Feature Matching Method Research Articles

Optimum Matching of Geometric Features for Material Metamorphosis in Heterogeneous Object Modeling

AbstractThis paper presents a new methodology of material blending for heterogeneous object modeling by matching the material governing features for designing a heterogeneous object. The proposed geometric feature matching method is used to generate non-self-intersecting and non-twisted connecting surfaces. The proposed method establishes point-to-point correspondence represented by a set of connecting lines between two material directrices. To blend the material features between the directrices, a heuristic optimization method developed with the objective is to maximize the sum of the inner products of the unit normals at the end points of the connecting lines and minimize the sum of the lengths of connecting lines. By subdividing the connecting lines into equal number of segments, one can construct a series of intermediate piecewise curves that represent the material metamorphosis between the governing material features. Implementation and examples are also presented.

Image registration using the Walsh transform

This paper presents a new algorithm which can be used to register images of the same or different modalities, e.g., images with multiple channels, such as X-rays, temperature or elevation, or simply images of different spectral bands. In particular, a correlation-based scheme is used, but instead of gray values, it correlates numbers formulated by different combinations of the extracted local Walsh coefficients of the images. Each image patch is expanded in terms of Walsh basis functions. Each Walsh basis function can be thought of as measuring a different aspect of local structure, e.g., horizontal edge, corner, etc. The coefficients of the expansion, therefore, can be thought of as dense local features, estimating at each point the degree of presence of, for example, a horizontal edge, a corner with contrast of a certain type, etc. These coefficients are normalized and used as digits in a chosen number system which allows one to create a unique number for each type of local structure. The choice of the basis of the number system allows one to give different emphasis to different types of local feature (e.g., corners versus edges), and, thus, the method we present forms a unified framework in terms of which several feature matching methods may be interpreted. The algorithm is compared with wavelet and contour based approaches, using simulated and real images. The two images are assumed to differ from each other by a rotation and a translation only.

Three-dimensional point cloud registration by matching surface features with relaxation labeling method

Automated approaches for the conversion of multiple overlapped three-dimensional (3D) point clouds into an integrated surface shape measurement in the form of a complete polygon surface are important in the general field of reverse engineering. Traditionally, the conversion process is achieved in a semi-automated manner that requires extensive user interaction. In this work, automated methods for point set registration are developed and experimentally validated using polygon surface reconstruction to represent raw, 3D point clouds obtained from non-contacting measurement systems. Using local differential properties extracted from the polygon surface representation for a measurement data set, a robust sculpture surface feature-matching method is described for automatically obtaining the initial orientation and mismatch estimates for each overlapped data set. Using both simulated and measured experimental data to quantify the performance of the method, it is shown that differential local surface features are appropriate metrics for identifying common features and initializing the relative positions of individual point clouds, thereby providing the basis for automating the registration and integration processes while improving the speed of the surface distance minimization method developed for the initial registration process.

A New Method for Automatic Detection of ShipTargets in SAR Images

Automatic interpretation of synthetic aperture radar (SAR) images is one of the most interesting and important application fields in image processing. Focusing on the medium resolution SAR images and combining with the previous algorithms, a novel technique to detecting ship targets from coastal regions in a fully automatic way is proposed in this paper. This paper presents current progress made on the detection model. In this method, sea regions and land regions were detected firstly according to the corresponding decimation algorithm and thresholding technique. Then the land regions can be masked out from the SAR image based on mapping principle of the image datas. And In order to obtain a high reliability and robustness, the processed processing chain detects possible targets by first searching in parallel for bright spots, i.e. potential ship bodies. Therefore, the sea image with ship targets is processed with maximum entropic algorithm, and we can extract the regions of interest which contain candidate ship targets. And the authentic ship targets were eventually detected by utilizing the method of feature matching. Finally, for later classification and recognition we calculate the feature parameters of every ship. Experimental results on 50 different SAR images are given to demonstrate that this method can automatically detect ship targets from SAR images with high efficiency.

Directional Filter Bank-Based Fingerprint Feature Extraction and Matching

The paper presents a new filter bank-based fingerprint feature extraction and matching method without needing to detect minutiae. The proposed method decomposes a fingerprint image into eight directional subband outputs using a directional filter bank (DFB) and then obtains directional energy distributions for each block from the decomposed subband outputs. Only dominant directional energy components are employed as elements of the input feature vector, which serves to reduce noise and improve efficiency. For the rotational alignment, additional input feature vectors in which various rotations are considered are extracted, and these input feature vectors are compared with the enrolled template feature vector. The proposed method significantly reduces the memory cost and processing time associated with verification, primarily because of the efficient DFB structure and the exploitation of directional specific information. Experimental results validate the effectiveness of the proposed method in extracting fingerprint features and achieving good performance.

최소고유치로 분할된 영상의 영역기반 유사도를 이용한 목표추적

The main problems of computational complexity in object tracking are definition of objects, segmentations and identifications in non-structured environments with erratic movements and collisions of objects. The object's information as a region that corresponds to objects without discriminating among objects are considered. This paper describes the algorithm that, automatically and efficiently, recognizes and keeps tracks of interest-regions selected by users in video or camera image sequences. The block-based feature matching method is used for the region tracking. This matching process considers only dominant feature points such as corners and curved-edges without requiring a pre-defined model of objects. Experimental results show that the proposed method provides above 96% precision for correct region matching and real-time process even when the objects undergo scaling and 3-dimen-sional movements In successive image sequences.

An Approach to Single Image Automatic Orientation and Point Determination by Using Ortho‐Images and a Dtm

This paper describes an approach to single image automatic orientation and point determination by using current ortho‐images and a DTM, and the experience gained in its implementation. The procedure proposed automatically extracts and matches feature points in evenly distributed patches on aerial images and ortho‐images. A large number of image measurements (up to several thousand) are obtained in this process and are included in a robust space resection to determine the orientation parameters of the aerial image. For point determination with a single image, a method is formalised which integrates the DTM interpolation into the space resection so that the 3D ground coordinates of the image points can be determined in a unified mathematical model. Tests and analyses of this method show that the large number of automatic image measurements relieves the requirement for complicated and precise feature extraction and matching methods. The ground points obtained from single image intersection have an accuracy of approximately 1 pixel in planimetry, which fulfils the requirement for ortho‐image updating. The elevation accuracy is mainly dependent on the quality of the current DTM and the interpolation method applied to it.

A General Method for Geometric Feature Matching and Model Extraction

Popular algorithms for feature matching and model extraction fall into two broad categories: generate-and-test and Hough transform variations. However, both methods suffer from problems in practica...

Real-Time Feature Matching in Image Sequences for Non-Structured Environments. Applications to Vehicle Guidance

This paper describes an integrated vehicle control system with visual feedback. A general-purpose, low-level feature matching method, able to work in real time without any strict assumptions on the environment structure or camera parameters, generates low-level matching results, which are used as source of data for applications like mobile object tracking, among others. A generalized predictive path-tracking control approach keeps the vehicle on the trajectory defined by the moving target. In the low-level matching process, block-based features (windows) are selected and tracked along a stream of monocular images; least residual square error and similarity between clusters of features are used as constraints to select the right matching pair between multiple candidates. Real-time performance is achieved through optimized algorithms and a parallel DSP-based multiprocessor system implementation. Object detection and tracking is motion-based, and does not require a predefined model of the target. The integrated control system has been tested on the ROMEO-3R experimental vehicle.

A prototype indexing approach to 2-D object description and recognition

This paper introduces an indexing approach to 2-D object description and recognition in the presence of rotation, translation, scale, and partial occlusion of objects. The scheme is based on the polygonal approximations of object boundaries. To obtain stable features to represent 2-D objects, three polygonal approximations are computed for the objects using different line fitting tolerances. Local structural features of objects are extracted, which consist of line and circular arc elements. The indexing entries computed based on the initial features are employed for fast access to the object-model database and generating hypotheses. A dynamic feature-matching method is designed to implement final-shape matching by evaluating and verifying the hypotheses. The system is tested with both manufactured workpieces and prototype-test-objects, and the experimental results are presented.

Exploiting Walsh-based attributes to stereo vision

This paper presents a new stereo feature matching method that extracts the disparity measure for the recovery of depth information in 2-D stereo images. In this method, a stereo pair of images are transformed row for row into strings carrying spatially varying Walsh coefficients as attributes. The significance of the information carried by the Walsh coefficients is expressed mathematically and through experimental evaluations. The choice of the Walsh coefficients in contrast to other orthogonal transform coefficients is a direct result of their computational simplicity and their interpretative meaning in terms of the information contained in the spatial domain. The string-to-string matching technique used to bring the two strings into correspondence integrates, into a unified process, both the feature detection and the feature matching processes. The uniqueness and the ordering constraints are explicitly integrated into this string-to-string matching technique. Both the issues of Gaussian filtering and the importance of enforcing the epipolar line constraint are addressed in view of the application of the proposed method. Experimental results are given and assessed in terms of both the accuracy in stereo matching and the ensuing computational requirements.

Robust automatic target recognition using a localized boundary representation

A localized classification approach which includes a localized target boundary representation, a set of local features to characterize parts of a target boundary, and a feature matching method is developed to classify highly degraded targets. Each pixel on the target boundary is represented by the perpendicular Euclidean distance between the boundary pixel and the chord connecting the end-points of a window centered on the boundary pixel. The resulting localized representation is quite robust with respect to noise and missing segments in the targets. A local feature is the segment of the localized representation between two points selected on the target boundary. The two points on the boundary may be specified or randomly selected. The reference features of a hypothesized target class are compared with segments of the localized representation of the test target to determine a dissimilarity measure between the hypothesized target class and the test target. Segments of the test target may also be matched with the reference localized contour sequences of the targets. The test target is assigned to a target class using a minimum mismatch rule. Results from a series of experiments conducted on three targets show that it is possible to classify targets experiencing high levels of noise and high percentages of missing segments in partial targets.

Automatic feature point extraction and tracking in image sequences for arbitrary camera motion

An automatic egomotion compensation based point correspondence algorithm is presented. A basic problem in autonomous navigation and motion estimation is automatically detecting and tracking features in consecutive frames, a challenging problem when camera motion is significant. In general, feature displacements between consecutive frames can be approximately decomposed into two components: (i) displacements due to camera motion which can be approximately compensated by image rotation, scaling, and translation; (ii) displacements due to object motion and/or perspective projection. In this paper, we introduce a two-step approach: First, the motion of the camera is compensated using a computational vision based image registration algorithm. Then consecutive frames are transformed to the same coordinate system and the feature correspondence problem is solved as though tracking moving objects for a stationary camera. Methods of subpixel accuracy feature matching, tracking and error analysis are introduced. The approach results in a robust and efficient algorithm. Results on several real image sequences are presented.

Fast feature matching using random field models for image registration

A new feature-matching method is presented for accomplishing image registration, based on two random field image models: SAR (spatial autoregressive) and GMRF (Gaussian-Markov random field). The model parameters estimated by the least squares (LS) method are used for feature comparison. A fast algorithm for calculating the model parameters is developed. An efficient hardware architecture is also presented. The analysis of the computational complexity indicates that this method is significantly faster than the widely used normalized cross-correlation method.