Multiple widths yield reliable finite differences

Fleck, Margaret M.

doi:10.1109/iccv.1990.139493

Cited by 19 publications

(20 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This allows the cost functions for these features to adapt to a variety of image types by automatically selecting, on a pixel by pixel basis, the kernel width that best matches the line-spread function of the imaging hardware used to obtain the current image [13,16].…”

Section: Image Feature Formulationmentioning

confidence: 99%

Interactive Segmentation with Intelligent Scissors

Mortensen

Barrett

1998

Graphical Models and Image Processing

464

311

View full text Add to dashboard Cite

Section: Image Feature Formulationmentioning

confidence: 99%

Interactive Segmentation with Intelligent Scissors

Mortensen

Barrett

1998

Graphical Models and Image Processing

464

311

View full text Add to dashboard Cite

“…Then the edges can be located simply by finding the local maxima of the derivative of the image or using the zero-crossing points of the second derivative. This approach was later developed by Marr and Hildreth [9], Canny [10,11] and others [12,13] where the gradient of the image I is given by the vector…”

Section: Starburst Pattern Center Estimationmentioning

confidence: 99%

Hohlraum target alignment from x-ray detector images using starburst design patterns

Leach¹,

Conder²,

Edwards³

et al. 2011

SPIE Proceedings

View full text Add to dashboard Cite

National Ignition Facility (NIF) is a high-energy laser facility comprised of 192 laser beams focused with enough power and precision on a hydrogen-filled spherical, cryogenic target to initiate a fusion reaction. The target container, or hohlraum, must be accurately aligned to an x-ray imaging system to allow careful monitoring of the frozen fuel layer in the target. To achieve alignment, x-ray images are acquired through starburst-shaped windows cut into opposite sides of the hohlraum. When the hohlraum is in alignment, the starburst pattern pairs match nearly exactly and allow a clear view of the ice layer formation on the edge of the target capsule. During the alignment process, x-ray image analysis is applied to determine the direction and magnitude of adjustment required. X-ray detector and source are moved in concert during the alignment process. The automated pointing alignment system described here is both accurate and efficient. In this paper, we describe the control and associated image processing that enables automation of the starburst pointing alignment.

show abstract

“…Second, the edge features used here are more robust and comprehensive than previous implementations: we maximize over different gradient kernels sizes to encompass the various edge types and scales while simultaneously attempting to balance edge detail with noise suppression [7], and we use the laplacian zero-crossing for boundary localization and fine detail livewire "snapping". Third, the discrete, bounded nature of the local edge costs permit the use of a specialized sorting algorithm that inserts points into a sorted list (called the active list) in constant time.…”

Section: Two-dimensional Dynamic Programmingmentioning

confidence: 99%

“…The laplacian zero-crossing is a binary edge feature used for edge localization [7,9]. Convolution of an image with a laplacian kernel approximates the 2 nd partial derivative of the image.…”

Section: Local Costsmentioning

confidence: 99%

Intelligent scissors for image composition

Mortensen

Barrett

1995

Proceedings of the 22nd Annual Conference on Computer Graphics and Interactive Techniques - SIGGRAPH '95

649

382

View full text Add to dashboard Cite

We present a new, interactive tool called Intelligent Scissors which we use for image segmentation and composition. Fully automated segmentation is an unsolved problem, while manual tracing is inaccurate and laboriously unacceptable. However, Intelligent Scissors allow objects within digital images to be extracted quickly and accurately using simple gesture motions with a mouse. When the gestured mouse position comes in proximity to an object edge, a live-wire boundary "snaps" to, and wraps around the object of interest.Live-wire boundary detection formulates discrete dynamic programming (DP) as a two-dimensional graph searching problem. DP provides mathematically optimal boundaries while greatly reducing sensitivity to local noise or other intervening structures. Robustness is further enhanced with on-the-fly training which causes the boundary to adhere to the specific type of edge currently being followed, rather than simply the strongest edge in the neighborhood. Boundary cooling automatically freezes unchanging segments and automates input of additional seed points. Cooling also allows the user to be much more free with the gesture path, thereby increasing the efficiency and finesse with which boundaries can be extracted.Extracted objects can be scaled, rotated, and composited using live-wire masks and spatial frequency equivalencing. Frequency equivalencing is performed by applying a Butterworth filter which matches the lowest frequency spectra to all other image components. Intelligent Scissors allow creation of convincing compositions from existing images while dramatically increasing the speed and precision with which objects can be extracted.

show abstract

Multiple widths yield reliable finite differences

Cited by 19 publications

References 13 publications

Interactive Segmentation with Intelligent Scissors

Interactive Segmentation with Intelligent Scissors

Hohlraum target alignment from x-ray detector images using starburst design patterns

Intelligent scissors for image composition

Contact Info

Product

Resources

About