Secure robot face recognition in cloud environments

Chiranjeevi, K.

doi:10.1007/s11042-020-10253-5

Cited by 11 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ThedecoderismadeupoffourU-Netblocks.Figure(c)showstheU-Netblockinmoredetail.For up-sampling,theimprovedU-Netmodelemploysthesub-pixelconvolutioninitialisedtoconvolution NNresizeapproach.Sub-pixelconvolutionlayer(convolutionlayer+periodicshuffling)hasbeen usedtosubstitutethemodel'sde-convolutionlayer.Whencontrastedtoresizingconvolutions,subpixelconvolutionhasthebenefitsofgettingstrongermodelingcapabilitywiththesameconvergence rate and converges with less test errors (Karri, 2021). However, randomness initiation, it has a chequerboardartefact.Insteadofrandomselection,ICNRhasbeenemployed,whichincorporates convolutionaccompaniedbyclosestneighborresizing,asproposedinthework (Liuetal.,2018).…”

Section: Decoder Sectionmentioning

confidence: 99%

Brain Tumour Detection Through Modified UNet-Based Semantic Segmentation

Potnuru

Naick

2022

International Journal of Biomedical and Clinical Engineering

View full text Add to dashboard Cite

The determination of the tumor's extent is a major challenge in brain tumour treatment planning and measurement. Non-invasive magnetic resonance imaging (MRI) has evolved as a first-line diagnostic tool for brain malignancies without the use of ionising radiation. Manually segmenting the extent of a brain tumour from 3D MRI volumes is a time-consuming process that significantly relies on the experience of the operator. As a result, we suggested a modified UNet structure based on residual networks that use periodic shuffling at the encoder region of the original UNet and sub-pixel convolution at the decoder section in this research. The proposed UNet was tested on BraTS Challenge 2017 with high-grade glioma (HGG). The model was tested on BraTS 2017 and 2018 datasets. Tumour core (TC), whole tumour (WT), and enhancing core (EC) were the three major labels to be segmented. The test results shown that proposed UNet outperform the existing techniques.

show abstract

Section: Decoder Sectionmentioning

confidence: 99%

Brain Tumour Detection Through Modified UNet-Based Semantic Segmentation

Potnuru

Naick

2022

International Journal of Biomedical and Clinical Engineering

View full text Add to dashboard Cite

show abstract

“…Media technologies include tools to support global media processing ranging from audio, video, images, interactive media, video games, virtual reality, and augmented reality. As illustrated, a robot could utilize a patient privacy face recognition module to detect the patient and link him with a disease database hosted on a remote cloud server to retrieve the disease information in a privacy mode [17]. Then, the robot could navigate the map of the environment and locations of other robots through the Simultaneous Localization and Mapping (SLAM) method [15] to circulate the disease information of the patient in a secured setting.…”

Section: Autonomous Nursing Robotsmentioning

confidence: 99%

Fuzzy Guided Autonomous Nursing Robot through Wireless Beacon Network

Narayanan¹,

Krishnan

Sơn

et al. 2021

Multimed Tools Appl

View full text Add to dashboard Cite

Robotics is one of the most emerging technologies today, and are used in a variety of applications, ranging from complex rocket technology to monitoring of crops in agriculture. Robots can be exceptionally useful in a smart hospital environment provided that they are equipped with improved vision capabilities for detection and avoidance of obstacles present in their path, thus allowing robots to perform their tasks without any disturbance. In the particular case of Autonomous Nursing Robots, major essential issues are effective robot path planning for the delivery of medicines to patients, measuring the patient body parameters through sensors, interacting with and informing the patient, by means of voicebased modules, about the doctors visiting schedule, his/her body parameter details, etc. This paper presents an approach of a complete Autonomous Nursing Robot which supports all the aforementioned tasks. In this paper, we present a new Autonomous Nursing Robot system capable of operating in a smart hospital environment area. The objective of the system is to identify the patient room, perform robot path planning for the delivery of medicines to a patient, and measure the patient body parameters, through a wireless BLE (Bluetooth Low Energy) beacon receiver and the BLE beacon transmitter at the respective patient rooms. Assuming that a wireless beacon is kept at the patient room, the robot follows the beacon's signal, identifies the respective room and delivers the needed medicine to the patient. A new fuzzy controller system which consists of three ultrasonic sensors and one camera is developed to detect the optimal robot path and to avoid the robot collision with stable and moving obstacles. The fuzzy controller effectively detects obstacles in the robot's vicinity and makes proper decisions for avoiding them. The navigation of the robot is implemented on a BLE tag module by using the AOA (Angle of Arrival) method. The robot uses sensors to measure the patient body parameters and updates these data to the hospital patient database system in a private cloud mode. It also makes uses of a Google assistant to interact with the patients. The robotic system was implemented on the Raspberry Pi using Matlab 2018b. The system performance was evaluated on a PC with an Intel Core i5 processor, while the solar power was used to power the system. Several sensors, namely HC-SR04 ultrasonic sensor, Logitech HD 720p image sensor, a temperature sensor and a heart rate sensor are used together with a camera to generate datasets for testing the proposed system. In particular, the system was tested on operations taking place in the context of a private hospital in Tirunelveli, Tamilnadu, India. A detailed comparison is performed, through some performance metrics, such as Correlation, Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE), against the related works of Deepu et al., Huh and Seo, Chinmayi et al., Alli et al., Xu, Ran et al., and Lee et al. The experimental system validation showed that the fuzzy co...

show abstract

“…Experimental results are conducted using the ORL database [35]. The Olivetti Research Laboratory (ORL) face dataset contains a set of face images.…”

Section: Performance Analysis Of Cnn Based Robot Face Recognition Modelsmentioning

confidence: 99%

Privacy Preserving Face Recognition in Cloud Robotics: A Comparative Study

et al. 2021

Self Cite

View full text Add to dashboard Cite

Real-time robotic applications encounter the robot on board resources’ limitations. The speed of robot face recognition can be improved by incorporating cloud technology. However, the transmission of data to the cloud servers exposes the data to security and privacy attacks. Therefore, encryption algorithms need to be set up. This paper aims to study the security and performance of potential encryption algorithms and their impact on the deep-learning-based face recognition task’s accuracy. To this end, experiments are conducted for robot face recognition through various deep learning algorithms after encrypting the images of the ORL database using cryptography and image-processing based algorithms.

show abstract

Secure robot face recognition in cloud environments

Cited by 11 publications

References 39 publications

Brain Tumour Detection Through Modified UNet-Based Semantic Segmentation

Brain Tumour Detection Through Modified UNet-Based Semantic Segmentation

Fuzzy Guided Autonomous Nursing Robot through Wireless Beacon Network

Privacy Preserving Face Recognition in Cloud Robotics: A Comparative Study

Contact Info

Product

Resources

About