Improving Harris corner selection strategy

Bellavia, Fabio; Tegolo, Domenico; Valenti, Cesare

doi:10.1049/iet-cvi.2009.0127

Cited by 66 publications

(36 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Except for the Patch dataset, the HarrisZ corner detector [59] was used to extract keypoints from images, whose results are similar to those of state-of-the-art detectors. The HarrisZ detector outputs a lower number of similar keypoints (i.e., with close scale, rotation and location) with respect to the Hessian-affine detector [9], but both obtain similar relative ranks among descriptors.…”

Section: Setup Protocolmentioning

confidence: 83%

Rethinking the sGLOH Descriptor

Bellavia

Colombo

2018

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Abstract-sGLOH (shifting GLOH) is a histogram-based keypoint descriptor that can be associated to multiple quantized rotations of the keypoint patch without any recomputation. This property can be exploited to define the best distance between two descriptor vectors, thus avoiding computing the dominant orientation. In addition, sGLOH can reject incongruous correspondences by adding a global constraint on the rotations either as an a priori knowledge or based on the data. This paper thoroughly reconsiders sGLOH and improves it in terms of robustness, speed and descriptor dimension. The revised sGLOH embeds more quantized rotations, thus yielding more correct matches. A novel fast matching scheme is also designed, which significantly reduces both computation time and memory usage. In addition, a new binarization technique based on comparisons inside each descriptor histogram is defined, yielding a more compact, faster, yet robust alternative. Results on an exhaustive comparative experimental evaluation show that the revised sGLOH descriptor incorporating the above ideas and combining them according to task requirements, improves in most cases the state of the art in both image matching and object recognition.

show abstract

Section: Setup Protocolmentioning

confidence: 83%

Rethinking the sGLOH Descriptor

Bellavia

Colombo

2018

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

show abstract

“…The optic disk, which can be located by using the Harris detector (Bellavia et al, 2011;Dehghani et al, 2012), was excluded from the evaluation of the method due to the complexity, and multi intertwining of its vessels (Dashtbozorg et al, 2014). This area usually contains many vessels and the corresponding graph is not reliable; detection percentages for both bifurcations and crossings are shown in Table 1.…”

Section: Resultsmentioning

confidence: 99%

Automatic Detection and Classification of Retinal Vascular Landmarks

Hamad¹,

Tegolo²,

Valenti³

2014

Image Anal Stereol

View full text Add to dashboard Cite

The main contribution of this paper is introducing a method to distinguish between different landmarks of the retina: bifurcations and crossings. The methodology may help in differentiating between arteries and veins and is useful in identifying diseases and other special pathologies, too. The method does not need any special skills, thus it can be assimilated to an automatic way for pinpointing landmarks; moreover it gives good responses for very small vessels. A skeletonized representation, taken out from the segmented binary image (obtained through a preprocessing step), is used to identify pixels with three or more neighbors. Then, the junction points are classified into bifurcations or crossovers depending on their geometrical and topological properties such as width, direction and connectivity of the surrounding segments. The proposed approach is applied to the public-domain DRIVE and STARE datasets and compared with the state-of-the-art methods using proper validation parameters. The method was successful in identifying the majority of the landmarks; the average correctly identified bifurcations in both DRIVE and STARE datasets for the recall and precision values are: 95.4% and 87.1% respectively; also for the crossovers, the recall and precision values are: 87.6% and 90.5% respectively; thus outperforming other studies.

show abstract

“…The HarrisZ keypoint detector [2] and the sGLOH descriptor [1], both proven to be robust and stable, have been used to get the matches ranked by a nearest neighbour selection. The former is based on the Harris corner detector [9], while the latter on the SIFT descriptor [12].…”

Section: Methodsmentioning

confidence: 99%

“…a more pessimistic assumption is made for the worst case scenario. However, since the feature axis ratio is usually related to the intensity variation of the keypoint region in all directions, which detectors often try to maximize [2,17], the values of α max i and α min i are usually close.…”

Section: The New Normalized Epipolar Errormentioning

confidence: 99%

noRANSAC for fundamental matrix estimation

Tegolo

Bellavia

2011

Procedings of the British Machine Vision Conference 2011

View full text Add to dashboard Cite

The estimation of the fundamental matrix from a set of corresponding points is a relevant topic in epipolar stereo geometry [10]. Due to the high amount of outliers between the matches, RANSAC-based approaches [7,13,29] have been used to obtain the fundamental matrix. In this paper two new contributes are presented: a new normalized epipolar error measure which takes into account the shape of the features used as matches [17] and a new strategy to compare fundamental matrices. The proposed error measure gives good results and it does not depend on the image scale. Moreover, the new evaluation strategy describes a valid tool to compare different RANSAC-based methods because it does not rely on the inlier ratio, which could not correspond to the best allowable fundamental matrix estimated model, but it makes use of a reference ground truth fundamental matrix obtained by a set of corresponding points given by the user.

show abstract

Improving Harris corner selection strategy

Cited by 66 publications

References 19 publications

Rethinking the sGLOH Descriptor

Rethinking the sGLOH Descriptor

Automatic Detection and Classification of Retinal Vascular Landmarks

noRANSAC for fundamental matrix estimation

Contact Info

Product

Resources

About