Comparison of GPU and FPGA Implementation of SVM Algorithm for Fast Image Segmentation

Pietroń, Marcin; Wielgosz, Maciej; Żurek, Dominik; Jamro, E.; Wiatr, K.

doi:10.1007/978-3-642-36424-2_25

Cited by 16 publications

(23 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, our proposed implementation achieved lower hardware resources utilization than some of the previous FPGA-based SVM classification implementations of different applications in literature [10], [12], [21], [23], [25], [34], [36]. Concerning power consumption, our implementation demonstrated lower power dissipation than other related work [6], [12], [25]. Therefore, our proposed system could be deployed as a real-time embedded system dedicated for melanoma detection.…”

Section: Resultsmentioning

confidence: 83%

“…Moreover, the common pipelining technique was used in many previous hardware designs [11,12,13], [17,18,19,20,21,22,23,24,25,26], taking advantage of the parallel processing capabilities of the FPGA that led to throughput increase of the implemented classification process. Some researchers designed a pipeline stage for common and shared multipliers required for computations to decrease usage of duplicate multiplications [19,20].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hardware Acceleration of SVM-Based Classifier for Melanoma Images

Afifi

GholamHosseini

Sinha

2016

Image and Video Technology – PSIVT 2015 Workshops

View full text Add to dashboard Cite

Abstract. Melanoma is the most aggressive form of skin cancer which is responsible for the majority of skin cancer related deaths. Recently, image-based Computer Aided Diagnosis (CAD) systems are being increasingly used to help skin cancer specialists in detecting melanoma lesions early, and consequently reduce mortality rates. In this paper, we implement the most compute-intensive classification stage in the CAD onto FPGA, aiming to achieve acceleration of the system for deploying as an embedded device. A hardware/software co-design approach was proposed for implementing the Support Vector Machine (SVM) classifier for classifying melanoma images online in real-time. The hybrid Zynq platform was used for implementing the proposed architecture of the SVM classifier designed using the High Level Synthesis design methodology. The implemented SVM classification system on Zynq demonstrated high performance with low resources utilization and power consumption, meeting several embedded systems constraints.

show abstract

Section: Resultsmentioning

confidence: 83%

Section: Introductionmentioning

confidence: 99%

Hardware Acceleration of SVM-Based Classifier for Melanoma Images

Afifi

GholamHosseini

Sinha

2016

Image and Video Technology – PSIVT 2015 Workshops

View full text Add to dashboard Cite

show abstract

“…The researchers in works [14], [15] wanted to compare the performances of FPGA and GPU implementations of a human skin SVM classifier against the software performances. The critical hardware composes of FPGA were designed using HDL in a completely pipelined organization, even as the other elements like FIFO and interfaces were implemented in HLL.…”

Section: Common Pipelining Techniquementioning

confidence: 99%

“…The implementation results confirmed the excellence of the implemented fully pipelined FPGA architecture on GPU and CPU for a small number of image pixels, while the GPU implementation was the fastest for a big number of pixels. The advantage of FPGA implementation is that consumes less power than the GPU implementation [15].…”

Section: Common Pipelining Techniquementioning

confidence: 99%

FPGA Implementation of SVM for Nonlinear Systems Regression

Sayehi¹,

Machhout²,

Tourki³

2017

ijacsa

View full text Add to dashboard Cite

Abstract-This work resumes the previous implementations of Support Vector Machine for Classification and Regression and explicates the different methods and approaches adopted. Ever since the rarity of works in the field of nonlinear systems regression, an implementation of testing phase of SVM was proposed exploiting the parallelism and reconfigurability of FieldProgrammable Gate Arrays (FPGA) platform. The nonlinear system chosen for application was a real challenging model: a fluid level control system existing in our laboratory. The implemented design with fixed point precision demonstrates good enough results comparing with the software performances based on the Normalized Mean Squared Error. Whereas, in term of computation time, a speed-up factor of 60 orders of time comparing to MATLAB results was achieved. Due to the flexibility of Xilinx System Generator, the design is capable to be reused for any other system with different data sets sizes and various kernel functions.

show abstract

“…In the field of computer vision, Kalarot et al [27] implement a generic disparity algorithm on the GTX 280 and the Altera Stratix III platforms. A complete blood vessel detection system from medical images [28] is implemented on a GTX 295 GPU and a Spartan-3 FPGA, while more recently, a) Pietron et al [29] compare a human skin classifier implementation on a Tesla m2090 and a Virtex 5 device and b) the ceramic tile defect detection algorithm of [30] is evaluated on the 9800GT GPU and three different FPGAs. In a slightly different direction, the authors of [31] evaluate the performance of High-Level Synthesis of GPU to FPGA stereo matching code.…”

Section: Gpu-fpga Comparisonmentioning

confidence: 99%

Acceleration techniques and evaluation on multi-core CPU, GPU and FPGA for image processing and super-resolution

Georgis

Lentaris

Reisis

2016

J Real-Time Image Proc

View full text Add to dashboard Cite

Super-Resolution (SR) techniques constitute a key element in image applications, which need highresolution reconstruction while in the worst case only a single low-resolution observation is available. SR techniques involve computationally demanding processes and thus researchers are currently focusing on SR performance acceleration. Aiming at improving the SR performance, the current paper builds up on the characteristics of the L-SEABI Super-Resolution (SR) method to introduce parallelization techniques for GPUs and FPGAs. The proposed techniques accelerate GPU reconstruction of Ultra-High Definition content, by achieving three (3x) times faster than the real-time performance on mid-range and previous generation devices and at least nine times (9x) faster than the real-time performance on high-end GPUs. The FPGA design leads to a scalable architecture performing four (4x) times faster than the real-time on low-end Xilinx Virtex 5 devices and sixty-nine times (69x) faster than the real-time on the Virtex 2000t. Moreover, we confirm the benefits of the proposed acceleration techniques by employing them on a different category of image-processing algorithms: on window-based Disparity functions, for which the proposed GPU technique shows an improvement over the CPU performance ranging from 14 times (14x) to 64 times (64x) while the proposed FPGA architecture provides 29x acceleration.

show abstract

Comparison of GPU and FPGA Implementation of SVM Algorithm for Fast Image Segmentation

Cited by 16 publications

References 4 publications

Hardware Acceleration of SVM-Based Classifier for Melanoma Images

Hardware Acceleration of SVM-Based Classifier for Melanoma Images

FPGA Implementation of SVM for Nonlinear Systems Regression

Acceleration techniques and evaluation on multi-core CPU, GPU and FPGA for image processing and super-resolution

Contact Info

Product

Resources

About