Estimation of the variance of noise in digital images using a median filter

Mikołajczak, G.; Pęksiński, Jakub

doi:10.1109/tsp.2016.7760927

Cited by 14 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the continuous scaling of digital systems and the increased demand on low power devices, design of effective soft error tolerance techniques is of high importance to cope with the increased susceptibility of systems to soft errors and 4 7 10 a0 a3 a1 a4 a5 a8 z1 z9 5 to enhance system reliability. In this work, we propose a double modular redundancy (DMR) technique that aims to achieve high reliability with reduced area overhead.…”

Section: Dmr Methodmentioning

confidence: 99%

“…For the second enable signal FIFO unit is enabled, output of the MUX is provided to the FIFO of 9* 8-bit register. All FIFO units have a comparator unit (CU) which does the Median sorting by Compare and Swap method [4]. When the sorting is completed the output bus is taken from the middle register.…”

Section: Fig 3 Overall Architecture Of Proposed Model Enabling Signalsmentioning

confidence: 99%

“…Median filtering system design is provided in Fig 7 this part has a FIFO for accepting inputs which is given out of the MUX, 9 8-BitRegisters representing 9pixels, a comparator unit (CU) which take care of compare and swap operation for obtaining median value and All registers are connected to LACG [4] system shown in Fig 8 for gated clock input.…”

Section: Design Of Median Filtermentioning

confidence: 99%

“…Recently, the DMR concept has been extended to provide error correction in certain cases by monitoring the Distribution of the module output errors. For example, using one redundant module, Soft-NMR [4] can correct soft errors if they cause the module-in-error to output a value that is unlikely compared to the typical distribution of outputs. While low cost, the technique does not correct all single errors.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Architectural Design of Effective Edge Preserving Median Filter with Error Correction System

2019

IJRTE

View full text Add to dashboard Cite

Designing of Median filter that can process 36 pixels at a time with edge preservation similar to a filter of size 9. Median sorting is done using Modified minimum exchange sorting method which attracts double the amount of inputs in order to reduce number of comparators used for median filtering. For the same reason i.e. double the amount of inputs switching loss is high in the circuit therefore data driven clock gating (DDCG) is applied for SRAM to form data driven FIFO. Considering space radiation that could excite memory state, Addition of DMR (Double Modular Redundancy) in FPIC would rectify the soft error that could possibly occur due to radiation in space. Therefore proposed method is capable of producing sharp image, controlling switching loss, minimizes area, and reduces soft errors.

show abstract

Section: Dmr Methodmentioning

confidence: 99%

Section: Fig 3 Overall Architecture Of Proposed Model Enabling Signalsmentioning

confidence: 99%

Section: Design Of Median Filtermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Architectural Design of Effective Edge Preserving Median Filter with Error Correction System

2019

IJRTE

View full text Add to dashboard Cite

show abstract

“…A Standard median filter is produced by orderly arranging the input samples in ascending order and choosing the input one as the median value, if there exists odd number of samples. Else the medial filter, will take any value of input sample that is placed between the two median values (it is usually an arithmetic average) (G. Mikolajczak and Peksinski, 2016) [30].…”

Section: Image Pre-processing Algorithmsmentioning

confidence: 99%

Hybrid Deep Learning Method for Diagnosis of Cucurbita Leaf Diseases

Nirmala¹,

Gomathy²

2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

In agricultural engineering, the main challenge is on methodologies used for disease detection. The manual methods depend on the experience of the personal. Due to large variation in environmental condition, disease diagnosis and classification becomes a challenging task. Apart from the disease, the leaves are affected by climate changes which is hard for the image processing method to discriminate the disease from the other background. In Cucurbita gourd family, the disease severity examination of leaf samples through computer vision, and deep learning methodologies have gained popularity in recent years. In this paper, a hybrid method based on Convolutional Neural Network (CNN) is proposed for automatic pumpkin leaf image classification. The Proposed Denoising and deep Convolutional Neural Network (CNN) method enhances the Pumpkin Leaf Preprocessing and diagnosis. Real time data base was used for training and testing of the proposed work. Investigation on existing pre-trained network Alexnet and googlenet was investigated is done to evaluate the performance of the proposed method. The system and computer simulations were performed using Matlab tool.

show abstract