Search

Despite extensive research on content-based image retrieval, challenges such as low accuracy, incapability to handle complex queries and high time consumption persist. Initially, a preprocessing technique is introduced in this study, a technique that uses a median filter to remove noise to achieve improved accuracy and reliability. Then, Fourier and circularity descriptors are extract in an effective manner correspondent to the texture and affine shape adaptation features. In addition, various descriptors, such as color histogram, color moment, color autocorrelogram and color coherency vector, are extracted as the invariant color features. The multiple ant colony optimization (MACOBTC) approach is implemented with whole features to find relevant features. Finally, the relevant features are utilized for the greedy learning of deep Boltzmann machine classifier (GDBM). The proposed approach obtains effective performance and accurate results on four datasets and is analyzed with various parameters such as accuracy, precision, recall, Jaccard, Dice, and Kappa coefficients. The GDBM provides a 25% increase in accuracy compared with existing techniques, such as the a priori classification algorithm.

We consider the person re-identification problem, assuming the availability of a sequence of images for each person, commonly referred to as video-based or multi-shot re-identification. We approach this problem from the perspective of learning discriminative distance metric functions. While existing distance metric learning methods typically employ the average feature vector as the data exemplar, this discards the inherent structure of the data. To overcome this issue, we describe the image sequence data using affine hulls. We show that directly computing the distance between the closest points on these affine hulls as in existing recognition algorithms is not sufficiently discriminative in the context of person re-identification. To this end, we incorporate affine hull data modeling into the traditional distance metric learning framework, learning discriminative feature representations directly using affine hulls. We perform extensive experiments on several publicly available data sets to show that the proposed approach improves the performance of existing metric learning algorithms irrespective of the feature space employed to perform metric learning. Furthermore, we advance the state of the art on iLIDS-VID, PRID, and SAIVT, with absolute rank-1 performance improvements of 6.0%, 11.4%, and 6.0% respectively.

In this paper, we study a simplified affine motion model-based coding framework to overcome the limitation of a translational motion model and maintain low-computational complexity. The proposed framework mainly has three key contributions. First, we propose to reduce the number of affine motion parameters from 6 to 4. The proposed four-parameter affine motion model can not only handle most of the complex motions in natural videos, but also save the bits for two parameters. Second, to efficiently encode the affine motion parameters, we propose two motion prediction modes, i.e., an advanced affine motion vector prediction scheme combined with a gradient-based fast affine motion estimation algorithm and an affine model merge scheme, where the latter attempts to reuse the affine motion parameters (instead of the motion vectors) of neighboring blocks. Third, we propose two fast affine motion compensation algorithms. One is the one-step sub-pixel interpolation that reduces the computations of each interpolation. The other is the interpolation-precision-based adaptive block size motion compensation that performs motion compensation at the block level rather than the pixel level to reduce the number of interpolation. Our proposed techniques have been implemented based on the state-of-the-art high-efficiency video coding standard, and the experimental results show that the proposed techniques altogether achieve, on average, 11.1% and 19.3% bits saving for random access and low-delay configurations, respectively, on typical video sequences that have rich rotation or zooming motions. Meanwhile, the computational complexity increases of both the encoder and the decoder are within an acceptable range.

Robust and reliable features with noise immunity, rotation-invariance, and low-dimensionality are the challenging aspects of pattern recognition. In this study, the authors presented a novel low-dimensional binary feature descriptor local diagonal Laplacian pattern (LDLP) for medical image registration. LDLP method is developed by defining the local relationship between a centre pixel and its diagonal neighbours and encoding it to a binary feature vector. The idea of centre-diagonal pixel correlation has drastically reduced the length of the feature vector without compromising the quality of local texture analysis. In the proposed work, first, the LDLP feature histograms of computed tomography (CT), magnetic resonance (MR), and ultrasound images are obtained. Further, these LDLP features of individual medical images are considered as target/fixed objects while their corresponding rotated and noisy features are considered as moving/floating objects to perform mono-modal rigid registration using an improved Procrustes analysis-based affine transform. The registration quality is examined by calculating the squared intensity error and the results are compared with the existing binary patterns such as local binary patterns, local tetra patterns, and local diagonal extrema patterns. The proposed LDLP feature descriptor-based rigid registration has attained relatively better performance in terms of registration accuracy and computational complexity.

Subspace clustering is an important problem in machine learning with many applications in computer vision and pattern recognition. Prior work has studied this problem using algebraic, iterative, statistical, low-rank and sparse representation techniques. While these methods have been applied to both linear and affine subspaces, theoretical results have only been established in the case of linear subspaces. For example, algebraic subspace clustering (ASC) is guaranteed to provide the correct clustering when the data points are in general position and the union of subspaces is transversal . In this paper we study in a rigorous fashion the properties of ASC in the case of affine subspaces. Using notions from algebraic geometry, we prove that the homogenization trick , which embeds points in a union of affine subspaces into points in a union of linear subspaces, preserves the general position of the points and the transversality of the union of subspaces in the embedded space, thus establishing the correctness of ASC for affine subspaces.

This paper presents a fast and accurate affine canonicalization method for planar shapes. This method improves on previous ones based on iterative optimization that produce multiple canonical versions. Canonicalization provides a common reference frame for shape comparison without the loss of discrimination ability often caused by invariant features. It also gives for free the alignment transformation between any pair of shapes. The proposed method is based on the properties of the joint angular distribution of marginal skewness and kurtosis, the so-called SK signature, which can be efficiently computed in closed form from the raw image moments. The experiments demonstrate that the method is robust to the non-affine distortions caused by natural perspective image conditions. Thus, it can be used as an automatic preprocessing step to add affine invariance in statistical pattern recognition applications.

Video compression marks its necessity when a huge sized video needs to be transmitted. The process starts with the identification of GoP (group of pictures), which depends on I- (intra), B- (bidirectional) and P- (predicted) frames determination. GoP is fixed, where consecutive frames are placed in an orderly manner based on the GoP size. Conventionally, B-frames lead to buffering of memory within the past and future frames consuming more computational time. Such issues are handled by an adaptive framework for determining frames based on matching criteria rather than fixed GoP. NSEW (North–South–East–West) affine translation (NAT) is proposed for replacing B with either I- or P-frame. The proposed framework involves video compression using affine motion-based free-form transformation and video decompression using warping methodologies for the purpose of compressing and decompressing the video sequence, based on the resulted I- and P-frames. B-spline transformation was also initiated at local level along with global affine transformation to improve the subjective quality of the decompressed video sequence. The methodology was investigated for the file size, computational time, peak-signal-to-noise ratio (PSNR) and Structural Similarity index (SSIM), which proved the superiority of the proposed technique. Further, the methodology was also investigated with optimizing the affine motion parameters (AMP) using nonlinear least squares, Broyden–Fletcher–Goldfarb–Shanno (BFGS) and limited-memory BFGS which yet again proved to be far more superior to conventional techniques with an average PSNR of 38.98 dB with LBFGS. To further improve the subjective quality, affine B-spline-based motion estimation using LBFGS was implemented and observed the average PSNR gain to be 42.03 dB.

Measuring rail profile in the presence of multiple degrees of freedom vibration is a very challenging task. This paper presents a novel method based on the local affine invariant feature descriptor to calibrate distorted profiles, which are obtained by traditional rail measurement system. It has three major modules: local affine invariant (LAI) feature descriptor, affine transformation estimation and parameters refinement. LAI feature descriptor is based on the affine geometry invariant and generated by calculating the proportions of different areas. Using the proposed LAI descriptor, we implement a three-stage profile calibration including matching, estimation, and refinement based on grouping and fast iterative closest point (FICP) algorithm. The performance of proposed LAI descriptor and calibrating method is tested by performing extensive experiments. The experimental results show that our LAI descriptor is highly descriptive and robust with respect to varying resolution and noise, and the LAI descriptor based calibration is effective and repeatable.

Robust image matching is crucial for many applications of remote sensing and photogrammetry, such as image fusion, image registration, and change detection. In this paper, we propose a robust feature matching method based on support-line voting and affine-invariant ratios. We first use popular feature matching algorithms, such as SIFT, to obtain a set of initial matches. A support-line descriptor based on multiple adaptive binning gradient histograms is subsequently applied in the support-line voting stage to filter outliers. In addition, we use affine-invariant ratios computed by a two-line structure to refine the matching results and estimate the local affine transformation. The local affine model is more robust to distortions caused by elevation differences than the global affine transformation, especially for high-resolution remote sensing images and UAV images. Thus, the proposed method is suitable for both rigid and non-rigid image matching problems. Finally, we extract as many high-precision correspondences as possible based on the local affine extension and build a grid-wise affine model for remote sensing image registration. We compare the proposed method with six state-of-the-art algorithms on several data sets and show that our method significantly outperforms the other methods. The proposed method achieves 94.46% average precision on 15 challenging remote sensing image pairs, while the second-best method, RANSAC, only achieves 70.3%. In addition, the number of detected correct matches of the proposed method is approximately four times the number of initial SIFT matches.

Calculating the geometry relationship by the positions of the correspondences from stereo images is a fundamental method to obtain the depth information. Such a method was quite widespread and popular thanks to its efficiency and easily accessed implementation. General speaking, the more density of the correspondences are, the more precisely the depth information can be calculated. Theoretically, a sufficient strengthened correspondences match algorithm can be utilized for depth information calculation under any circumstances. Unfortunately, the updated image feature detectors are all sensitive to the view point changes: with the rising of the stereo images' view angle, the number of matched features drastically reduced, resulting in the number of matched features not adequate to cover every details of the stereo images. This disadvantages of feature detections in practice hampers its application for the depth calibration. To tackle the sensitive of view point to stereo images, in this paper, we will propose an affine invariant affine scale space structure, which is more robust to detect the correspondences from stereo images. The purpose of affine scale space is to create a more general approach to the affine invariant image scale representation by modifying the corresponding Gaussian filters in order to cope with the specific change of view point. The affine adaptation of the scale space is to retain a linear relationship with the transiting of the view point. With linear relationship, the affine scale space can be established as a more general approach for the detection of correspondences from stereo images. With a better correspondences detection, a more precise depth information can be made.

Estimating homography using only one affine correspondence.The proposed theory makes multi-homography estimation less ambiguous.Stochastic sampling can be omitted from robust homography estimation.Affine-covariant detectors are compared w.r.t. quality of estimated homographies.Equivalence of affine and perspective-invariances for known epipolar geometry. We propose a method, called HAF, to estimate planar homography from an affine correspondence satisfying the epipolar constraint in an image pair. An affine correspondence consists of a point pair and the related local affine transformation mapping the pixels infinitely close to the point locations from the first to the second images. As a minimal solver, it estimates the homography from only one correspondence, however, it is generalized for the over-determined case as well. The required local affinities are obtained by affine-covariant feature detectors accurately. As a side-effect of the tests, the state-of-the-art affine-covariant detectors are compared to each other w.r.t. the accuracy of the estimated point-wise homographies. The proposed method is validated both on the publicly available AdelaideRMF dataset and in a synthetic testing environment.

A novel target detection method based on affine invariant interest point detection, feature encoding, and large-margin dimensionality reduction (LDR) is proposed for optical remote sensing images. First, four types of interest point detectors are introduced, and their performance in extracting low-level affine invariant descriptors using affine shape estimation is compared. Such a description can deal with significant affine transformations, including viewpoints. Second, feature encoding, which extends bag-of-words (BOW) by encoding high-order statistics, is selected to generate mid-level representation. Finally, LDR based on the large-margin constraint and stochastic subgradient is introduced to make the high-dimensional mid-level representation applicable for target detection. The experiments on aircraft and vehicle detections illustrate the effectiveness of the affine invariant description and LDR (compared with principal component analysis) in improving the detection performance. The experiments also demonstrate the effectiveness of the proposed method compared with popular approaches including Gabor, HOG, LBP, BOW, and R-CNN.

Mismatch removal is a key step in many computer vision problems. In this paper, we handle the mismatch removal problem by adopting shape interaction matrix (SIM). Given the homogeneous coordinates of the two corresponding point sets, we first compute the SIMs of the two point sets. Then, we detect the mismatches by picking out the most different entries between the two SIMs. Even under strong affine transformations, outliers, noises, and burstiness, our method can still work well. Actually, this paper is the first non-iterative mismatch removal method that achieves affine invariance. Extensive results on synthetic 2D points matching data sets and real image matching data sets verify the effectiveness, efficiency, and robustness of our method in removing mismatches. Moreover, when applied to partial-duplicate image search, our method reaches higher retrieval precisions with shorter time cost compared with the state-of-the-art geometric verification methods.

The problem of aligning of 3D point data is the known registration task. The most popular registration algorithm is the Iterative Closest Point (ICP). This paper proposes a new algorithm for affine registration of point clouds by incorporating the affine transformation into the point-to-plane ICP algorithm. At each iterative step of the algorithm, a closed-form solution for the affine transformation is derived.

The modern era of information technology suffers a serious loss due to the lack of a cutting edge methodology for storing mega sized videos. It is at this juncture, video compression makes a mark for its necessity. There have been several research outcomes where almost all researchers have followed a particular methodology of adopting GoP (Group of pictures) for video compression, focusing on I (Intra), B (Bi-directional) & P (Predicted) frame determination. These frames remain fixed throughout the process of GoP regardless of the camera motion. Moreover, it also leads to buffering of memory within the past and future thereby consuming more computational time for B-frames. These vital issues are handled by an adaptive framework of determining frames based on a matching criteria rather than utilizing fixed GoP pattern. NSEW affine translation (NAT) is introduced for replacing B-frames with either I or P frame. The framework involves VCAME (Video Compression using Affine Motion Estimation) & VDAW (Video Decompression using Affine Warping) methodologies for compressing and decompressing a video sequence, based on the resulted I & P frames. The methodology was investigated over four vital parameters, the file size, computational time, SSIM (Structural Similarity Index) & PSNR (Peak Signal to Noise ratio), which proved the superiority of the proposed technique. Further, the methodology was also investigated with optimizing the affine motion parameters (AMP) using nonlinear least squares, BFGS (Broyden–Fletcher–Goldfarb–Shanno) and Limited-memory BFGS which yet again proved to be far more superior than conventional techniques yielding an average PSNR gain of 2.52 dB .

Correlation filter achieves promising performance with high speed in visual tracking. However, conventional correlation filter based trackers cannot tackle affine transformation issues such as scale variation, rotation and skew. To address this problem, in this paper, we propose a part-based representation tracker via kernelized correlation filter (KCF) for visual tracking. A Spatial-Temporal Angle Matrix (STAM), severed as confidence metric, is proposed to select reliable patches from parts via multiple correlation filters. These stable patches are used to estimate a 2D affine transformation matrix of the target in a geometric method. Specially, the whole combination scheme for these stable patches is proposed to exploit sampling space in order to obtain numerous affine matrices and their corresponding candidates. The diversiform candidates would help to seek for the optimal candidate to represent the object's accurate affine transformation in a higher probability. Both qualitative and quantitative evaluations on VOT2014 challenge and Object Tracking Benchmark (OTB) show that the proposed tracking method achieves favorable performance compared with other state-of-the-art methods.

Rolling shutter distortions degrade the quality of videos captured by hand-held cameras. This letter proposes an affine motion model for removing rolling shutter distortions. The model represents the image motion during image capture as a sequence of affine transformations and computes the composition of these affine transformations precisely. Because an affine transformation can be represented by a neural network with one layer of linear neurons, the motion model can be represented by a multilayer neural network of linear neurons. Thus, the backpropagation algorithm can be used to improve the efficiency of the optimization process that estimates the model parameters. The proposed model is calibration-free. It is more general than other rolling shutter motion models because it only assumes that the velocity of the image during image acquisition is piecewise constant. Experimental results demonstrate that the model is more accurate than two state-of-the-art models and that the model parameters can be estimated efficiently.

Since few years ago it has been generally accepted without any dispute that the 3D affine transformation applied to high-resolution satellite imageries (HRSI), produces results as accurate as those obtained by the RPCs derived from rigorous photogrammetric model. However, as the higher order terms are absent in the affine transformation, the degree of success of this model obviously hinges upon the geometric nature of the imagery to be geo-rectified. In authors view, there are a latent confusion and misunderstanding in the minds of the photogrammetric practitioners as regards the potential of the 3D affine transformation as a replacement model for the geometric correction of the HRSI. The main intention of this paper is, therefore, to analyse the 3D affine transformation by concentrating more on its limitations. To obtain deeper insight into the nature of the 3D affine model, it is applied to images with larger field of view as well as the images of highly mountainous terrains. The geo-coding success of the affine model is then evaluated by comparing the object coordinates of a dense cloud of homologous points derived by the affine model with the object coordinates of the same points obtained by the standard terrain-independent rational functions. Extensive tests conducted over excessively mountainous as well as the hilly terrains indicate that there are clear distortion trends in the residual ground coordinates that cannot be fully absorbed into the 3D affine coefficients. The sources of these non-linear trends such as the satellite attitude and position variations, the terrain relief, the earth curvature and their impact on the final accuracy are analysed using the scatter patterns of the residual errors.

Shape is considered to be one of the most promising tools to represent and recognise an object. In this study, an effective and rigorous shape matching algorithm is developed based on a new descriptor and relaxation labelling technique. For each contour point, the descriptor captures the distribution of all points within the shape region along the vector perpendicular to that from the centroid to the point. In addition to stable affine invariance, the descriptor is robust to noise since it makes use of all points in the shape region. The descriptor distance is used to initialise the contour point matching probability, and relaxation labelling technique is utilised to update the matching probability using a new compatibility coefficient function, which is defined based on the shape projection preserving characteristic. The experiments on synthetic and real remote sensing data are provided to test the performance of the authors’ proposed algorithm. Compared to other four state-of-the-art contour-based shape matching algorithms, their algorithm is more robust and capable of shape matching under affine transformations and noise.

Face recognition (FR) is one of the most effervescent fields of research with extensive applications that span numerous domains, and it stands resolutely as one of the most challenging problems in computer vision. The accuracy of FR systems is severely affected when two images under consideration for a match, vary in their scale and/or affine angles. The prevalent affine and scale invariant recognition systems have been predominantly developed only for objects, and hence in this study, the authors propose a novel approach for faces based on the affine-SIFT (ASIFT) and two-dimensional principal component analysis (2DPCA) techniques, to accomplish the formidable task of facial image recognition, invariant of scale and affine angles, i.e. the ability to simulate with enough accuracy, all the distortions caused by the differences in resolution and the variation of the camera optical axis direction. In the formulation of ASIFT-2DPCA, they investigate three different variants of 2DPCA: classical 2DPCA, quaternion 2DPCA and sparse 2DPCA to gauge as to which is more effective. The authors'experimentations will demonstrate that the proposed approach can robustly handle affine and scale variations, and hence provide better accuracy and matching performance than the state-of-the-art methodologies.

The development of a virtual environments is desirable in many engineering applications for several reasons. For example, it can reduce the number of dangerous operations during the virtual inspection of mines, pipes for gas, water and sewer to inspect its current condition and identify possible failures. The proposal in this paper is an alternative solution to this problem obtaining a virtual image through the reconstruction of the inner pipe for assessment and fault detection. The proposed method employs regions with affine transformations used as dense correspondence, which are calculated through local correspondences, such as the detector/descriptor SIFT (Scale-invariant feature transform). The SIFT is required to obtain the position and orientation of the camera in the captured positions to get the structure of the scene through correspondences and to create a 3D reconstruction.

In this paper, we discuss the digitization and applications of smooth affine shear tight frames, a recently developed new class of directional multiscale representation systems. An affine wavelet tight frame is generated by isotropic dilations and translations of directional wavelet generators, while an affine shear tight frame is generated by anisotropic dilations, shears, and translations of shearlet generators. These two tight frames are actually connected in the sense that an affine shear tight frame can be obtained from an affine wavelet tight frame through subsampling. Consequently, an affine shear tight frame has an underlying filter bank from the MRA structure of its associated affine wavelet tight frame. We discuss the digitization of digital affine shear filter banks associated with the affine shear tight frames. Moreover, we provide the detailed algorithmic steps for both the forward and backward digital affine shear transforms. Analysis of the redundancy rate and computational complexity shows...

Display Omitted In the proposed algorithm, simultaneously 4 pixel/voxel locations can be transformed to compute AT of the entire image.The proposed architecture requires only relevant frames instead of all the frames simultaneously.The faster implementation of the affine transform is useful during image registration of the 3D bio-medical images. Affine Transform (AT) is widely used in high-speed image processing systems. This transform plays an important role in various high-speed image processing applications. AT, an important process during the intensity-based image registration, is applied iteratively during the registration. This is also used for the analysis of the interior of an organ and to get a better view of the organs from various angles in 3D coordinate system. Hence, for real-time medical image registration and visualization of the acquired volumetric images, acceleration of AT is very much sought for. In this paper, a parallel and pipelined architecture of the proposed AT algorithm has been presented. This will accelerate the transform process and reduce the processing time of medical image registration. The architecture is mapped in Field-Programmable Gate Array (FPGA) for prototyping and verification. The results show that the computational complexity of the proposed parallel algorithm is almost 4 times better than that of the conventional algorithm.

A novel surface normal estimator is introduced using affine-invariant features extracted and tracked across multiple views. Normal estimation is robustified and integrated into our reconstruction pipeline that has increased accuracy compared to the State-of-the-Art. Parameters of the views and the obtained spatial model, including surface normals, are refined by a novel bundle adjustment-like numerical optimization. The process is an alternation with a novel robust view-dependent consistency check for surface normals, removing normals inconsistent with the multiple-view track. Our algorithms are quantitatively validated on the reverse engineering of geometrical elements such as planes, spheres, or cylinders. It is shown here that the accuracy of the estimated surface properties is appropriate for object detection. The pipeline is also tested on the reconstruction of man-made and free-form objects.

Image matching is a vital process for many photogrammetric and remote sensing applications such as image registration and aerial triangulation. In this paper, an accurate affine invariant image matching approach is presented. The proposed approach consists of three main steps. In the first step, two affine invariant feature detectors, including MSER and Harris-Affine features are applied for feature extraction. In the second step, initial corresponding features are selected using Euclidean distance between feature descriptors, followed by a consistency check process. Finally to overcome low positional accuracy of the local affine feature, an advanced version of the least square matching (LSM) namely, Oriented Least Square Matching (OLSM) is developed. Wellknown LSM method has been widely accepted as one of the most accurate methods to obtain high reliable corresponding points from a stereo image pair. However, it is sensitive to significant geometric distortion and requires very good initial approximation. In the proposed OLSM method, shape and size of the matching window are appropriately approximated using obtained affine shape information of the initial elliptical feature pairs. The proposed method was successfully applied for matching various synthetic and real close range and satellite images. Results demonstrate its accuracy and capability compared to standard LSM method.

Local features offer high repeatability, which supports efficient matching between images, but they do not provide sufficient discriminative power. Imposing a geometric coherence constraint on local features improves the discriminative power but makes the matching sensitive to anisotropic transformations. We propose a novel feature representation approach to solve the latter problem. Each image is abstracted by a set of tuples of local features. We revisit affine shape adaptation and extend its conclusion to characterize the geometrically stable feature of each tuple. The representation thus provides higher repeatability with anisotropic scaling and shearing than found in previous research. We develop a simple matching model by voting in the geometrically stable feature space, where votes arise from tuple correspondences. To make the required index space linear as regards the number of features, we propose a second approach called a centrality-sensitive pyramid to select potentially meaningful tuples of local features on the basis of their spatial neighborhood information. It achieves faster neighborhood association and has a greater robustness to errors in interest point detection and description. We comprehensively evaluated our approach using Flickr Logos 32, Holiday, Oxford Buildings, and Flickr 100 K benchmarks. Extensive experiments and comparisons with advanced approaches demonstrate the superiority of our approach in image retrieval tasks.

This paper proposes a novel method to address the registration of images with affine transformation. Firstly, the Maximally Stable Extremal Region (MSER) detection method is performed on the reference image and the image to be registered, respectively. And the coarse affine transformation matrix between the two images is estimated by the matched MSER pairs. Two circular regions containing roughly the same image content are also obtained by fitting and normalizing the centroids of the matched MSERs from the two images. Secondly, a scale invariant and approximate affine transformation invariant feature point detection algorithm based on the Gabor filter decomposition and phase congruency is performed on the two coarsely aligned regions, and two feature point sets are achieved, respectively. Finally, the affine transformation matrix between the two feature point sets is obtained by using a probabilistic point set registration algorithm, and the final affine transformation matrix between the reference image and the image to be registered is achieved according to the coarse affine transformation matrix and the affine transformation matrix between the two feature point sets. Several sets of experiments demonstrate that our proposed method performs competitively with the classical scale-invariant feature transform (SIFT) method for images with scale changes, and performs better than the traditional MSER and Affine-SIFT (ASIFT) methods for images with affine distortions. Moreover, the proposed method shows higher computation efficiency and robustness to illumination change than some existing area-based or feature-based methods do. A combination of coarse alignment and refinement is employed in the method.Input images are coarsely aligned by fitting and normalizing the matched MSERs.A phase congruency and point set registration based refinement step is used.The method accurately and efficiently aligns images with affine distortions.The method is robust to illumination changes.

We present a novel method for affine transformation estimation of image regions. We illustrate the benefits of using the proposed method in three realms: (1) locating large amounts of point matches with highly accurate localization; (2) producing very accurate affine transformation estimations of for each matched region; (3) effectively rejecting false matches. We show that this is achievable with low computational demand. Point matching is one of the most fundamental tasks in computer vision, being used extensively in applications such as object detection, object tracking, and structure from motion. The major challenge in point matching is to preserve large numbers of accurate matches between corresponding scene locations under different geometric and radiometric conditions, while keeping the number of false matches small. Recent publications have shown that applying the affine transformation model on local regions is a particularly suitable approach for point matching. Yet affine invariant methods are n...

Comunicació presentada a 11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2016), celebrat del 27 al 29 de febrer de 2016 a Roma, Itàlia. Patch-based approaches are used in state-of-the-art methods for image inpainting. This paper presents a new method for exemplar-based image inpainting using transformed patches. The transformation is determined for each patch in a fully automatic way from a surrounding texture content. We build upon a recent affine invariant patch similarity measure that performs an appropriate patch comparison by automatically adapting the size and shape of the patches. As a consequence, it intrinsically extends the set of available source patches to copy information from. We incorporate this measure into a variational formulation for inpainting and present a numerical algorithm for optimizing it. We show that our method can be applied to complete a perspectively distorted texture as well as to automatically inpaint one view of a scene using other view of the same scene as a source. We present experimental results both for gray and color images, and a comparison with some exemplar-based image inpainting methods. The first, second and fourth authors acknowledge partial support by the MINECO/FEDER project with reference TIN2015-70410-C2-1-R , the MICINN project with reference MTM2012- 30772, and by GRC reference 2014 SGR 1301, Generalitat de Catalunya. The second and third authors were partly founded by the Centre National dEtudes Spatiales (CNES, MISS Project), BPIFrance and R´egion Ile de France, in the framework of the FUI 18 Plein Phare project, the European Research Council (advanced grant Twelve Labours n246961), the Office of Naval research (ONR grant N00014-14-1-0023), and ANRDGA project ANR-12-ASTR-0035.

Affine shear tight frames with 2-layer structure are introduced. Characterizations and constructions of smooth affine shear tight frames with 2-layer structure are provided. Digital affine shear banks with 2-layer structure are then constructed. The implementation of digital affine shear transforms using the transition and subdivision operators are given. Numerical experiments on image denoising demonstrate the advantage of our digital affine shear filter banks with 2-layer structure.

This paper introduced a novel affine, rotation invariant filtering feature matching model based on RGB and geometric-based images. The proposed model was implemented based on summation of epipolar distance of angles, scale estimation based on intensity gradients, and normal vector estimation by using geometric data. Since of former ordering, our method is affine and rotation invariant which provides robustness to our method. Comparable experiments with well stabilized descriptors such as BRAND, MSER, ORB, BRISK with our method. Our method achieved improved results under texture, geometry and a combination of both information.

Perspective cameras are the most popular imaging sensors used in computer vision. However, many application fields, including automotive, surveillance, and robotics, require the use of wide angle cameras (e.g., fisheye), which allow to acquire a larger portion of the scene using a single device at the cost of the introduction of noticeable radial distortion in the images. Affine covariant feature detectors have proved successful in a variety of computer vision applications, including object recognition, image registration, and visual search. Moreover, their robustness to a series of variabilities related to both the scene and the image acquisition process has been thoroughly studied in the literature. In this paper, we investigate their effectiveness on fisheye images providing both theoretical and experimental analyses. As theoretical outcome, we show that the inherently non-linear radial distortion can be locally approximated by linear functions with a reasonably small error. The experimental analysis builds on Mikolajczyk's benchmark to assess the robustness of three popular affine region detectors (i.e., maximally stable extremal regions, and Harris and Hessian affine region detectors), with respect to different variabilities as well as to radial distortion. To support the evaluations, we rely on the Oxford data set and introduce a novel benchmark data set comprising 50 images depicting different scene categories. Experiments are carried out on rectilinear images to which radial distortion is artificially added, and on real-world images acquired using fisheye lenses. Our analysis points out that affine region detectors can be effectively employed directly on fisheye images and that the radial distortion is locally modeled as an additional affine variability.

Texture image feature extraction is one of hot topics of texture image recognition in recent years. As to this, a novel technique for texture image feature extraction based on edge affine invariant moment is presented in this paper. Firstly, each texture image is checked by a short step affine transformation Sobel algorithm initially. Then, the corresponding texture image feature named edge affine invariant moment will be calculated and added to feature vector set. Subsequently, cluster analysis will be loaded upon the set by K-means algorithm and the categorized texture image can be obtained. Three simulation experiments closed to real environment over the two well-known Brodatz and KTH-TIPS texture databases are performed in order to test the efficiency of our proposed algorithm.

Display Omitted Polar Harmonic Transform is used to detect image copy-move forgery under affine transforms.Circular domain feature extraction improves detection accuracy.Marking the innermost pixels produces fine boundary of the detected region.Post-processing filter eliminates the false detections. In copy-move forgery, the copied region may be rotated and/or scaled to fit the scene better. Most of the existing methods fail when the region is subject to affine transforms. This paper presents a method for detecting this kind of image tampering based on circular pattern matching. The image is first filtered and divided into circular blocks. A rotation and scaling invariant feature is then extracted from each block using Polar Harmonic Transform (PHT). The feature vectors are then lexicographically sorted, and the forged regions are detected by finding the similar block pairs after proper post-processing. Experimental results demonstrate the efficiency of the method.

Current techniques for shape analysis tend to seek invariance to similarity transformations (rotation, translation, and scale), but certain imaging situations require invariance to larger groups, such as affine or projective groups. Here we present a general Riemannian framework for shape analysis of planar objects where metrics and related quantities are invariant to affine and projective groups. Highlighting two possibilities for representing object boundaries-ordered points (or landmarks) and parameterized curves-we study different combinations of these representations (points and curves) and transformations (affine and projective). Specifically, we provide solutions to three out of four situations and develop algorithms for computing geodesics and intrinsic sample statistics, leading up to Gaussian-type statistical models, and classifying test shapes using such models learned from training data. In the case of parameterized curves, we also achieve the desired goal of invariance to re-parameterizations. The geodesics are constructed by particularizing the path-straightening algorithm to geometries of current manifolds and are used, in turn, to compute shape statistics and Gaussian-type shape models. We demonstrate these ideas using a number of examples from shape and activity recognition.

Great attention has been devoted to the development of shape descriptors that is the key to object recognition. Previous works have great success on either relatively simple symbols or limited transformations, e.g., translation, rotation and scaling. We propose a new affine invariant, named characteristic ratio (CHAR) that includes more points for complex symbols with rich inner structures. Moreover, we build a novel shape descriptor with CHAR values calculated on collinear points that cover the convex hull of a shape. Dynamic Time Warping algorithm is employed to compare the similarity of spectrum. The performance of the proposed descriptor is validated by the experiments compared with the classical SIFT descriptor, Shape Context (SC), recently developed Cross Ratio Spectrum (CRS) and Circular Blurred Shape Model (CBSM) on three kinds of symbols, i.e., alphanumeric characters, television networks logos and traffic signs with a wide range of transformations (2016 images in total). The results indicate a high recognition rate to severe affine deformations, and a good discriminating ability to similar symbols. We also perform the experiments on the GREC database corrupted by noise with different degrees, showing the robustness of our descriptor to noise.

Moment has been widely used for contour matching. To use the moment to achieve contour matching under affine transformations, the affine-invariant support point set (SPS) should be constructed first. Then, a novel method of acquiring SPS based on the contour projection (SPS-CP) is proposed here. For an arbitrary selected contour point, the contour is projected onto the line vertical to the vector connecting the contour centroid and the selected point, and the contour points with the sampled projection values are picked up to form the SPS-CP of the point. SPS-CP which captures the global structure of the contour is stably affine-invariant. Experiments on synthetic and real data demonstrate that moments generated from SPS-CP outperform those generated from SPSs sampled by uniform spacing or affine length.

In this paper we present an affine SIFT matching method to achieve reliable correspondence points in stereo matching with large viewpoint changes. We extended the affine invariant of the conventional SIFT approach by estimating the shape of the local patch around the interest point. Since we can obtain the scale information by SIFT detector, a second moment matrix (SMM) descriptor was employed to describe the shape. Furthermore, by comparing the shapes of the potential matches, we can normalize the template of SIFT descriptor and obtain the initial affine transformation. At last, we applied the iterative based method to achieve a fine registration with the estimated initial transformation parameters. The experiment results show that the proposed method is more robust to viewpoint changes and the accuracy of registration is better than feature based methods.

Finding correspondences between two sets of visual features of 2D image is a key problem in computer vision tasks. In practice situation, objects often undergo occlusion, background clutter, illumination and 3D viewpoint changes which increase the difficulties of matching, thus a robust matching method is needed to tackle with these problems. In this paper, we propose a robust approach to image matching based on Hessian affine region detector and local Delaunay triangulation and affine invariant geometric constraint. Firstly, Hessian affine keypoints with Scale Invariant Feature Transform(SIFT) descriptors are extracted for model and scene image, then matching the Hessian affine keypoints to get initial matched keypoints based on Euclidean distance of their (SIFT) descriptors. Third, Delaunay triangulation of the initial matched Hessian affine keypoints. Based on unique topological structure of Delaunay triangulation of a set of keypoints, we divide the keypoints into two classes, one class with the same number of neighbor triangles, the other class with different number of neighbor triangles, from the two classes of keypoints, we obtained matched triangles by local Delaunay triangulation. There are may have wrong matched triangles, we adopt local affine invariant geometric constraint to refine the matched triangles. Finally, get the final matched keypoints from the refined matched triangles. By using three pairs of images, the experimental results indicate that the proposed method can get higher correctness of image matching than RANSAC based method.

Colour, texture, shape, and relative position descriptors are fundamental visual descriptors. In particular, a relative position descriptor is a quantitative representation of the relative position of two spatial objects, and a basis from which models of spatial relationships (like inside, above, around, near) can be derived. The affine properties of visual descriptors have been the subject of much attention. Here, we focus on the PHI-descriptor, introduced in recent work. We show that it is a relative position descriptor with remarkable affine properties, and we illustrate these properties with two experiments.

paper presents remote sensing image matching using sift algorithm and affine transformation. The novelty in our approach is to find the features in the reference image and then match the input image with that of reference image using Affine Transformation. Both synthetic and real data have been considered in this work for the evaluation of the proposed methodology. After registering the image, the outliers are removed. A speeded up affine invariant detector is proposed in this paper for local feature extraction. The experimental results show that the proposed algorithm decreases the redundancy of key points and speeds up the implementation. It is able to account for differences in spectral content, rotation, scale, translation, different viewpoint, and change in illumination. The proposed technique improves the computational efficiency and decrease the storage requirement.

Recently, sparse coding has become popular for image classification. However, images are often captured under different conditions such as varied poses, scales and different camera parameters. This means local features may not be discriminative enough to cope with these variations. To solve this problem, affine transformation along with sparse coding is proposed. Although proven effective, the affine sparse coding has no constraints on the tilt and orientations as well as the encoding parameter consistency of the transformed local features. To solve these problems, we propose a Laplacian affine sparse coding algorithm which combines the tilt and orientations of affine local features as well as the dependency among local features. We add tilt and orientation smooth constraints into the objective function of sparse coding. Besides, a Laplacian regularization term is also used to characterize the encoding parameter similarity. Experimental results on several public datasets demonstrate the effectiveness of the proposed method.

In this paper, a novel affine invariant descriptor for object matching is proposed. The advantage of Maximally Stable Extremal Regions (MSER) method is applied to get the most stable regions in the image. Inside each region, we pick the seeds as keypoints since MSER regions are invariant to affine transformation. Besides that, Voronoi diagram is employed to split the image into small Voronoi cells or local regions based on the key points picked in the previous step. Finally, local features inside each local region including color, texture and geometric properties are extracted to generate the descriptor. Our experiments demonstrate that the proposed affine invariant local descriptor based on Voronoi tessellation is more stable and robust to object matching than SIFT descriptor while using the same keypoints.