A modified approximation of 2D Gaussian smoothing filters for fixed-point platforms

Khorbotly, Sami; Hassan, Firas

doi:10.1109/ssst.2011.5753797

Cited by 28 publications

(28 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…7. The above mentioned proposed hardware is better than previous approximate approach [16], [17] in terms of hardware complexity. …”

Section: B Approximate 5 × 5 2d Gaussian Smooth Filtermentioning

confidence: 93%

“…In [16], [17] approximate 2GSF uses all 25 elements of 5 × 5 block. The time and hardware complexity on above approaches are critical and can be reduced by Mirror short pixel approximation (MSPA).…”

Section: ) Mirror Short Pixel Approximation In Input Image Matrixmentioning

confidence: 99%

“…Average value of first, second and third row is 212, 210 and 212. One can observe that there is small variation in pixel values to represent row, so it is optimal to process 2 elements instead of 9 elements as in conventional and modified approximation [17]. This is shown in Fig.…”

Section: ) Mirror Short Pixel Approximation In Input Image Matrixmentioning

confidence: 99%

“…The major drawback of the design is its hardware complexity and uneven accuracy. An approach proposed in [17] used fixed point data and rounded-off filter coefficients, the approach reduces the computation time but hardware complexity is still a major concern. To overcome hardware complexity issue, this paper proposes an energyefficient approximate 2D gaussian smoothing filter.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Energy-efficient approximate 2D Gaussian smoothing filter for error tolerant applications

Dr¹,

Kumar²

2015

2015 IEEE International Advance Computing Conference (IACC)

View full text Add to dashboard Cite

Present multimedia applications demand highly energy-efficient devices due to need of intensive computation. Most filtering applications engage 2D gaussian smooth filter which is slow and severely affects the performance. In this paper, we propose a novel energy efficient approximate 2D gaussian smoothing filter. The proposed approach is based on "Mirror Short Pixel Approximation" and rounding-off gaussian kernel coefficients. In Mirror Short Pixel Approximation the elements of input image block is replaced via mirror pixel value. The proposed approach is modelled in high level language to check efficacy on benchmark image, which results in minor degradation of image quality. The proposed design is realized on Virtex 6 FPGA. The Simulation results show reduction of 85%, 8%, 58% in area, power and delay respectively compared to existing approximate 2D gaussian smooth filter.Index Terms-Mirror Short Pixel Approximation, 2D Gaussian smooth filter, Gaussian kernel, Error Tolerant, FPGA.

show abstract

“…7. The above mentioned proposed hardware is better than previous approximate approach [16], [17] in terms of hardware complexity. …”

Section: B Approximate 5 × 5 2d Gaussian Smooth Filtermentioning

confidence: 93%

Section: ) Mirror Short Pixel Approximation In Input Image Matrixmentioning

confidence: 99%

Section: ) Mirror Short Pixel Approximation In Input Image Matrixmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Energy-efficient approximate 2D Gaussian smoothing filter for error tolerant applications

Dr¹,

Kumar²

2015

2015 IEEE International Advance Computing Conference (IACC)

View full text Add to dashboard Cite

show abstract

“…This algorithm has been implemented both as a software application and as a hardware core for the FPGA. Due to lack of space we omit details about hardware core implementation; an example of implementation of such algorithm on a FPGA is given in [23].…”

Section: A Applicationsmentioning

confidence: 99%

Mini-Robot's Performance Optimization via Online Reconfiguration and HW/SW Task Scheduling

Durelli

Cresci

Sciuto

et al. 2012

2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops &Amp; PhD Forum

View full text Add to dashboard Cite

Nowadays a big effort is spent on research in heterogeneous computing and in particular in accelerator-based solutions. The field of embedded systems and in particular researches regarding autonomous robots have a great interest in this subject since the use of FPGAs on these devices as coprocessors is a common practice due to the tasks they have to accomplish. Autonomous robots are used to perform environment analysis, for example in critical situations, when human intervention could be dangerous or even impossible. In this paper in order to exploit their potentialities, given their heterogeneous nature, techniques from hardware and software codesign have been applied to this field. A particular focus during the design has been given to the problematic of runtime reconfiguration in order to efficiently use them in real scenarios. This work presents a methodology which permits, given multiple implementations of the same task, to choose at runtime which one to use on the basis of off-line profiling informations in order to achieve the best execution time. This research has been carried out by implementing such a technique in the case of a robot equipped with an ARM processor running GNU/Linux, and a Xilinx FPGA as a hardware accelerator.

show abstract

FPGA-Based Implementation of Digital Filters for Image Denoising

Shirakol

Hiremath

Kerur

2021

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

A modified approximation of 2D Gaussian smoothing filters for fixed-point platforms

Cited by 28 publications

References 8 publications

Energy-efficient approximate 2D Gaussian smoothing filter for error tolerant applications

Energy-efficient approximate 2D Gaussian smoothing filter for error tolerant applications

Mini-Robot's Performance Optimization via Online Reconfiguration and HW/SW Task Scheduling

FPGA-Based Implementation of Digital Filters for Image Denoising

Contact Info

Product

Resources

About