Towards a Robust Scale Invariant Feature Correspondence (original) (raw)

A More Robust Feature Correspondence for more Accurate Image Recognition

2014 Canadian Conference on Computer and Robot Vision, 2014

In this paper, a novel algorithm for finding the optimal correspondence between two sets of image features has been introduced. The proposed algorithm pays attention not only to the similarity between features but also to the spatial layout of every matched feature and its neighbors. Unlike related methods that use geometrical relations between the neighboring features, the proposed method employes topology that survives against different types of deformations like scaling and rotation; resulting in more robust matching. The features are expressed as an undirected graph where every node represents a local feature and every edge represents adjacency between them. The topology of the resulting graph can be considered as a robust global feature of the represented object. The matching process is modeled as a graph matching problem; which in turn is formulated as a variation of the quadratic assignment problem. In this variation, a number of parameters are used to control the significance of global vs. local features to tune the performance and customize the model. The experimental results show a significant improvement in the number of correct matches using the proposed method compared to different methods.

Reducing ambiguity in feature point matching by preserving local geometric consistency

2008 15th IEEE International Conference on Image Processing, 2008

In this paper, feature point matching is formulated as an optimization problem in which the uniqueness condition is constrained. We propose a novel score function based on homography-induced pairwise constraints, and a novel optimization algorithm based on relaxation labeling. Homographyinduced pairwise constraints are effective for image pairs with viewpoint or scale changes, unlike previous pairwise constraints. The proposed optimization algorithm searches for a uniqueness-constrained solution, while the original relaxation-labeling algorithm is appropriate for finding manyto-one correspondences. The effectiveness of the proposed method is shown by experiments involving image pairs with viewpoint or scale changes in addition to repeated textures and nonrigid deformation. The proposed method is also applied to object recognition, giving some promising results.

Object Matching in the Presence of Non-Rigid Deformations Close to Similarities

2007 IEEE 11th International Conference on Computer Vision, 2007

In this paper we address the problem of object retrieval based on scale-space interest points, namely top-points. The original retrieval algorithm can only cope with scale-Euclidean transformations. We extend the algorithm to the case of non-rigid transformations like affine and perspective transformations and investigate its robustness. The proposed algorithm is proven to be highly robust under various degrading factors, such as noise, occlusion, rendering artifacts, etc. and can deal with multiple occurrences of the object.

Robust feature matching via advanced neighborhood topology consensus

Neurocomputing, 2021

Feature matching is one of the key techniques in many vision-based tasks, which aims to establish reliable correspondences between two sets of features. In this paper, we present a new feature matching method, which formulates the matching of two feature sets as a mathematical model based on two common consistency constraints. We first propose an advanced consensus of neighborhood topology, which can better exploit the consensus of topological structures to identify inliers. In order to have reliable neighborhood information for the feature points, a subset with high percentage inliers obtained by a guided matching strategy from the putative matches for the neighborhood construction is used. We demonstrate the advantages of our proposed method on various real image pairs. The results demonstrate that the proposed method is superior to the state-of-the-art feature matching methods.

Deformation invariant image matching based on dissimilarity of spatial features

In this paper, a new deformation invariant image matching method, known as spatial orientation feature matching (SOFM), is presented. A new similarity value, which measures the similarity of the signal through the path based on triple-wise signal eigenvector correlation, is proposed. The proposed method extracts similarity feature values by relying on the distinct path between two specific interest points and following the alternation of the signal while traversing the path. Because these similarity values of the path are deformation invariant, the proposed method supports various types of transformation in the original image, such as scale, translation, rotation, intensity noises and occlusion. Moreover, the triple-wise similarity scores are accumulated in a 2-D similarity space; thus, robust matched correspondence points are obtained using cumulative similarity space. SOFM was compared to the most recent related methods using corner correspondence (CC) and precision-recall evaluation metrics. The findings confirmed that SOFM provides higher correspondence ratios, and the results indicate that it outperforms currently utilized methods in terms of accuracy and generalization.

A framework for efficient correspondence using feature interrelations

2008 19th International Conference on Pattern Recognition, 2008

We propose a formulation for solving the point pattern correspondence problem, relying on transformation invariants. Our approach can accommodate any degree of descriptors thus modeling any kind of potential deformation according to the needs of each specific problem. Other potential descriptors such as color or local appearance can also be incorporated. A brief study on the complexity of the methodology is made which proves to be inherently polynomial while allowing for further adjustments via thresholding. Initial experiments on both synthetic and real data demonstrate its potentials in terms of accuracy and robustness to noise and outliers.

The Representation and Matching of Images Using Top Points

Journal of Mathematical Imaging and Vision, 2009

In previous work, singular points (or top points) in the scale space representation of generic images have proven valuable for image matching. In this paper, we propose a novel construction that encodes the scale space description of top points in the form of a directed acyclic graph. This representation allows us to utilize coarse-tofine graph matching algorithms for comparing images represented in terms of top point configurations instead of using solely the top points and their features in a point matching algorithm, as was done previously. The nodes of the graph represent the critical paths together with their top points. The edge set captures the neighborhood distribution of vertices in scale space, and is constructed through a hierarchical tessellation of scale space using a Delaunay triangulation of the top points. We present a coarse-to-fine many-tomany matching algorithm for comparing such graph-based representations. The algorithm is based on a metric-tree representation of labeled graphs and their low-distortion embeddings into normed vector spaces via spherical encoding. This is a two-step transformation that reduces the matching problem to that of computing a distribution-based dis-tance measure between two such embeddings. To evaluate the quality of our representation, four sets of experiments are performed. First, the stability of this representation under Gaussian noise of increasing magnitude is examined. Second, a series of recognition experiments is run on a face database. Third, a set of clutter and occlusion experiments is performed to measure the robustness of the algorithm. Fourth, the algorithm is compared to a leading interest pointbased framework in an object recognition experiment.

Scale invariant and deformation tolerant partial shape matching

Image and Vision Computing, 2011

We present a novel approach to the problem of establishing the best match between an open contour and a part of a closed contour. At the heart of the proposed scheme lies a novel shape descriptor that also permits the quantification of local scale. Shape descriptors are computed along open or closed contours in a spatially non-uniform manner. The resulting ordered collections of shape descriptors constitute the global shape representation. A variant of an existing Dynamic Time Warping (DTW) matching technique is proposed to handle the matching of shape representations. Due to the properties of the employed shape descriptor, sampling scheme and matching procedure, the proposed approach performs partial shape matching that is invariant to Euclidean transformations, starting point as well as to considerable shape deformations. Additionally, the problem of matching closed-to-closed contours is naturally treated as a special case. Extensive experiments on benchmark datasets but also in the context of specific applications, demonstrate that the proposed scheme outperforms existing methods for the problem of partial shape matching and performs comparably to methods for full shape matching.

Evaluating the robustness of feature correspondence using different feature extractors

2014 19th International Conference on Methods and Models in Automation and Robotics (MMAR), 2014

The importance of choosing a suitable feature detector and descriptor to find the optimal correspondence between two sets of image features has been highlighted. In this direction, this paper presents an evaluation of some well known feature detectors and descriptors; including HARRIS-FREAK, HESSIAN-SURF, MSER-SURF, and FAST-FREAK; in the search for an optimal detector and descriptor pair that best serves the matching procedure between two images. The adopted matching algorithm pays attention not only to the similarity between features but also to the spatial layout in the neighborhood of every matched feature. The experiments conducted on 50 images; representing 10 objects from COIL-100 data-set with extra synthetic deformations; reveal that HARRIS-FREAK's extractor results in better feature correspondence.

A global correspondence for scale invariant matching using mutual information and the graph search

2006

In this paper we propose a novel approach to find a global correspondence between two images by maximizing mutual information in the presence of large scale changes and rotations. Our approach combines the local descriptors with global search. We have tested our method on various test images and compared the matching performance with the SIFT descriptors. The experimental results show that the proposed local descriptor and graph-based search provides robust point matching for scale, rotation and illumination changes.