A multi-scale bilateral structure tensor based corner detector
read more
Citations
Detecting Hand Bone Fractures in X-Ray Images
A combined post-filtering method to improve accuracy of variational optical flow estimation
Detecting Curvilinear Features Using Structure Tensors
Extended structure tensors for multiple directionality estimation
Improved structure-adaptive anisotropic filter based on a nonlinear structure tensor
References
A Combined Corner and Edge Detector
Bilateral filtering for gray and color images
SUSAN—A New Approach to Low Level Image Processing
Gray-level corner detection
Robust image corner detection through curvature scale space
Related Papers (5)
Frequently Asked Questions (11)
Q2. Why do the ramp edges show corner-like structures in a fine scale?
Due to digitization in the square grid, in discrete images often the ramp edges will show corner-like trivial structures in a fine scale.
Q3. What is the basic idea of the proposed method?
The basic idea of the proposed method lies in that both the spatial and gradient distances should be involved in smoothing the structure tensor elements.
Q4. How can the authors obtain the image at different scales?
The images at different scales can be obtained by smoothing the original image The authorwith a series of Gaussian kernels Kς with different standard deviations ς.
Q5. Why is the proposed nonlinear structure tensor A, so sensitive?
Because the proposed nonlinear bilateral structure tensor Aρ,σ incorporates the local gradient information in the structure tensor construction, it could achieve much higher true detection and localization accuracies than the linear structure tensor used in the original Harris corner detector.
Q6. What is the structure tensor for a gray level image?
The structure tensor for a gray level image The authoris a 22 symmetric matrix that contains in each element the orientation and intensity information in a local area.
Q7. What is the weight distribution of the pixel in the corner?
for the pixels lying on the same edge, the ones near to the corner pixel have higher weights than the others because they have shorter spatial distances to the corner point.
Q8. What is the way to measure the cornerness of a pixel?
if the local structure tensor can better preserve the local structural information at (x,y), the cornerness measured from it should be more reliable and accurate.
Q9. What is the weight distribution of the edges of the corner?
In this example, the edge pixels have higher weights than the non-edge pixels because they are more similar to the examined corner pixel in terms of gradient.
Q10. How did the authors propose to construct a nonlinear structure tensor?
In [11], the authors proposed two different ways to construct a nonlinear structure tensor: one is by isotropic diffusion and the other is by anisotropic diffusion.
Q11. What are the basic factors in the formation of a local pattern?
There are two basic factors in the formation of a local pattern: the relative positions between neighboring pixels and the intensity variations between them.