Blind Image Separation using Sparse Representation

Souidene, W.; Bey, Abdeldjalil Aïssa El; Abed-Meraim, Karim; Beghdadi, Azeddine

doi:10.1109/icip.2007.4379262

Cited by 12 publications

(3 citation statements)

References 14 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, of size (m, n) are combined and those M linear mixtures of these original images are observed. These last mixtures can be modelized by the following linear system [4]:…”

Section: Mathematical Modelmentioning

confidence: 99%

Real Time Hardware Co-Simulation for Blind Image Separation Algorithm Using ZYNG 7000 & Xilinx System Generator

Mekhfioui¹

2020

IJETER

View full text Add to dashboard Cite

The implementation of blind image processing required a solid background knowledge of the design and description languages of the material. This paper describes an effective method for implementing real-time blind image separation algorithms on hardware, without needing a comprehensive knowledge of hardware design and description languages(VHDL).This study concerns the separation of a mixture of images, with no prior information on the images or on the way they have been mixed together. It describes the methodology for implementing real-time DSP applications on FPGAs and the concept of hardware/software co-simulation of the blind image separation algorithm using MATLAB Simulink and Xilinx System Generator (XSG).The performance of efficient architectures is implemented on the ZYBO Z7 Zynq-7020 FPGA.

show abstract

“…, of size (m, n) are combined and those M linear mixtures of these original images are observed. These last mixtures can be modelized by the following linear system [4]:…”

Section: Mathematical Modelmentioning

confidence: 99%

Real Time Hardware Co-Simulation for Blind Image Separation Algorithm Using ZYNG 7000 & Xilinx System Generator

Mekhfioui¹

2020

IJETER

View full text Add to dashboard Cite

show abstract

“…It is interesting to note that, in many applications of image processing, a Laplacian operator is explicitly applied to an image in order to establish a sparse image representation [29], which can facilitate the solution of an inverse problem. However, in boundary-enhanced PCT, we observe that the Laplacian operator is implicitly administered by the wave propagation physics.…”

Section: Few-view Boundary-enhanced Image Reconstruction In Pctmentioning

confidence: 99%

Image reconstruction exploiting object sparsity in boundary-enhanced X-ray phase-contrast tomography

Sidky¹,

Anastasio²,

Pan³

2010

Opt. Express

View full text Add to dashboard Cite

Propagation-based X-ray phase-contrast tomography (PCT) seeks to reconstruct information regarding the complex-valued refractive index distribution of an object. In many applications, a boundary-enhanced image is sought that reveals the locations of discontinuities in the real-valued component of the refractive index distribution. We investigate two iterative algorithms for few-view image reconstruction in boundary-enhanced PCT that exploit the fact that a boundary-enhanced PCT image, or its gradient, is often sparse. In order to exploit object sparseness, the reconstruction algorithms seek to minimize the ℓ 1 -norm or TV-norm of the image, subject to data consistency constraints. We demonstrate that the algorithms can reconstruct accurate boundary-enhanced images from highly incomplete few-view projection data.

show abstract

“…In [77], this type of reflection mixture is handled using a cyclic permutation approach while in [78], a generalized mixture ratio is estimated for the image separation. In [79], an iterative sparse blind separation algorithm is employed.…”

Section: Image Decompositionmentioning

confidence: 99%

Image Separation using Multi-layer Image Segmentation for Translucent Partially Overlapped Objects

Mahyari¹

View full text Add to dashboard Cite

One way to solve under-determined image separation is to use statistical information about the type of data to be decomposed. In this dissertation, we propose a two stage method for cervical cell separation. In the first stage, we propose a CNN-based multi-layer random walker image segmentation method. The results of image segmentation at the first stage are then used as the side information for the cervical cell separation in the second stage.Convolutional neural networks (CNNs) are recently used in computer vision applications such as image segmentation. One of the biggest advantages of CNNs is that they extract important features automatically from the data. However, CNNs usually use a high number of data for training but it is not always possible to find enough training data for some applications. Also, CNNs are good at generalizing the training, but not for finding the accurate edges of cervical cells at the current implementations for cervical cell segmentation.One solution to improve CNN segmentation results is to use a post-processing method as edge refinement. Random walker image segmentation method is a graph-based image segmentation method that is good at region growing; so, it can be used as the refinement step. However, random walker is sensitive to initial setup, so if the seeds are not extracted correctly, the final segmentation results will be poor. In this dissertation we use a CNN-based random walker image segmentation approach for cervical cell segmentation. Different from other methods that use CNN binary segmentation results for fine tuning, CNN probabilistic map is utilized to guide random walker image segmentation method at the refinement step.

show abstract

Blind Image Separation using Sparse Representation

Cited by 12 publications

References 14 publications

Real Time Hardware Co-Simulation for Blind Image Separation Algorithm Using ZYNG 7000 & Xilinx System Generator

Real Time Hardware Co-Simulation for Blind Image Separation Algorithm Using ZYNG 7000 & Xilinx System Generator

Image reconstruction exploiting object sparsity in boundary-enhanced X-ray phase-contrast tomography

Image Separation using Multi-layer Image Segmentation for Translucent Partially Overlapped Objects

Contact Info

Product

Resources

About