Parallel implementation and performance evaluation of facial recognition algorithms using open source technologies

Author(s):  
J. Suryaprasad ◽  
D. S. Sandesh ◽  
I. Priyanka ◽  
G. N. Pravalika ◽  
Aman Kumar
Buildings ◽  
2019 ◽  
Vol 9 (3) ◽  
pp. 59 ◽  
Author(s):  
Lenka Kabošová ◽  
Stanislav Kmeť ◽  
Dušan Katunský

Over the past few decades, digital tools have become indispensable in the field of architecture. The complex design tasks that make up architectural design methods benefit from utilizing advanced simulation software and, consequently, design solutions have become more nature-adapted and site-specific. Computer simulations and performance-oriented design enable us to address global challenges, such as climate change, in the preliminary conceptual design phase. In this paper, an innovative architectural design method is introduced. This method consists of the following: (1) an analysis of the local microclimate, specifically the wind situation; (2) the parametric shape generation of the airport terminal incorporating wind as a form-finding factor; (3) Computational Fluid Dynamics (CFD) analysis; and (4) wind-performance studies of various shapes and designs. A combination of programs, such as Rhinoceros (Rhino), and open-source plug-ins, such as Grasshopper and Swift, along with the post-processing software Paraview, are utilized for the wind-performance evaluation of a case study airport terminal in Reykjavik, Iceland. The objective of this wind-performance evaluation is to enhance the local wind situation and, by employing the proposed architectural shape, to regulate the wind pattern to find the optimal wind flow around the designed building. By utilizing the aforementioned software, or other open-source software, the proposed method can be easily integrated into regular architectural practice.


Author(s):  
Amir Dirin ◽  
Nicolas Delbiaggio ◽  
Janne Kauttonen

<p class="affiliations"><strong>Abstract— </strong>Computer visions and their applications have become important in contemporary life. Hence, researches on facial and object recognition have become increasingly important both from academicians and practitioners. Smart gadgets such as smartphones are nowadays capable of high processing power, memory capacity, along with high resolutions camera. Furthermore, the connectivity bandwidth and the speed of the interaction have significantly impacted the popularity of mobile object recognition applications. These developments in addition to computer vision’s algorithms advancement have transferred object’s recognitions from desktop environments to the mobile world. The aim of this paper to reveal the efficiency and accuracy of the existing open-source facial recognition algorithms in real-life settings. We use the following popular open-source algorithms for efficiency evaluations: Eigenfaces, Fisherfaces, Local Binary Pattern Histogram, the deep convolutional neural network algorithm, and OpenFace. The evaluations of the test cases indicate that among the compared facial recognition algorithms the OpenFace algorithm has the highest accuracy to identify faces. The findings of this study help the practitioner on their decision of the algorithm selections and the academician on how to improve the accuracy of the current algorithms even further.</p>


2016 ◽  
Vol 73 (1) ◽  
pp. 495-513 ◽  
Author(s):  
David García-Lucas ◽  
Gabriel Cebrián-Márquez ◽  
Pedro Cuenca

2002 ◽  
Author(s):  
James M. Baumann ◽  
Ronald L. Dilsavor ◽  
James Stubbles ◽  
John C. Mossing

2013 ◽  
Vol 13 (22) ◽  
pp. 5255-5259
Author(s):  
Jin Wang ◽  
Xiaodong Zhang ◽  
Shuo Zhang ◽  
Yingzi Li

Author(s):  
Khaldoon Moosa Mhaidat ◽  
Ahmad Baset ◽  
Osama Al-Khaleel

OpenSPARC is the only 64-bit Chip Multi-Threaded (CMT) processor that has ever been made open-source and non-proprietary. In this paper, the authors present an FPGA-based embedded system and methodology for prototyping and validating the OpenSPARC processor. They also present synthesis and performance evaluation results for OpenSPARC on a Virtex-5 FPGA platform. Light version of OpenSolaris was successfully booted on the platform, and the High Performance Embedded Computing (HPEC) benchmark suite was used to evaluate the performance. Xilinx ISE suite was used for synthesis, implementation, and chip programming. The down-scaled FPGA implementation of the processor runs at 81.3 MHz. The whole processor would require about 176453 Virtex-5 logic slices. To the best of their knowledge, they are the first researchers to report detailed FPGA synthesis results for OpenSPARC and evaluate its performance on FPGA using the HPEC benchmarks. Other researchers may find these results useful when comparing with other processors or studying the impact of a certain design change or addition on performance and cost.


2020 ◽  
Author(s):  
Xavier Cano-Ferrer ◽  
Sergi gomez

We present the design and performance evaluation of a 3D printable bionic hand developed to be manufactured, assembled and programmed in the simplest way by the user. This prosthetic device can be controlled by surface electromyography (EMG) performing the six most important types of grasp to achieve the activities of daily living (ADL’s). Our design represents an affordable option with competitive features when compared to the existing commercial and open source devices.


Sign in / Sign up

Export Citation Format

Share Document