Feature point extraction using scale-space representation

Abdeljaoued, Yousri; Ebrahimi, Touradj

doi:10.1109/icip.2004.1421757

Cited by 4 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As accuracy usually indicates the localization of the detected corners, such a metric based on the number of the detected corners is flawed. In order to measure accuracy, the locations of the detected corners should be considered instead [37] (see Section IV-B.2).…”

Section: ) Human Visual Inspectionmentioning

confidence: 99%

“…3) Preferred Metrics: In fact, the performance evaluation of corner detectors should be automated and without using any human intuition. For example, they could be evaluated in terms of repeatability and localization error which were previously used for evaluating other types of feature detectors and matching techniques [37]- [39]. We present them in the following section.…”

Section: ) Human Visual Inspectionmentioning

confidence: 99%

“…Lower localization error indicates the better accuracy. It was measured using the root-meansquare-error (RMSE) of corresponding positions of matching corners in the original and transformed images [6], [37]:…”

Section: B Existing Corner Matching Evaluationmentioning

confidence: 99%

“…where (x 0i , y 0i ) and (x ti , y ti ) are the positions of i-th matching corner in original and transformed images respectively. An RMSE value of maximum 3 pixels was allowed to find the corner matches [37]. If less than 3 pixels error is allowed, then some true corners may be missed leading to low repeatability.…”

Section: B Existing Corner Matching Evaluationmentioning

confidence: 99%

“…1) Corner Detection Performance Measurement: The performance of a corner detector is evaluated using repeatability and localization error [37], [39]. For many applications, e.g., image copyright protection, once we have the required number of repeated corners, localization of the repeated corners is very important.…”

Section: Proposed Evaluation Metricsmentioning

confidence: 99%

See 4 more Smart Citations

An Improved Curvature Scale-Space Corner Detector and a Robust Corner Matching Approach for Transformed Image Identification

Awrangjeb

2008

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

There are many applications, such as image copyright protection, where transformed images of a given test image need to be identified. The solution to this identification problem consists of two main stages. In stage one, certain representative features, such as corners, are detected in all images. In stage two, the representative features of the test image and the stored images are compared to identify the transformed images for the test image. Curvature scale-space (CSS) corner detectors look for curvature maxima or inflection points on planar curves. However, the arc-length used to parameterize the planar curves by the existing CSS detectors is not invariant to geometric transformations such as scaling. As a solution to stage one, this paper presents an improved CSS corner detector using the affine-length parameterization which is relatively invariant to affine transformations. We then present an improved corner matching technique as a solution to the stage two. Finally, we apply the proposed corner detection and matching techniques to identify the transformed images for a given image and report the promising results.

show abstract

Section: ) Human Visual Inspectionmentioning

confidence: 99%

Section: ) Human Visual Inspectionmentioning

confidence: 99%

Section: B Existing Corner Matching Evaluationmentioning

confidence: 99%

Section: B Existing Corner Matching Evaluationmentioning

confidence: 99%

Section: Proposed Evaluation Metricsmentioning

confidence: 99%

See 3 more Smart Citations

An Improved Curvature Scale-Space Corner Detector and a Robust Corner Matching Approach for Transformed Image Identification

Awrangjeb

2008

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

Image Feature Information Extraction for Interest Point Detection: A Comprehensive Review

Gao

Zhang

et al. 2023

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Interest point detection is one of the most fundamental and critical problems in computer vision and image processing. In this paper, we carry out a comprehensive review on image feature information (IFI) extraction techniques for interest point detection. To systematically introduce how the existing interest point detection methods extract IFI from an input image, we propose a taxonomy of the IFI extraction techniques for interest point detection. According to this taxonomy, we discuss different types of IFI extraction techniques for interest point detection. Furthermore, we identify the main unresolved issues related to the existing IFI extraction techniques for interest point detection and any interest point detection methods that have not been discussed before. The existing popular datasets and evaluation standards are provided and the performances for fifteen state-of-the-art approaches are evaluated and discussed. Moreover, future research directions on IFI extraction techniques for interest point detection are elaborated.

show abstract

Polar-Radius-Invariant-Moment Based on Key-Points for Hand Gesture Shape Recognition

Zhao¹,

Li²,

Zhang³

et al. 2012

JSW

View full text Add to dashboard Cite

For the whole matching cannot handle partial occlusion and lack of specificity, a new method using Polar-Radius-Invariant-Moment, which is based on Key-Points to extract features for target’s shape recognition, is presented in this paper. Firstly, key-points of the hand shape are extracted through discrete curve evolution method. Secondly, Polar-Radius-Invariant-Moment based on Key-Points is used to describe the characteristics of the gesture shape. Finally, Euclidean distance is utilized in gesture recognition to verify the validity of this method. Hand objects are selected as the test case to testify the performance of the method. Simulation results prove that this method has a better classification character than that of obtained by the Polar-Radius-Invariant-Moment with recognizing the object shape rapidly and accurately, and that it also can keep highly stable even if the object contour was ill-segmented or noisy

show abstract

Feature point extraction using scale-space representation

Cited by 4 publications

References 7 publications

An Improved Curvature Scale-Space Corner Detector and a Robust Corner Matching Approach for Transformed Image Identification

An Improved Curvature Scale-Space Corner Detector and a Robust Corner Matching Approach for Transformed Image Identification

Image Feature Information Extraction for Interest Point Detection: A Comprehensive Review

Polar-Radius-Invariant-Moment Based on Key-Points for Hand Gesture Shape Recognition

Contact Info

Product

Resources

About