques are relevant for sonar texture analysis which also involves such invariance issues. We deal with both the characterization of the visual signatures of the keypoints and the spatial patterns they form. In this respect, spatial statistics are considered. We report a quantitative evaluation for sonar seabed texture data sets comprising six texture classes such as mud, rock, and gravely sand. We clearly demonstrate the improvement brought by keypoint-based techniques compared to classical features used for sonar texture analysis such as cooccurrence and Gabor features. In this respect, we demonstrate that the joint characterization of the visual signatures of the visual keypoints and their spatial organization reaches the best recognition performances (about 97% of correct classification w.r.t. 70% and 81% using cooccurrence and Gabor features). Furthermore, the combination of difference of Gaussian keypoints and scale-invariant feature transform descriptors is recommended as the most discriminating keypoint-based framework for the analysis of sonar seabed textures. [ABSTRACT FROM AUTHOR]

Mobile reception of digital TV signals often suffers from lost slices due to suboptimal channel characteristics. In this contribution we propose novel inter-sequence error concealment techniques which reconstruct lost blocks of distorted high-resolution TV signals by inserting error-free blocks of low-resolution reference signals. The proposed methods are well-suited for future automotive multi-broadcast receivers. As the reference signals are typically delayed, scaled and possibly cropped versions of the distorted TV signals, spatio-temporal image alignment is a crucial point. We first focus on pixel-based alignment utilizing a numerical optimization scheme. To reduce complexity a feature-based approach is introduced alternatively taking advantage of the scale-invariant feature transform. Simulations show that the proposed techniques can achieve supreme reconstruction quality outperforming conventional techniques by up to 15.0 dB PSNRY. The pixel-based approach mostly reaches the maximum reconstruction quality for both raw and compressed video signals. Feature-based concealment performs slightly worse but reduces the computation time by a factor of up to 36.6 at a maximum loss of 1.0 dB. A novel hybrid concealment technique combining the proposed methods with a temporal approach further increases the reconstruction quality. Applying one simple and one sophisticated mode selection scheme, a gain of 3.2 dB and 4.6 dB can be achieved, respectively. [ABSTRACT FROM AUTHOR]

Abstract: Currently, reverse engineering has attracted increasing attention in the non-destructive detection field, since it is a viable method to create a three-dimensional (3D) virtual model of an existing physical part. Feature points matching and 3D reconstruction are critical processes in reverse engineering of binocular stereo vision. In this paper, we present a 3D reconstruction method based on the feature matching algorithm of a scale-invariant feature transform (SIFT). First, we find the paired matching pixel points in the two corresponding digital images by using the SIFT matching algorithm. Second, the middle points on the common perpendicular of non-coplanar lines are exploited to estimate the 3D points. Finally, experimental results are presented to demonstrate the practicality of the proposed method. [Copyright &y& Elsevier]

• A novel 3D SIFT aided path independent DVC method is proposed. • The DVC method demonstrate outstanding adaptability to deal with large and complex deformation. • The DVC method is accelerated by parallel computing on GPU. • Ultrafast computation speed is achieved by of the DVC method on GPU. A novel path independent digital volume correlation (DVC) method is proposed, in which the internal deformation field is determined with the aid of the features extracted from the volume images. The deformation vector at each point of interest is first estimated by tracking the motion of the nearby keypoints obtained through 3D scale-invariant feature transform (SIFT), and then fed as the initial guess into the 3D inverse compositional Gauss-Newton algorithm to achieve high accuracy result. Benefiting from the robustness of SIFT to various deformation and distortion of image, the proposed DVC method demonstrates outstanding performance to automatically process the volume images containing large and complex deformation, which keep challenging to current DVC methods for decades. The proposed DVC method is further powered by the parallel computing on GPU. An ultrafast computation speed (about 10,000 POI/s) can be reached on a personal computer when dealing with the volume images of normal sizes. The 3D SIFT aided DVC method, which achieves unprecedented balance between accuracy, adaptability, and efficiency, shows great potential in the quantitative analysis of internal deformation. [ABSTRACT FROM AUTHOR]

Accurate registration is an essential prerequisite for analysis and applications involving remote sensing imagery. It is usually difficult to extract enough matching points for inter-band registration in hyperspectral imagery due to the different spectral responses for land features in different image bands. This is especially true for non-adjacent bands. The inconsistency in geometric distortion caused by topographic relief also makes it inappropriate to use a single affine transformation relationship for the geometric transformation of the entire image. Currently, accurate registration between spectral bands of Zhuhai-1 satellite hyperspectral imagery remains challenging. In this paper, a full-spectrum registration method was proposed to address this problem. The method combines the transfer strategy based on the affine transformation relationship between adjacent spectrums with the differential correction from dense Delaunay triangulation. Firstly, the scale-invariant feature transform (SIFT) extraction method was used to extract and match feature points of adjacent bands. The RANdom SAmple Consensus (RANSAC) algorithm and the least square method is then used to eliminate mismatching point pairs to obtain fine matching point pairs. Secondly, a dense Delaunay triangulation was constructed based on fine matching point pairs. The affine transformation relation for non-adjacent bands was established for each triangle using the affine transformation relation transfer strategy. Finally, the affine transformation relation was used to perform differential correction for each triangle. Three Zhuhai-1 satellite hyperspectral images covering different terrains were used as experiment data. The evaluation results showed that the adjacent band registration accuracy ranged from 0.2 to 0.6 pixels. The structural similarity measure and cosine similarity measure between non-adjacent bands were both greater than 0.80. Moreover, the full-spectrum registration accuracy was less than 1 pixel. These registration results can meet the needs of Zhuhai-1 hyperspectral imagery applications in various fields. [ABSTRACT FROM AUTHOR]

To secure the secret communication, a robust video steganography algorithm is proposed. The major objectives of the proposed method (PM) are: (1) perceiving the region of interest (ROI) keypoints' locations in video frames for concealing the secret data and (2) determining the appropriate amount of data to be embedded into the perceived ROI keypoints' region. In the PM, keypoints are initially extracted from each video frame using scale-invariant feature transform (SIFT) and a speeded-up robust features (SURF) descriptor against a set of predefined geometrical and signal processing attacks. Next, ROI keypoints are generated by comparing the SIFT and SURF keypoint descriptors of the original frame and attacked versions of the frame. Then ROI keypoints are divided into four least significant bit (LSB) groups to determine the embedding capacity of each ROI keypoint. Subsequently, the secret data are encrypted using a symmetric key-based shift cipher to provide an additional security layer for secret communication. Finally, the encrypted secret data have been embedded into the ROI keypoints using the LSB substitution method based on the four LSB groups' values. The PM is tested on 22 standard benchmark videos. The efficiency of the PM is evaluated in terms of the perceptual invisibility, robustness, and concealing capacity. From experimental results, it is observed that the PM outperforms contemporary methods by attaining significant outcomes. [ABSTRACT FROM AUTHOR]

• A novel path-independent DIC method aided with SIFT features is proposed. • The proposed DIC method demonstrate excellent adaptability to deal with large and complex deformation. • Ultrafast computation speed of the proposed DIC method is achieved by introducing parallel computing on GPU. Current iterative digital image correlation (DIC) algorithms can efficiently converge at the deformation vector with high accuracy when they are fed with reliable initial guess. Thus, the adaptability of DIC method is dominated to a large extent by the estimation of initial guess. In recent years, image feature-based technique, especially the scale-invariant feature transform (SIFT), was introduced to DIC for the estimation of initial guess in the case of large and complex deformation, due to its robustness in handling the images with translation, rotation, scaling, and localized distortion. However, feature extraction and matching in SIFT are very time consuming, which limits the applications of the SIFT-aided DIC. In this study, we developed a SIFT-aided path-independent DIC method and accelerated it by introducing the parallel computing on graphics processing unit (GPU) or multi-core CPU. In our method, SIFT features are used to estimate the initial guess for the inverse compositional Gauss-Newton (IC-GN) algorithm at each point of interest (POI). The experimental study shows that the developed method can deal with large and inhomogeneous deformation with high accuracy. Parallel computing (especially on GPU) accelerates significantly the proposed DIC method. The achieved computation speed satisfies the need for real-time processing with high resolution for the images of normal sizes. [ABSTRACT FROM AUTHOR]

Due to considerable diversities of multimodality remote sensing images in spectral component, the performances of scale-invariant feature transform (or SIFT) may be problematic. In view of this, a model of image registration based on tangent-crossing-point feature is proposed. With the help of tangent-cross-point feature, verifying the correctness of the feature matching is very easy, since it adopts the location information indexed by the correct matching pair of feature-points and transformation information determined by the correct matching pair of curves simultaneously. Experimental results show that this method is more efficient and reliable than the classic SIFT algorithm in some cases. [ABSTRACT FROM AUTHOR]

• Implementation of parameterizable horizontal/vertical SIMD vector processor architectures. • Performance-optimized hardware and ISA for image processing tasks. • Complete SIFT implementation with detailed horizontal/vertical vectorization strategies. • Extensive architecture comparison for ASIC implementation (performance, area, energy). Embedded automotive Computer Vision systems for real-time motion tracking and 3D scene reconstruction demand for high image feature extraction performance and have a heavily constrained energy budget unable to be met by general-purpose CPUs and GPUs. Due to the required programming flexibility for software updates and algorithmic extensions, the use of fully dedicated hardware accelerators is not advisable in most cases. In this paper, a vertical and a horizontal SIMD vector processor architecture are implemented and compared for accelerating the Scale-Invariant Feature Transform feature extraction algorithm, exploiting inherent data-level parallelism prevalent in this application and considering different programming code strategies for the different vectorization paradigms. An evaluation for a 45 nm ASIC technology shows an overall performance gain of up to 24.8x, and up to 151.3x higher total performance-area-energy efficiency compared to a reference scalar two-issue VLIW processor. Compared to other implementations on programmable ASIP and mobile GPU platforms, the proposed vertical SIMD vector processor achieves a performance gain of up to 5.1x and up to 31.3x higher performance-energy efficiency. [ABSTRACT FROM AUTHOR]

• A large field of view visible image acquisition and processing system was designed in the EAST device. • Image acquisition, storage and processing servers are connected with high performance. • A block matching scale-invariant feature transformation was adopted to form the large field of view. A large field of view visible image acquisition and processing system was designed to address the discharge visual needs for estimating the state of plasma operation and the first wall conditions during the plasma discharge of the Experimental Advanced Superconducting Tokamak (EAST) device. The entire system, which consisted of software and hardware, was introduced in detail. Moreover, three sets of the visible camera diagnostic systems with the different field-of-view images acquired by three industrial personal computers (IPCs) were used for forming the large field of view through image stitching. Three IPCs, and data storage and image processing servers are connected by a reflective memory network, which can realize the collection and fast transmission of image data during discharge. In addition, an image stitching algorithm based on block matching scale-invariant feature transformation was adopted. To accelerate the processing of the algorithm, parallelization was achieved by using the Graphics Processing Unit (GPU). Through the mesa test and experimental results, the proposed system provides a feasible way of transmitting and stitching images quickly and fulfills the EAST experimental demands. [ABSTRACT FROM AUTHOR]

Visual homing is an attractive autonomous mobile robot navigation technique, which only uses vision sensors to guide the robot to the specified target location. Landmark is the only input form of the visual homing approaches, which is usually represented by scale-invariant features. However, the landmark distribution has a great impact on the homing performance of the robot, as irregularly distributed landmarks will significantly reduce the navigation precision. In this paper, we propose three strategies to solve this problem. We use scale-invariant feature transform (SIFT) features as natural landmarks, and the proposed strategies can optimize the landmark distribution without over-eliminating landmarks or increasing calculation amount. Experiments on both panoramic image databases and a real mobile robot have verified the effectiveness and feasibility of the proposed strategies. [ABSTRACT FROM AUTHOR]

Region duplication is a simple and effective operation to create digital image forgeries, where a continuous portion of pixels in an image is copied and pasted to a different location in the same image. Many prior copy–move forgery detection methods suffer from their inability to detect the duplicated region, which is subjected to various geometric transformations. A keypoint-based approach is proposed to detect the copy–move forgery in an image. Our method starts by extracting the keypoints through a fast Hessian detector. Then the adaptive minimal–maximal suppression (AMMS) strategy is developed for distributing the keypoints evenly throughout an image. By using AMMS and a sped-up robust feature descriptor, the proposed method is able to deal with the problem of insufficient keypoints in the almost uniform area. Finally, the geometric transformation performed in cloning is recovered by using the maximum likelihood estimation of the homography. Experimental results show the efficacy of this technique in detecting copy–move forgeries and estimating the geometric transformation parameters. Compared with the state of the art, our approach obtains a higher true positive rate and a lower false positive rate. [ABSTRACT FROM AUTHOR]