In order to ensure that SAR scene matching aided navigation system can acquire the position errors and yawing errors simultaneously, we propose an image matching algorithm based on Scale Invariant Feature Transform (SIFT). However, the SIFT is proposed for optical image, and its performance degrades when used in SAR image. To enhance the adaptability of SIFT, two ways are employed. One is the a...

In this paper, we present an efficient multi-scale similarity matching method for shape-based image indexing and retrieval. This method is affine-invariant and stable against noise and shape deformations. Shapes which have undergone mirror reflection can also be retrieved in a unified manner. In this approach, similarity matching is cast as correspondence matching of two shapes which is then so...

Biomedical systems have been using ontology matching as a primary technique for heterogeneity resolution. However, the natural intricacy and vastness of biomedical data have compelled biomedical ontologies to become large-scale and complex; consequently, biomedical ontology matching has become a computationally intensive task. Our parallel heterogeneity resolution system, i.e., SPHeRe, is built...

A novel BA complex network model of color space is proposed based on two fundamental rules of BA scale-free network model: growth and preferential attachment. The scale-free characteristic of color space is discovered by analyzing evolving process of template's color distribution. And then the template's BA complex network model can be used to select important color pixels which have much large...

In this paper, we propose fast string matching system using GPU for large scale string matching. The key of our proposed system is the use of bit-parallel pattern matching approach for compact NFA representation and fast simulation of NFA transition on GPU. In the experiments, we show the usefulness of our proposed pattern matching system.

We develop a robust multi-scale structure-aware neural network for human pose estimation. This method improves the recent deep conv-deconv hourglass models with four key improvements: (1) multi-scale supervision to strengthen contextual feature learning in matching body keypoints by combining feature heatmaps across scales, (2) multi-scale regression network at the end to globally optimize the ...

the most important factor in donor-recipient matching for hematopoietic stem cell transplantation is their hla typing. for many patients, we can not find a full-matched donor. in high risk patients, one locus  mismatched related donors are suitable alternatives. (1, 2) since the matching of patients and their siblings usually is based on low resolution hla typing, the matching of one locus mism...

Stereo image matching is to find conjugate points on overlapping images pair, i.e., search for the same image pixels of a ground point on the left and right images. When the image orientation parameters are known, the 3D (X,Y,Z) coordinates of the ground point can be calculated. This process is the core part of DEM (Digital Elevation Model) generation in digital photogrammetry. Research on this...

One of the main challenges confronting high-resolution remote sensing image matching is how to address the issue of geometric deformation between images, especially when the images are obtained from different viewpoints. In this paper, a robust matching method for Unmanned Aerial Vehicle images of different viewpoint angles based on regional coherency is proposed. The literature on the geometri...