Deep Learning on a Raspberry Pi for Real Time Face Recognition

Dürr, Oliver; Pauchard, Yves; Browarnik, Diego Hernan; Axthelm, Rebekka; Loeser, Martin

doi:10.2312/egp.20151036

Cited by 6 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in [92] the use of hybrid accelerators has decreased the detection time and improved the raspberry pi processing time performance. In the recognition process, the raspberry pi has an average of 1.5 FPS processing rate when neural network algorithms are used [76] [85]. However, the average value is exceeded in [92] and [37].…”

Section: Discussion and Recommendationsmentioning

confidence: 99%

“…5 convolution blocks using masks from (11 x 11) to (3 x 3), followed by ReLU rectification layer and Max pooling, and 3 fully connected layers were used. A similar implementation is done in [76] and achieved recognition accuracy of 97%. However, the system was tested on a small dataset of 6 persons with 40 pictures per person.…”

Section: B Neural Network Algorithms For Face Detection and Recognitionmentioning

confidence: 99%

“…Experiments using public benchmarks (i.e., FERET and LFW) showed that LBPNet approach achieved high recognition accuracies. In [76] a face recognition system implementation using CNN on Raspberry Pi Model B, could yield a latency of 529ms to detect and recognize a face in an image with 97% accuracy. Viola-Jones algorithm from Open CV library was used for face detection on 8 bits-gray scale image, while CNN, implemented in python, was used for classification.…”

Section: B Neural Network Algorithms For Face Detection and Recognitionmentioning

confidence: 99%

See 2 more Smart Citations

Hardware Accelerators for Real-Time Face Recognition: A Survey

2022

View full text Add to dashboard Cite

Real-time face recognition has been of great interest in the last decade due to its wide and variant critical applications which include biometrics, security in public places, and identification in login systems. This has encouraged researchers to design fast and accurate embedded and portable systems that are capable to detect and recognize a large number of faces at almost video frame rate. Due to the increasing volume of reference faces, traditional general purpose computing engines such as the ones based on Intel's Pentium processors have shown not to be adequate and various dedicated hardware accelerators based on either Graphical Processing Unit (GPU), Field Programmable Gate Arrays (FPGA), Application Specific Integrated Circuit (ASIC), or even multi-core Central Processing Units (CPU) have emerged. Earlier published review papers on face detection/recognition have discussed face detection and face recognition algorithms enhancement that improve the detection accuracy. Nevertheless, none of them has reviewed the hardware accelerators used for this application. Accordingly, this paper aims to provide a comprehensive review of the most recent face recognition algorithms and associated embedded hardware systems targeting real-time performance. A detailed comparison between neural network and non-neural network-based algorithms in terms of accuracy and processing time is provided. Discussions on their suitability to be implemented into parallel hardware architectures such as Single Instruction Multiple Thread (SIMT) or Single Instruction Multiple Data (SIMD) is also discussed.

show abstract

Section: Discussion and Recommendationsmentioning

confidence: 99%

Section: B Neural Network Algorithms For Face Detection and Recognitionmentioning

confidence: 99%

Section: B Neural Network Algorithms For Face Detection and Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

Hardware Accelerators for Real-Time Face Recognition: A Survey

2022

View full text Add to dashboard Cite

show abstract

“…Durr et al proposed a model that uses deep learning on Raspberry Pi for face recognition, and it is performed in real time where authors trained convolutional neural network (CNN) on a desktop PC and deployed on Raspberry Pi model B for classification procedure. OpenCV's results were outperformed, and an astounding accuracy of 97% was observed [23].…”

Section: Literature Surveymentioning

confidence: 99%

A Check on WHO Protocol Implementation for COVID-19 Using IoT

Sharma

Dhingra

Dawar

2021

Internet of Things and Its Applications

View full text Add to dashboard Cite

COVID-19, which is also known as coronavirus disease, causes a situation of emergency in all over the world from March 2020, and every country was under lockdown to control its rigorous spread. While other people are self-conscious about their looks, they hide their emotions from the public by hiding their faces. Scientists proved that wearing face masks works on impeding COVID-19 transmission [1]. Since the outbreak, the WHO suggested some measures to control the spread, and the governance bodies all over the world are adopting measures suggested by the WHO. The essential precautions that the World Health Organization suggested are to maintain personal hygiene and social distancing and to wear a face mask in public places. Wearing a mask in public areas is one of the most effective methods, and it actually reduces the growth rate of COVID-19 by 40%. However, wearing a mask for a very long time could be exhausting and frustrating, and this is the main reason that people do not follow it [2]. The lawmakers and the governments worldwide are facing a lot of difficulties in controlling the spread of this deadly virus [3]. To ensure that this protocol is followed, an IoT system is proposed, which will ensure a correct way to wear a face mask and thus can result in a controlled situation when it comes to the spread of the coronavirus pandemic.The coronavirus epidemic has given rise to an extraordinary degree of worldwide scientific cooperation. Artificial intelligence (AI) based on machine learning and deep learning can help to fight COVID-19 in many ways [4]. The advancements in the area of machine learning and data analysis have allowed various researchers and

show abstract