Feature Preserving Image Smoothing Using a Continuous Mixture of Tensors

Subakan, Özlem N.; Jian, Bing; Vemuri, Baba C.; Vallejos, C. Eduardo

doi:10.1109/iccv.2007.4408918

Cited by 14 publications

(10 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Let f(K) be its density function with respect to some carrier measure dK on n . (This model has been presented in the context of the diffusion weighted MR signal attenuation by Jian and Vemuri in [3] and later used in the context of image smoothing by Subakan et al in [22].) We propose to model the orientation distribution by a continuous mixture of Gaussian functions: (2) where ξ encodes the coordinates, G(ξ; g) is the response of the Gabor filter with an orientation determined by g a unit direction vector, G 0 denotes the maximal filter response.…”

Section: Local Orientation Representation and The Rigaut Kernelmentioning

confidence: 99%

“…To analyze orientations in regions with one or more orientations, we use the steerable Gabor filters. Steerable Gabor filters have been studied extensively in [6,22].…”

Section: Local Orientation Representation and The Rigaut Kernelmentioning

confidence: 99%

“…Recently Kalliomaki and Lampinen [6] presented approximate steerability of Gabor filters in 2D for pattern recognition purposes. 3D steerable Gabor filters were formulated in [22]. Here we employ them to extract orientation information required in the first stage of the proposed approach.…”

Section: Introductionmentioning

confidence: 99%

“…Continuous mixture is preferred here over the finite mixture model because one need not specify the number of components in the mixture explicitly. For more details see [5,22]. The continuous mixture representation is cast as the Laplace transform of the mixing density over the space of covariance (positive definite) matrices.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Image segmentation via convolution of a level-set function with a Rigaut Kernel

Subakan

Vemuri

2008

2008 IEEE Conference on Computer Vision and Pattern Recognition

Self Cite

View full text Add to dashboard Cite

Image segmentation is a fundamental task in Computer Vision and there are numerous algorithms that have been successfully applied in various domains. There are still plenty of challenges to be met with. In this paper, we consider one such challenge, that of achieving segmentation while preserving complicated and detailed features present in the image, be it a gray level or a textured image. We present a novel approach that does not make use of any prior information about the objects in the image being segmented. Segmentation is achieved using local orientation information, which is obtained via the application of a steerable Gabor filter bank, in a statistical framework. This information is used to construct a spatially varying kernel called the Rigaut Kernel, which is then convolved with the signed distance function of an evolving contour (placed in the image) to achieve segmentation. We present numerous experimental results on real images, including a quantitative evaluation. Superior performance of our technique is depicted via comparison to the state-of-the-art algorithms in literature.

show abstract

Section: Local Orientation Representation and The Rigaut Kernelmentioning

confidence: 99%

“…To analyze orientations in regions with one or more orientations, we use the steerable Gabor filters. Steerable Gabor filters have been studied extensively in [6,22].…”

Section: Local Orientation Representation and The Rigaut Kernelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Image segmentation via convolution of a level-set function with a Rigaut Kernel

Subakan

Vemuri

2008

2008 IEEE Conference on Computer Vision and Pattern Recognition

Self Cite

View full text Add to dashboard Cite

show abstract

“…Several pioneer image denoising researches used wavelet transformation techniques [27], partial differential equation based approaches [28]- [30], and conveyed scant coding approaches [18], [31], [32]. Singh et al [33] introduced a multi-class classifier for images which are adulterated with Gaussian noise.…”

Section: Introductionmentioning

confidence: 99%

A Robust System for Noisy Image Classification Combining Denoising Autoencoder and Convolutional Neural Network

Roy¹,

Hossain²,

Akhand³

et al. 2018

ijacsa

View full text Add to dashboard Cite

Abstract-Image classification, a complex perceptual task with many real life important applications, faces a major challenge in presence of noise. Noise degrades the performance of the classifiers and makes them less suitable in real life scenarios. To solve this issue, several researches have been conducted utilizing denoising autoencoder (DAE) to restore original images from noisy images and then Convolutional Neural Network (CNN) is used for classification. The existing models perform well only when the noise level present in the training set and test set are same or differs only a little. To fit a model in real life applications, it should be independent to level of noise. The aim of this study is to develop a robust image classification system which performs well at regular to massive noise levels. The proposed method first trains a DAE with low-level noise-injected images and a CNN with noiseless native images independently. Then it arranges these two trained models in three different combinational structures: CNN, DAE-CNN, and DAE-DAE-CNN to classify images corrupted with zero, regular and massive noises, accordingly. Final system outcome is chosen by applying the winner-takes-all combination on individual outcomes of the three structures. Although proposed system consists of three DAEs and three CNNs in different structure layers, the DAEs and CNNs are the copy of same DAE and CNN trained initially which makes it computationally efficient as well. In DAE-DAE-CNN, two identical DAEs are arranged in a cascaded structure to make the structure well suited for classifying massive noisy data while the DAE is trained with low noisy image data. The proposed method is tested with MNIST handwritten numeral dataset with different noise levels. Experimental results revealed the effectiveness of the proposed method showing better results than individual structures as well as the other related methods.

show abstract

Color Image Segmentation in a Quaternion Framework

Subakan

Vemuri

2009

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

In this paper, we present a feature/detail preserving color image segmentation framework using Hamiltonian quaternions. First, we introduce a novel Quaternionic Gabor Filter (QGF) which can combine the color channels and the orientations in the image plane. Using the QGFs, we extract the local orientation information in the color images. Second, in order to model this derived orientation information, we propose a continuous mixture of appropriate hypercomplex exponential basis functions. We derive a closed form solution for this continuous mixture model. This analytic solution is in the form of a spatially varying kernel which, when convolved with the signed distance function of an evolving contour (placed in the color image), yields a detail preserving segmentation.

show abstract

Feature Preserving Image Smoothing Using a Continuous Mixture of Tensors

Cited by 14 publications

References 20 publications

Image segmentation via convolution of a level-set function with a Rigaut Kernel

Image segmentation via convolution of a level-set function with a Rigaut Kernel

A Robust System for Noisy Image Classification Combining Denoising Autoencoder and Convolutional Neural Network

Color Image Segmentation in a Quaternion Framework

Contact Info

Product

Resources

About