Local ordered grey levels as an aid to corner detection

Paler, K.; Föglein, J.; Illingworth, J.; Kittler, Josef

doi:10.1016/0031-3203(84)90051-7

Cited by 45 publications

(24 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have also considered the detector of Paler et al [8] which appears to operate on a very different principle from those detectors based on image calculus in that a median filtered version of the image is subtracted from the original and a cornerness measure formed by multiplying the gray-level differences with the contrast over a window. Davies [20], however, has shown that subject to certain assumptions, this detector also conforms to the curvature-times-gradient-magnitude format.…”

Section: Application To Corner Detectorsmentioning

confidence: 99%

“…In Section IV, we illustrate the application of the methodology presented where we examine the performance and operation of three well-known corner detectors: the Kitchen & Rosenfeld detector [7], the Paler detector [8] and the Harris & Stephens detector [9] also known as the Plessey corner detector. One advantage of the present approach is that it enables us to probe the key issues in the functioning of each of the detectors as well as assessing labeling performance in operation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Performance assessment of feature detection algorithms: a methodology and case study on corner detectors

Rockett

2003

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Abstract-In this paper, we describe a generic methodology for evaluating the labeling performance of feature detectors. We describe a method for generating a test set and apply the methodology to the performance assessment of three well-known corner detectors: the Kitchen-Rosenfeld, Paler et al., and Harris-Stephens corner detectors. The labeling deficiencies of each of these detectors is related to their discrimination ability between corners and various of the features which comprise the class of noncorners.

show abstract

Section: Application To Corner Detectorsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Performance assessment of feature detection algorithms: a methodology and case study on corner detectors

Rockett

2003

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…The idea of using intensity differences between the central points and neighboring points [173,232,240] has been adopted in [202,203]. They construct a decision tree to classify point neighborhoods into corners [203].…”

Section: Machine Learning-based Methodsmentioning

confidence: 99%

“…Another approach [173] indicates that for interest points the median value over a small neighborhood is significantly different from the corner point value. Thus the difference in intensity between the center and median gives a strong indication for corners.…”

Section: Intensity Variationsmentioning

confidence: 99%

Local Invariant Feature Detectors: A Survey

Tuytelaars

Mikolajczyk

2007

FNT in Computer Graphics and Vision

1,146

573

View full text Add to dashboard Cite

In this survey, we give an overview of invariant interest point detectors, how they evolved over time, how they work, and what their respective strengths and weaknesses are. We begin with defining the properties of the ideal local feature detector. This is followed by an overview of the literature over the past four decades organized in different categories of feature extraction methods. We then provide a more detailed analysis of a selection of methods which had a particularly significant impact on the research field. We conclude with a summary and promising future research directions.

show abstract

“…A measure of saliency is introduced to further direct the search for matching features within the database of a: Original image b: Line detected (Canny, 1986) c: Corner detected (Paler, 1984) d: Line segmented e: Stored model Figure 1 shows the effect of these operations being performed in sequence on a raw image. Increasingly staticto-static low level data transformations such as edge detection, and to a lesser extent static-to-dynamic data transformations such as Hough transformation are being performed in hardware using discrete, semi-custom or custom design techniques with the result that greater emphasis is placed on the design of software algorithms applied to segmented images in forming hypotheses.…”

mentioning

confidence: 99%

Interpretation of 2D Scenes Using a General Relational Model

McAndrew¹,

Wallace²

1987

Procedings of the Alvey Vision Conference 1987

View full text Add to dashboard Cite

A general strategy for the interpretation of twodimensional views of manufactured components is presented. The model database contains as primitives parameterised two-dimensional shape descriptions including feature type, position, and orientation where appropriate. Depending on the extent of each feature either a point or a point vector is associated with each constituent feature within the model or scene. Attributed geometric pairwise relations are formed between relevant primitives. The complexity of the search space of possible scene-model feature correspondences is limited in two ways. Firstly, the pre-formed pairwise relations are used to indicate the probable occurrence of both specific components and specific features. Secondly, a measure of saliency is employed which directs the search to those features which most precisely determine particular components. This is an extension and generalisation of previous work on the matching of two-dimensional descriptions and complements work on low and intermediate level processing of the scene data, based on the use of the generalised Hough transformation.

show abstract

Local ordered grey levels as an aid to corner detection

Cited by 45 publications

References 6 publications

Performance assessment of feature detection algorithms: a methodology and case study on corner detectors

Performance assessment of feature detection algorithms: a methodology and case study on corner detectors

Local Invariant Feature Detectors: A Survey

Interpretation of 2D Scenes Using a General Relational Model

Contact Info

Product

Resources

About