An Analysis of Fuzzy and Spatial Methods for Edge Detection

Mamoria, Pushpa; Raj, Deepa

doi:10.5815/ijieeb.2016.06.08

Cited by 4 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Where 𝜎 is the standard deviation which is assumed constant for all dimensions, 𝑢 𝑖 is the mean value for the ith dimension. Accordingly, the 2D and 3D Gaussian functions are expressed as: The Laplacian is a 2 nd order differential operator as ∑ 𝜕𝑓 2 𝑥 𝑖 𝑛 𝑖=1 which has been used for edge detection in CV [Mamoria andRaj 2016, Wikipedia 2016]. The Laplacian of Gaussian (LoG) for the 1D, 2D, and 3D input can be expressed as below given 𝑢 = 0: In this study the 2D Gaussian is distributed to two 1D vectors of sensitive to noise, and therefore, the image is often Gaussian smoothed before applying the Laplacian filter in practice.…”

Section: Gaussian and Laplacian Filtersmentioning

confidence: 99%

Distributive Convolution for Faster Feature Mapping of Two-Dimensional and Volumetric Images

Xu,

Jiang

2024

Preprint

View full text Add to dashboard Cite

This study introduces a distributive convolution framework for feature mapping based on the distributive property of matrix multiplication, aiming to improve computing speed of convolutions for the two-dimensional (2D) plane and three-dimensional (3D) volumetric images. This method distributes the 2D and 3D kernels (filters) to the 1D (one-dimensional) and 2D ones, and apply convolutions concurrently at each spatial direction, and then fuses (adds) results together. It is different than the spatially separable convolution based on the associative property which applies convolution with separated filters in sequence. The Gaussian and Laplacian filters using the distributive convolution are evaluated on some public images for de-noise and edge detection. Results show that this method achieves similar effects as compared to the traditional convolution, and even improves the edge detection performance for some cases. The fusion of direct linear addition achieves similar performance as that of root mean square. In comparison, the spatially separable convolution obtains similar effect for the Gaussian blur but inferior performance for edge detection.

show abstract

Section: Gaussian and Laplacian Filtersmentioning

confidence: 99%

Distributive Convolution for Faster Feature Mapping of Two-Dimensional and Volumetric Images

Xu,

Jiang

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…which has been used for edge detection in CV [Mamoria andRaj 2016, Wikipedia 2016]. The Laplacian of Gaussian (LoG) for the 1D, 2D, and 3D input can be expressed as below given 𝑢 = 0:…”

Section: Gaussian and Laplacian Filtersmentioning

confidence: 99%

Distributive Convolution for Faster Feature Mapping of Two-Dimensional and Volumetric Images

Xu,

Jiang

2024

Preprint

View full text Add to dashboard Cite

This study introduces a distributive convolution framework for feature mapping, aiming to improve computing speed of convolutions for the two-dimensional (2D) plane and three-dimensional (3D) volumetric images. This method distributes the kernel (filter) to smaller ones (e.g., one-dimensional, 1D) at each spatial direction, applies convolutions concurrently and then fuses (adds) results together. It is different from the separable convolution which separates the convolution on the channel direction and operates in sequence. The Gaussian and Laplacian filters using the distributive convolution are evaluated on some public images for de-noise and edge detection. Results show that this method achieves similar effects and even improved edge detection performance for some cases as compared to the traditional convolution. The fusion of linear addition achieves similar performance as that of the root square addition. This indicates a potential future opportunity to speed up the convolutional neural network which requires extensive computing recourse for both 2D and 3D images. Note that the evaluations are based on a limited number of filters and images.

show abstract

“…When we enhance the value of the parameter, we get smoother edges. It must be kept in mind that this value should not be equal to, 0 and 1 but must lie in between due to the reason that it will result in loss of certain important features [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Edge Detection based on Ant Colony Optimization Using Adaptive Thresholding Technique

Gautam¹,

Raj²

2018

IJIGSP

View full text Add to dashboard Cite

Abstract-Image edge detection is a process where true edges of an image are identified. In past, gradient based methods in which first or second order pixel difference is used to find discontinuities and if magnitude value of gradient is higher than certain threshold then that pixel under observation is identified as edge pixel. These methods are full of error, because in addition to true edges they also find false edges and infect false edges are more in comparison to true edges. To solve such problem, swarm intelligence based ant colony optimization based edge detection method is detailed where numbers of falsely detected edges are very small. The performance of the ant colony optimization (ACO) is done in terms of Peak Signal to Noise Ratio, Performance Ratio and Efficiency.

show abstract

An Analysis of Fuzzy and Spatial Methods for Edge Detection

Cited by 4 publications

References 13 publications

Distributive Convolution for Faster Feature Mapping of Two-Dimensional and Volumetric Images

Distributive Convolution for Faster Feature Mapping of Two-Dimensional and Volumetric Images

Distributive Convolution for Faster Feature Mapping of Two-Dimensional and Volumetric Images

Edge Detection based on Ant Colony Optimization Using Adaptive Thresholding Technique

Contact Info

Product

Resources

About