2006
DOI: 10.1117/12.644430
|View full text |Cite
|
Sign up to set email alerts
|

Finding corners in images by foveated search

Abstract: We develop a new approach to finding corners in images that combines foveated edge detection and curvature calculation with saccadic placement of foveal fixations. Each saccade moves the fovea to a location of high curvature combined with high edge gradient. Edges are located using a foveated Canny edge detector with spatial constant that increases with eccentricity. Next, we calculate a measure of local corner strength, based on a product of curvature and gradient. An inhibition factor based on previous visit… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
3
0

Year Published

2006
2006
2007
2007

Publication Types

Select...
2
1

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(3 citation statements)
references
References 24 publications
(25 reference statements)
0
3
0
Order By: Relevance
“…Corner: Another important aspect in the pixel or spatial domain is information pertaining to the corners. Corners have long been recognized as visual information carriers and various algorithms have been proposed to detect them for use in basic visual tasks [14]. Corners are considered more localized than edges and are better in defining shapes of objects in images as an edge can provide local information only in one direction, normal to the edge [14].…”
Section: Just Noticeable Distortion (Jnd) Visual Maskmentioning
confidence: 99%
See 1 more Smart Citation
“…Corner: Another important aspect in the pixel or spatial domain is information pertaining to the corners. Corners have long been recognized as visual information carriers and various algorithms have been proposed to detect them for use in basic visual tasks [14]. Corners are considered more localized than edges and are better in defining shapes of objects in images as an edge can provide local information only in one direction, normal to the edge [14].…”
Section: Just Noticeable Distortion (Jnd) Visual Maskmentioning
confidence: 99%
“…Corners have long been recognized as visual information carriers and various algorithms have been proposed to detect them for use in basic visual tasks [14]. Corners are considered more localized than edges and are better in defining shapes of objects in images as an edge can provide local information only in one direction, normal to the edge [14]. A corner represents the point where two edges meet and the human eye is more sensitive to changes made in these places.…”
Section: Just Noticeable Distortion (Jnd) Visual Maskmentioning
confidence: 99%
“…One interesting application we are studying is the visual search for corners. 3 We accomplish the search by using the principles of foveated visual search combined with an automated fixation selection. Our effort is an attempt to demonstrate a case study of feature detection by means of foveated searching.…”
mentioning
confidence: 99%