Standard Deviation for Obtaining the Optimal Direction in the Removal of Impulse Noise

Awad, Ali S.

doi:10.1109/lsp.2011.2154330

Cited by 57 publications

(29 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the validity of experimentation, stream data of various resolutions are generated. First, we evaluate the performance of four image processing applications on CPU only mode and heterogeneous mode using GPU respectively on RIDE: standard deviation filter [17], surf [18], matrix multiplication [19], and FFT [20]. Figure 9 shows the execution time of four applications for 24,160 × 25,720 resolution input images after storing them in the topic of three broker nodes.…”

Section: Resultsmentioning

confidence: 99%

RIDE: real-time massive image processing platform on distributed environment

Kim

Jeong

2018

J Image Video Proc.

View full text Add to dashboard Cite

As the demand for real-time data processing increases, a high-speed processing platform for large-scale stream data becomes necessary. For fast processing large-scale stream data, it is essential to use multiple distributed nodes. So far, there have been few studies on real-time massive image processing through efficient management and allocation of heterogeneous resources for various user-specified nodes on distributed environments. In this paper, we shall present a new platform called RIDE (Real-time massive Image processing platform on Distributed Environment) which efficiently allocates resources and executes load balancing according to the amount of stream data on distributed environments. It minimizes communication overhead by using a parallel processing strategy which handles the stream data considering both coarse-grained and fine-grained parallelism simultaneously. Coarse-grained parallelism is achieved by the automatic allocation of input streams onto partitions of broker buffer each processed by its corresponding worker node, and maximized by adaptive resource management which adjusts the number of worker nodes in a group according to the frame rate in real time. Fine-grained parallelism is achieved by parallel processing of task on each worker node and maximized by allocating heterogeneous resources such as GPU and embedded machines appropriately. Moreover, it provides a scheme of application topology which has a great advantage for higher performance by configuring the worker nodes of each stage using adaptive heterogeneous resource management. Finally, it supports dynamic fault tolerance for real-time image processing through the coordination between components in our system.

show abstract

Section: Resultsmentioning

confidence: 99%

RIDE: real-time massive image processing platform on distributed environment

Kim

Jeong

2018

J Image Video Proc.

View full text Add to dashboard Cite

show abstract

“…Various existing methods for image processing have utilized some or the other measures of dispersion to identify the outliers. Awad [2] has demonstrated that the detection process can be based on finding the optimum direction by calculating the standard deviation of different directions in the filtering window. The measures of dispersion used in this proposed algorithm for setting different thresholds are the mean, the standard deviation, and the quartile.…”

Section: Basic Conceptmentioning

confidence: 99%

“…In RVIN, noisy pixels are randomly located between 0 and 255, and hence, it is very difficult to detect the noise and restore the image [2]. Since the difference between a noisy pixel and a noise-free pixel in RVIN may not be huge, the image appears hazy and blurred.…”

Section: Introductionmentioning

confidence: 99%

Triple Threshold Statistical Detection filter for removing high density random-valued impulse noise in images

Singh

Maheswari

2018

J Image Video Proc.

View full text Add to dashboard Cite

This study presents a novel noise detection algorithm which satisfactorily detects noisy pixels in images corrupted by random-valued impulse noise of high levels up to 80% noise density. Three levels of adaptive thresholds along with an auxiliary condition are used in this method which adequately addresses the drawbacks of existing methods, especially the miss detection of noise-free pixels as noisy pixels and vice versa. A noise signature is calculated for every pixel and compared with the first threshold to identify noise followed by the comparison of the central pixel with the second and third levels of thresholds. In addition to the standard deviation and mean, the concept of quartile has been used as another measure of dispersion. After detection, a fuzzy switching weighted median filter is applied to restore the corrupted image. The simulation results demonstrate that the proposed method is able to outperform the existing methods in both the detection and filtering of random-valued impulse noise in images.

show abstract

“…In Random Valued Impulse Noise (RVIN), noisy pixels randomly assume a value between 0 and 255 and it is very difficult to detect them [2]. The noise removal from noisy images in such situations becomes a challenging problem.…”

Section: Introductionmentioning

confidence: 99%