Some defects in finite-difference edge finders

Fleck, Margaret M.

doi:10.1109/34.120328

Cited by 96 publications

(36 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Then, a finite difference edge finder is applied to compute the gradient magnitude. The optimal finite difference edge finder for the Canny edge detection algorithm is given in (Fleck, 1992), which we use in our evaluation. Then non-maxima suppression (peak detection) is applied to the gradient magnitude image that retains only those points at the top of the ridge, whilst suppressing others.…”

Section: Evaluation and Experimental Resultsmentioning

confidence: 99%

Moving-edge detection via heat flow analogy

Direkoğlu

Nixon

2011

Pattern Recognition Letters

View full text Add to dashboard Cite

a b s t r a c tIn this paper, a new and automatic moving-edge detection algorithm is proposed, based on using the heat flow analogy. This algorithm starts with anisotropic heat diffusion in the spatial domain, to remove noise and sharpen region boundaries for the purpose of obtaining high quality edge data. Then, isotropic and linear heat diffusion is applied in the temporal domain to calculate the total amount of heat flow. The moving-edges are represented as the total amount of heat flow out from the reference frame. The overall process is completed by non-maxima suppression and hysteresis thresholding to obtain binary movingedges. Evaluation, on a variety of data, indicates that this approach can handle noise in the temporal domain because of the averaging inherent of isotropic heat flow. Results also show that this technique can detect moving-edges in image sequences, without background image subtraction.

show abstract

Section: Evaluation and Experimental Resultsmentioning

confidence: 99%

Moving-edge detection via heat flow analogy

Direkoğlu

Nixon

2011

Pattern Recognition Letters

View full text Add to dashboard Cite

show abstract

“…For each realisation of the neural network weights, a vector of actual outputs is produced Oa = N(w) xIp (38) The learning objective is to solve this equation in order to find N(w), allowing the definition of a weight set WL such that Op = 0Q(WL) =N(WL) X lp (39) As an algebraic solution is not known, an iterative solution was proposed by [145] as the minimisation of the function E(w) = 2115P -Öa(w)II (40) Among the different techniques for minimising a function of 9, back propagation is based on a steepest descent technique.…”

Section: Learning Objectivementioning

confidence: 99%

Edge detection using neural network arbitration

Ramalho

1995

Fifth International Conference on Image Processing and Its Applications

View full text Add to dashboard Cite

“…10) The resulting method is even more redundant than in the one-dimensional case: the method adds a considerable amount of spurious edges, as observed in [6,10]. Indeed, not all zero crossing of the regularized Laplacian, S η N f are necessarily extrema of ∇S η N [f ], which end up as "false" edges despite being zero crossings of (2.10).…”

Section: Zero Crossing Edge Detection For Incomplete Datamentioning

confidence: 99%

Three Novel Edge Detection Methods for Incomplete and Noisy Spectral Data

Tadmor

Zou

2008

J Fourier Anal Appl

View full text Add to dashboard Cite

We propose three novel methods for recovering edges in piecewise smooth functions from their possibly incomplete and noisy spectral information. The proposed methods utilize three different approaches: #1. The randomly-based sparse Inverse Fast Fourier Transform (sIFT); #2. The Total Variation-based (TV) compressed sensing; and #3. The modified zero crossing. The different approaches share a common feature: edges are identified through separation of scales. To this end, we advocate here the use of concentration kernels (Tadmor, Acta Numer. 16:305-378, 2007), to convert the global spectral data into an approximate jump function which is localized in the immediate neighborhoods of the edges. Building on these concentration kernels, we show that the sIFT method, the TV-based compressed sensing and the zero crossing yield effective edge detectors, where finitely many jump discontinuities are accurately recovered. One-and two-dimensional numerical results are presented.

show abstract

Some defects in finite-difference edge finders

Cited by 96 publications

References 24 publications

Moving-edge detection via heat flow analogy

Moving-edge detection via heat flow analogy

Edge detection using neural network arbitration

Three Novel Edge Detection Methods for Incomplete and Noisy Spectral Data

Contact Info

Product

Resources

About