Image Geometric Transformation Research Articles

Visualization of the Image Geometric Transformation Group Based on Riemannian Manifold

Geometric transformations of images are the predominant factor, which influences the effectiveness of visual tracking and detection tasks in computer vision. Naturally, although it makes significant sense to grasp the process of image geometric transformations, the numerical relationship of geometric transformations cannot be revealed directly from images themselves. Even if the geometric transformation matrices form the three-dimensional special linear group, Sl(3, ℝ) group, it is difficult to comprehend the manifold of this invisible visual motion, which resides in the high-dimensional space. Furthermore, the main challenge is the deficiency of analytic expressions of the Riemannian logarithmic map to compute the geodesic distance on the Sl(3, ℝ) manifold. Facing these issues, this paper comes up with a novel approach to visualize the geometric transformation in images by presenting a new metric, and then, computes a set of coordinate-vectors in the three-dimensional state transition space for visualization using the Riemannian stress majorization. The superiority of the presented framework for visualization, in terms of accuracy and efficiency, is demonstrated through abundant experiments on aerial images and moving objects.

Computer Vision in Control and Robotics for Educational Purposes

Abstract The paper is devoted to computer vision education for ITMO University students specializing in control systems and robotics. The set of laboratory works are attached. Several examples of finished works are provided. The topics of the laboratory course consists of histograms, profiles, projections, image geometric transformations, filtering and edges detection, images segmentation, Hough transformation, image morphologic analysis.

A Privacy-Preserving Filter for Oblique Face Images Based on Adaptive Hopping Gaussian Mixtures

Photographs taken in public places often contain faces of bystanders thus leading to a perceived or actual violation of privacy. To address this issue, we propose to pseudo-randomly modify the appearance of face regions in the images using a privacy filter that prevents a human or a face recogniser from inferring the identity of people. The filter, which is applied only when the resolution is high enough for a face to be recognisable, adaptively distorts the face appearance as a function of its resolution. Moreover, the proposed filter locally changes the values of its parameters to counter attacks that attempt to estimate them. The filter exploits both global adaptiveness to reduce distortion and local parameter hopping to make their estimation difficult for an attacker. In order to evaluate the efficiency of the proposed approach, we consider an important scenario of oblique face images: photographs taken with low altitude Micro Aerial Vehicles (MAVs). We use a state-of-the-art face recognition algorithm and synthetically generated face data with 3D geometric image transformations that mimic faces captured from an MAV at different heights and pitch angles. Experimental results show that the proposed filter protects privacy while reducing distortion, and is also robust against attacks.

Geometric transformation of images and LiDAR point clouds under quadratic constraint

ABSTRACTThe combination of point and linear features can strengthen the robustness and accuracy of the registration of image and light detection and ranging (LiDAR) point clouds. The key point of registration is the establishment of a geometric transformation model. This paper proposes a quadratic-constraint-based geometric transformation (QCGT) line model, in which combines point and linear features, and simultaneously takes the orientation and position of the line into account. The coordinates of points and lines uniformly described by line model in the same mathematical framework are used to construct a coplanarity equation. The data set of International Society for Photogrammetry and Remote Sensing (ISPRS) test project is used, and the robustness and efficiency of QCGT is verified by progressive experiments. The experimental results have shown that QCGT is feasible and can achieve more reliable results than the traditional method. The geometric constraints of the line model are enhanced due to the quadratic constraint, solving the problems of the different mathematical representation of geometric features and reducing the complexity of transformation.

Fast and accurate Slicewise OutLIer Detection (SOLID) with informed model estimation for diffusion MRI data

The accurate characterization of the diffusion process in tissue using diffusion MRI is greatly challenged by the presence of artefacts. Subject motion causes not only spatial misalignments between diffusion weighted images, but often also slicewise signal intensity errors. Voxelwise robust model estimation is commonly used to exclude intensity errors as outliers. Slicewise outliers, however, become distributed over multiple adjacent slices after image registration and transformation. This challenges outlier detection with voxelwise procedures due to partial volume effects. Detecting the outlier slices before any transformations are applied to diffusion weighted images is therefore required. In this work, we present i) an automated tool coined SOLID for slicewise outlier detection prior to geometrical image transformation, and ii) a framework to naturally interpret data uncertainty information from SOLID and include it as such in model estimators. SOLID uses a straightforward intensity metric, is independent of the choice of the diffusion MRI model, and can handle datasets with a few or irregularly distributed gradient directions. The SOLID-informed estimation framework prevents the need to completely reject diffusion weighted images or individual voxel measurements by downweighting measurements with their degree of uncertainty, thereby supporting convergence and well-conditioning of iterative estimation algorithms. In comprehensive simulation experiments, SOLID detects outliers with a high sensitivity and specificity, and can achieve higher or at least similar sensitivity and specificity compared to other tools that are based on more complex and time-consuming procedures for the scenarios investigated. SOLID was further validated on data from 54 neonatal subjects which were visually inspected for outlier slices with the interactive tool developed as part of this study, showing its potential to quickly highlight problematic volumes and slices in large population studies. The informed model estimation framework was evaluated both in simulations and in vivo human data.

Ultra-fast basic geometrical transformations on linear image data structure

Abstract This paper presents a general, ultra-fast approach for geometrical image transformations, based on the usage of linear lookup hash tables. The new method is developed to fix distortions on document images as part of a real-time optical character recognition (OCR) system. The approach is generalized and uses linear image representation combined with pre-computed lookup tables. Backward mapping is used for generation of lookup tables, while forward mapping is presented as an alternative and more efficient mapping model for specific cases. Also, a theoretical space and time complexity analysis of the proposed method is provided. To achieve maximal computational performance, pointer arithmetic and highly-optimized low-level machine code implementations are provided, including the specialized implementations for horizontal mirror, vertical mirror, and 90° rotation. Also, a modified variant of the approach, based on auto-generated machine code is presented. Very high computational performances are achieved at the expense of memory usage. The performances from the perspective of time complexity are analyzed and compared with classical implementation, FPGA implementation, and other implementations of the image rotation. Numerical results are given for a set of different PC specifications to provide full insight into the implementation performances. The processing time for very large images are below 200 ms for backward mapping and below 100 ms for forward mapping for most machines, which is 30–60 times faster than the classical implementation, 5–20 times faster than the FPGA implementation, and up to 6 times faster than other implementations of image rotation. Original documents belonging to Nikola Tesla are used for visual demonstration of performance.

Quantum realization of the bilinear interpolation method for NEQR

In recent years, quantum image processing is one of the most active fields in quantum computation and quantum information. Image scaling as a kind of image geometric transformation has been widely studied and applied in the classical image processing, however, the quantum version of which does not exist. This paper is concerned with the feasibility of the classical bilinear interpolation based on novel enhanced quantum image representation (NEQR). Firstly, the feasibility of the bilinear interpolation for NEQR is proven. Then the concrete quantum circuits of the bilinear interpolation including scaling up and scaling down for NEQR are given by using the multiply Control-Not operation, special adding one operation, the reverse parallel adder, parallel subtractor, multiplier and division operations. Finally, the complexity analysis of the quantum network circuit based on the basic quantum gates is deduced. Simulation result shows that the scaled-up image using bilinear interpolation is clearer and less distorted than nearest interpolation.

DETECTION AND TRACKING OF MOVING OBJECTS WITH REAL-TIME ONBOARD VISION SYSTEM

Abstract. Detection of moving objects in video sequence received from moving video sensor is a one of the most important problem in computer vision. The main purpose of this work is developing set of algorithms, which can detect and track moving objects in real time computer vision system. This set includes three main parts: the algorithm for estimation and compensation of geometric transformations of images, an algorithm for detection of moving objects, an algorithm to tracking of the detected objects and prediction their position. The results can be claimed to create onboard vision systems of aircraft, including those relating to small and unmanned aircraft.

Efficient character segmentation approach for machine-typed documents

In this paper an efficient approach for segmentation of the individual characters from scanned documents typed on old typewriters is proposed. The approach proposed in this paper is primarily intended for processing of machine-typed documents, but can be used for machine-printed documents as well. The proposed character segmentation approach uses the modified projection profiles technique which is based on using the sliding window for obtaining the information about the document image structure. This is followed by histogram processing in order to determine the spaces between lines, words and characters in the document image. The decision-making logic used in the process of character segmentation is describes and represents the most an integral aspect of the proposed technique. Beside the character segmentation approach, the ultra-fast architecture for geometrical image transformations, which is used for image rotation in the process of skew correction, is presented, and its fast implementation using pointer arithmetic and a highly optimized low-level machine routine is provided. The proposed character segmentation approach is semi-automatic and uses threshold values to control the segmentation process. Provided results for segmentation accuracy show that the proposed approach outperforms the state-of-the-art approaches in most cases. Also, the results from the aspect of the time complexity show that the new technique performs faster than state-of-the-art approaches and can process even very large document images in less than one second, which makes this approach suitable for real-time tasks. Finally, visual demonstration of the proposed approach performances is achieved using original documents authored by Nikola Tesla.

A Robust Digital Watermarking Algorithm for Copyright Protection of Aerial Photogrammetric Images

AbstractCurrent research on digital watermarking for the copyright protection of digital multimedia data has led to fairly advanced techniques with fruitful results. However, there remains a lack of research on digital watermarking for geospatial data, which is very costly to produce but is of great importance and with wide application. In this study an analysis and discussion of digital watermarking is carried out for digital aerial photogrammetric images. Focusing on the requirements for the main applications of such images, a feature‐based digital watermarking algorithm is proposed. Testing and analysis of the robustness of the watermark is performed to achieve the goal of copyright protection, even after image processing and geometric transformation have been undertaken on the watermarked image. Furthermore, the image quality is (almost) preserved to avoid detrimental effects on subsequent applications. The experimental results prove that the proposed watermarking method has a certain degree of robustness and can resist most types of image‐processing and geometric attacks, while maintaining the data quality of the aerial images.

Geometric transformations of multidimensional color images based on NASS

We present quantum algorithms to realize geometric transformations (two-point swappings, symmetric flips, local flips, orthogonal rotations, and translations) based on an n-qubit normal arbitrary superposition state (NASS). These transformations are implemented using quantum circuits consisting of basic quantum gates, which are constructed with polynomial numbers of single-qubit and two-qubit gates. Complexity analysis shows that the global operators (symmetric flips, local flips, orthogonal rotations) can be implemented with O(n) gates. The proposed geometric transformations are used to facilitate applications of quantum images with low complexity.

영상 분할을 위한 HOG 가이드 필터를 적용한 엣지 보존 기술

The edge preserving method is important for image storage and geometric transformation. In this paper, we propose a new edge preserving method using HOG-Guide filter for image segmentation. In our approach, we extract edge information using gradient histogram to set HOG guide line. Then, we use HOG guide line to smooth image. With two to four iterations of smoothing operations, we finally obtain desirable edge preserved image. Our experimental results showed good performances showing that our proposed method is better than other methods.

Investigation of the generalizing capabilities of convolutional neural networks in forming rotation-invariant attributes

This paper gives the results of a study of the possibilities of convolutional neural networks to generalize knowledge concerning primitive geometrical image transformations when solving pattern-recognition problems of handwritten numerals. Experiments were directed to the study of how the recognition of patterns in arbitrary orientations is affected by broadening the training sample with rotated images. Results are presented for convolutional neural networks of two architectures, showing that, to ensure rotation-invariant recognition, it is necessary for all classes of images in the entire range of rotations to be present in the training sample.

SU‐E‐T‐04: 3D Dose Based Patient Compensator QA Procedure for Proton Radiotherapy

Purpose:In proton double‐scattering radiotherapy, compensators are the essential patient specific devices to contour the distal dose distribution to the tumor target. Traditional compensator QA is limited to checking the drilled surface profiles against the plan. In our work, a compensator QA process was established that assess the entire compensator including its internal structure for patient 3D dose verification.Methods:The fabricated patient compensators were CT scanned. Through mathematical image processing and geometric transformations, the CT images of the proton compensator were combined with the patient simulation CT images into a new series of CT images, in which the imaged compensator is placed at the planned location along the corresponding beam line. The new CT images were input into the Eclipse treatment planning system. The original plan was calculated to the combined CT image series without the plan compensator. The newly computed patient 3D dose from the combined patientcompensator images was verified against the original plan dose. Test plans include the compensators with defects intentionally created inside the fabricated compensators.Results:The calculated 3D dose with the combined compensator and patient CT images reflects the impact of the fabricated compensator to the patient. For the test cases in which no defects were created, the dose distributions were in agreement between our method and the corresponding original plans. For the compensator with the defects, the purposely changed material and a purposely created internal defect were successfully detected while not possible with just the traditional compensator profiles detection methods.Conclusion:We present here a 3D dose verification process to qualify the fabricated proton double‐scattering compensator. Such compensator detection process assesses the patient 3D impact of the fabricated compensator surface profile as well as the compensator internal material and structure changes.This research receives funding support from CURA Medical Technologies.

Single Sample Face Recognition using LGBP and Locality Preserving Discriminant Analysis

On single sample condition, current face recognition algorithm yields serious performance drop or even fail to work, therefore a face recognition algorithm based on LGBP and locality preserving discriminant analysis (LPDA) was proposed. Image enhancement and geometric transformation were firstly introduced to single sample face image for face reconstruction, making reconstruct image and original counterpart as a new training sample set. The feature of LGBP was then adopted for face image feature extraction. Afterwards LPDA was used for feature dimension reduction. Classification was finally accomplished by Euclidean distanceNearest Neighbour Classifier. The validity of this algorithm was testified by ORL database, Yale database and FERET database.

法工学鑑定のための半自動画像幾何変換プログラムの開発

法工学鑑定のための半自動画像幾何変換プログラムの開発

The Epipolarity Constraint in Stereo-Radargrammetric DEM Generation

For stereometric processing of optical image pairs, the concept of epipolar geometry is widely used. It helps to reduce the complexity of image matching, which can be seen to be the most crucial step within a workflow to generate digital elevation models. In this paper, it is shown that this concept is also applicable to the cocircular geometry of synthetic aperture radar (SAR) image pairs. First, it is proven that, for any feasible SAR acquisition, the deviation from true epipolar geometry is within subpixel range and therefore acceptably small. Based on this, we propose a method to create “epipolar” geometry for arbitrary stereo configurations of any SAR sensor through appropriate geometric image transformations. Consequently, the semiglobal matching (SGM) algorithm can be applied, which is restricted to epipolar geometry and is thus known to be highly efficient. This innovative approach, integrating both epipolar transformation and SGM, has been applied to a TerraSAR-X stereo data set. Its benefit has been demonstrated in a comparative assessment with respect to results, which have been previously achieved on the same test data using state-of-the-art stereometric methods.

Robust Differential Circle Patterns based on fuzzy membership-pooling: A novel local image descriptor

This paper presents a novel image descriptor, which is robust to a variety of photometric and geometric image transformations. Specifically, the Robust Differential Circle Patterns (RDCP) are proposed to encode the continuous intensity changes along the circular-shaped structures around each pixel. Compared to the pixel-wise feature computing schemes, RDCP is capable of describing relatively large local structures in the image. While in the descriptor constructing stage, the proposed fuzzy membership-pooling algorithm can not only capture the local structure of the interest region but also achieve rotation invariance inherently. Experimental results on three popular datasets (Oxford dataset, Patch dataset, and Ukbench dataset) demonstrate the superiority of proposed method over the state-of-the-art algorithms under various image transformations such as rotation and scaling changes, viewpoint changes, image blurring, JPEG compression, illumination changes, and image noise.

Analysis of Gaussian-Hermite Moment Invariants on Image Geometric Transformation

Gaussian-Hermite moments and their invariants have been widely used in image processing and pattern recognition. The moments are strictly invariant for the continuous function. However, the digital images are discrete. The image function and the moment imvariants may change during image geometric transformation. To address this problem, an analysis with respect to the fluctuation of moment invariants on image geometric transformation is presented. The guidance is provided as well to minimizing the fluctuation of the Gaussian-Hermite moments.

Analysis of Gaussian-Hermite Moment Invariants on Image Geometric Transformation

Gaussian-Hermite moments and their invariants have been widely used in image processing and pattern recognition. The moments are strictly invariant for the continuous function. However, the digital images are discrete. The image function and the moment imvariants may change during image geometric transformation. To address this problem, an analysis with respect to the fluctuation of moment invariants on image geometric transformation is presented. The guidance is provided as well to minimizing the fluctuation of the Gaussian-Hermite moments.