Smart Mirror

description21 papers

group6 followers

lightbulbAbout this topic

A smart mirror is an interactive display that integrates digital technology with a reflective surface, enabling users to access information, control smart home devices, and utilize applications through voice commands or touch interfaces, while simultaneously serving as a traditional mirror.

lightbulbAbout this topic

Key research themes

1. How can Raspberry Pi-based smart mirrors integrate multimodal interaction and IoT functions for enhanced home automation and user convenience?

This research area focuses on leveraging Raspberry Pi microcomputers combined with various sensors and modules to create smart mirrors capable of face recognition, voice interaction, multimedia display, and IoT home automation functionalities. It is significant because it enables affordable, compact, and adaptable smart home interfaces that enhance daily user engagement and automate routine tasks seamlessly.

Design of Smart Mirror Based On Raspberry Pi

by Bhavana Jain H.N.

2022

Key finding: The paper demonstrated a cost-effective smart mirror prototype using a Raspberry Pi host and STM32 microcontroller, integrating face recognition via webcam, voice synthesis through SYN6288, and home automation controls such... Read more

articleView Paper downloadDownload

IoT based Smart Mirror Using Raspberry PI

by IJRASET Publication

2023, International Journal for Research in Applied Science & Engineering Technology (IJRASET)

Key finding: This study expanded the Raspberry Pi smart mirror concept with advanced touch interface using IR frames and 8-channel relay control circuitry for home appliance automation. It emphasized practical implementation details... Read more

articleView Paper downloadDownload

IoT Based Smart Mirror Using Raspberry Pi 4 and YOLO Algorithm: A Novel Framework for Interactive Display

by Dr.Viswanatha V .

2022, INDIAN JOURNAL OF SCIENCE AND TECHNOLOGY

Key finding: By incorporating the YOLO deep learning algorithm on Raspberry Pi 3 and 4 models, the system advanced human detection capabilities for security and intrusion monitoring while providing personalized displays for weather, news,... Read more

articleView Paper downloadDownload

Smart Mirror Using Raspberry PI

by IJRASET Publication

2022, International Journal for Research in Applied Science & Engineering Technology (IJRASET)

Key finding: This work presented a smart mirror system that accepts voice commands and facial recognition to switch between standard reflective and smart display modes. It underlined improvements in user lifestyle through quick access to... Read more

articleView Paper downloadDownload

keyboard_arrow_downShow more

2. What are the current machine learning and computer vision approaches utilized in smart mirrors for user identification, security, and health monitoring?

This theme investigates the application of machine learning techniques such as convolutional neural networks (CNNs), YOLO object detection, and multimodal computer vision to enable smart mirrors with person identification, intrusion detection, and health status assessment. These capabilities enhance personalization, security, and potential healthcare functionalities within ambient assisted living environments.

DEVELOPMENT OF HUMAN MACHINE INTERFACE USING SMART MIRROR AND FACE RECOGNITION ALGORITHM

by IAEME Publication

2021, IAEME PUBLICATION

Key finding: Implemented a convolutional neural network (CNN)-based face recognition system integrated within a smart mirror, achieving 100% accuracy in authorized user identification. This approach directly addressed unauthorized access... Read more

articleView Paper downloadDownload

IoT Based Smart Mirror Using Raspberry Pi 4 and YOLO Algorithm: A Novel Framework for Interactive Display

by Dr.Viswanatha V .

2022, INDIAN JOURNAL OF SCIENCE AND TECHNOLOGY

Key finding: Applied the YOLO (You Only Look Once) algorithm for real-time human detection to support security functions such as intrusion detection and monitoring. This enhanced object detection capability enabled the mirror to send... Read more

articleView Paper downloadDownload

Design and Implementation of Smart Glass with Voice Detection Capability to Help Visually Impaired People

by gyan prakash

2025, International Journal of MC Square Scientific Research

Key finding: Though focused on smart glasses rather than mirrors, this work demonstrated an integrated vision-based system using a camera sensor and digital signal processing to capture images, perform image-based object and scene... Read more

articleView Paper downloadDownload

Wize Mirror - a smart, multisensory cardio-metabolic risk monitoring system

by Matthew Pediaditis

2024, Computer Vision and Image Understanding

Key finding: Developed a multisensory smart mirror platform using computer vision and machine learning for 3D morphological face analysis and recognition of psychosomatic states linked to cardio-metabolic health risks. This research... Read more

articleView Paper downloadDownload

keyboard_arrow_downShow more

3. How are smart mirrors being adapted for specialized public and institutional information systems using voice interaction and environmental monitoring?

This research stream explores smart mirrors configured as interactive information desks or ambient interfaces in public institutions like universities. It emphasizes voice-assisted query handling, real-time environment sensing (e.g., entrance monitoring), and multimodal interactivity aimed at improving accessibility, reducing dependency on staff, and supporting users including disabled populations.

Smart information desk system with voice assistant for universities

by Dabiah alboaneen

2022, International Journal of Electrical and Computer Engineering (IJECE)

Key finding: Implemented a university smart mirror information desk on Raspberry Pi 4, using voice recognition to provide hands-free responses about academic inquiries, lecturer office hours, and exam schedules. The system also integrated... Read more

articleView Paper downloadDownload

A Mobile-Programmable Smart Mirror for Ambient IoT Environments

by tara al-hadithy

2022, 2017 5th International Conference on Future Internet of Things and Cloud Workshops (FiCloudW)

Key finding: Proposed a service-oriented, highly customizable smart mirror architecture that interfaces with mobile applications to allow personalized user profile generation and interaction within ambient IoT settings. The system’s... Read more

articleView Paper downloadDownload

Visual Aid Systems from Smart City to Improve the Life of People with Low Vision

by ioana baritz

2024, Sustainability

Key finding: Discussed urban-level smart systems including smart mirrors as assistive technologies for visually impaired citizens within smart city infrastructures. It emphasized integration of interactive digital modules for navigation... Read more

articleView Paper downloadDownload

keyboard_arrow_downShow more

All papers in Smart Mirror

Raspberry Pi Augmentation: A cost effective solution to Google Glass

by Manoj Bramhe

2024

In this paper, we present the concept of using a Raspberry Pi as the main computer. This human enhancement is voice controlled, uses a camera module to interact with the outside world and process the retrieved information for real-time... more

descriptionView Paper arrow_downwardDownload

Research and Analysis of Smart Mirror

by Sahil Yadav

2024

The project shows the design of a smart device-Smart Mirror. The smart mirror here is mainly for home environment. These smart mirrors are not widely used due to cost or high requirements of hardware. The proposed smart mirror will be... more

descriptionView Paper arrow_downwardDownload

Enhancing Mood Based Music Selection through Physiological Sensing Technology

by IJRASET Publication

2024, International Journal for Research in Applied Science & Engineering Technology (IJRASET)

This research paper presents the development of an emotional sensor system that combines computer vision techniques with physiological sensors to detect and analyse facial expressions. The system utilizes a webcam for capturing facial... more

descriptionView Paper arrow_downwardDownload

Research and Analysis of Smart Mirror

by Sahil Yadav

2024

descriptionView Paper arrow_downwardDownload

Wize Mirror - a smart, multisensory cardio-metabolic risk monitoring system

by Matthew Pediaditis

2024, Computer Vision and Image Understanding

In the recent years personal health monitoring systems have been gaining popularity, both as a result of the pull from the general population, keen to improve well-being and early detection of possibly serious health conditions and the... more

descriptionView Paper arrow_downwardDownload

Face morphology: Can it tell us something about body weight and fat?

by Luca Bastiani

2024, Computers in Biology and Medicine

This paper proposes a method for an automatic extraction of geometric features, related to weight parameters, from 3D facial data acquired with lowcost depth scanners. The novelty of the method relies both on the processing of the 3D... more

descriptionView Paper arrow_downwardDownload

HealthNet: IoT-based Healthcare Monitoring and Management System

by Adnan Hasan and

2024, IJRASET

The Internet of Things (IoT) is a network of interconnected devices that can collect, store, analyze and transmit data over the Internet. IoT has the potential to revolutionize the healthcare industry by enabling remote patient care,... more

descriptionView Paper arrow_downwardDownload

Smart Infant Baby Monitoring System Using IOT

by IJRASET Publication

2024, International Journal for Research in Applied Science & Engineering Technology (IJRASET)

The Smart Infant Baby Monitoring System is an IOT-based project. The goal of this research is to lower SIDS. The primary factor in infant mortality is sudden infant death syndrome. Infants' breathing, temperature, heart rate, and... more

While reading parameters it displays as reading. Fig: Reading is displayed on LCD

If finger is placed then the parameters are shown on LCD

GSM SIM 900 A is the GSM module used for GPRS/GPS communication. The module offers 9OOMHZ nad 1800 MHZ frequency band to send SMS. In this any abnormal parameter is noted then the SMS is send to parents mobile.

MAX30102 is a pulse oximetry and heart rate monitoring system. It is a biosensor.It is used to monitor temperature, heart rate and SPO2. In this project when a baby finger is placed on sendor, it monitors the baby’s body temperature, hear rate and SPO2. If there is any abnormal parameter is noted then it sends signal to the processor. Each component of the Raspberry Pi Pico is connected to the other via wired or wireless connections, acting as a compact computer. It evaluates the values in line with the code we have given it, leading to the intended outcome. The temperature and heart rate sensors take measurements and produce an output. The erroneous parameters are sent by SMS and LCD, respectively. The baby's screams are picked up by the condenser microphone. The microphone sends a signal to the microcontroller while the baby is crying. Next, a signal to switch ON the DC motor is sent. Then the cradle swings.

The project trial has been done on a baby by monitoring health conditions using this project. The results are accurate

The measured parameters calculated and if abnormal parameters are noted the SMS is sent via GSM modul:

ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538 Volume I1 Issue IV Apr 2023- Available at www.ijraset.com With the use of wireless technology and textile sensors that make it pleasant to wear and more accurate and precise than previous sensors, the system we have suggested seeks to monitor the baby’s vital indicators, including heartbeats and body temperature. There is now more information that can be broadcast via the internet to enable remote access. The camera module that is mounted to the cradle aids in continuous movement tracking and finite monitoring of the infant in a finite area.

descriptionView Paper arrow_downwardDownload

Artificially Intelligent Smart Mirror using Raspberry Pi

by Sayeed Bin Hossain

2023, International Journal of Computer Applications

In this era of evolving technology, the human life is becoming simpler and time efficient. This paper depicts the design and development of smart mirror which will make our everyday life easier and time efficient. Smart Mirror is a simple... more

descriptionView Paper arrow_downwardDownload

Health Mirror

by priya pal

2023, International Journal for Research in Applied Science and Engineering Technology

This paper describes and explains design and working of a mirror made smart enough to be a health mirror which is IoT based and works with Arduino mega. This health mirror act as a personal health assistance which helps to do regular... more

Fig.1 Implementation of the system 8266 Wifi Module: The Wifi module supplies 3.3V. The function of the module is to update the data on the web page.

descriptionView Paper arrow_downwardDownload

Health Mirror

by Paurnima vadak

2023, International Journal for Research in Applied Science and Engineering Technology

descriptionView Paper arrow_downwardDownload

A smart mirror to promote a healthy lifestyle

by Massimo Martinelli

2023, Biosystems Engineering

ICT solutions to foster behavioural change have been shown to be effective in implementing primary prevention in terms of a healthy lifestyle. Primary prevention is the most viable approach to reduce the socioeconomic burden of chronic... more

descriptionView Paper arrow_downwardDownload

Face morphology: Can it tell us something about body weight and fat?

by Maria A Pascali

2023, Computers in Biology and Medicine

descriptionView Paper arrow_downwardDownload

Wize Mirror - a smart, multisensory cardio-metabolic risk monitoring system

by Maria A Pascali

2023, Computer Vision and Image Understanding

descriptionView Paper arrow_downwardDownload

Mirror mirror on the wall… An intelligent multisensory mirror for well-being self-assessment

by Maria A Pascali

2023, 2015 IEEE International Conference on Multimedia and Expo (ICME)

The face reveals the healthy status of an individual, through a combination of physical signs and facial expressions. The project SEMEOTICONS is translating the semeiotic code of the human face into computational descriptors and measures,... more

descriptionView Paper arrow_downwardDownload

A smart mirror to promote a healthy lifestyle

by Maria A Pascali

2023, Biosystems Engineering

descriptionView Paper arrow_downwardDownload

Evaluation of head pose features for stress detection and classification

by Dimitris Manousos

2023, 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI)

This paper investigates variations in head pose features in response to specific stressors. A proper experiment consisting of neutral and stressful states was performed aiming to cover different types of stress affect. Then, features... more

descriptionView Paper arrow_downwardDownload

Wize Mirror - a smart, multisensory cardio-metabolic risk monitoring system

by Dimitris Manousos

2023, Computer Vision and Image Understanding

Fig. 1. Illustrative representation of the Wize Mirror. On the right widgets panel with the user graphical interface, optionally this may also include: clock, weather forecast news, etc. On the left pictorial representation of different devices used for data acquisition.

Fig. 2. Processing pipeline of the Wize Mirror methods described in this paper.

Fig. 3. Comparison between detected and tracked faces obtained with the random forest and Kalman filter (first row), and the refined head pose using the ICP algorithm (second row). The depth images have been coloured in order to facilitate the visualization, the colour information is not used in the process.

Fig. 4. Example of sub-sampling for four different levels to perform the multi-resolution registration.

Fig. 5. Comparison between the two different segmentation stages used for pre- processing the input depth data for subsequent 3D reconstruction. Input depth im- ages (left), depth segmentation (centre) and model segmentation (right). The colour images are only used to visualise the segmentation results. The colour information is not used in any of the segmentation methods.

Fig. 6. Average face models used for face segmentation, generated using Face- Gen software. Model used for the reconstruction needed in morphological analysis of cardio-metabolic risks (left). Model utilised to build the personalised mask for tracking (right).

Fig. 7. Plastic head model used for the reconstruction experiments (left), recon- structed model using the proposed method (right).

Fig. 8. Comparison between 3D reconstructions obtained using the proposed method. The images on the top represent the signed distance between the two reconstructions: the current reconstruction and a reference reconstruction. The histograms (on the bottom) are calculated with the number of points belonging to the reconstructed face (63,000 points on average) and clustered depending on their signed distance (in meters) to the reference scan. The average error for all the experiments is 1.7 + 2.4 mm.

Fig. 9. 3D geometric reconstruction results. RGB image (left), 3D reconstruction fot morphological analysis of cardio-metabolic risk (centre), and personalised mask fot face tracking (right).

Fig. 10. The 23 landmarks used to analyse faces from the morphological viewpoint.

List of linear and planar measurements which were found to correlate with waist circumference in Lee and Kim (2014). dg stands for Euclidean distance, d, horizontal (Euclidean) distance, dy vertical (Euclidean) dis- tance, and A(p;,..., Pn) is the area of the polygon formed by points Di gany Pn. Fig. 10 explains both the position and the label of the land- Fig. 11. Geodesic (left) and Euclidean (right) distance between two landmarks.

Fig. 12. Two views of each curve passing through four landmarks, on a 3D face model. In the first (resp. second) row is visualized the geodesic path a (resp. b).

Fig. 13. Sections given by the intersection of the 3D face mesh with equally-spaced planes perpendicular to the z-axis.

Fig. 15. A visualization of the features f3, f6, and f7. Note: due to the symmetry of the face model used, f6 and f7 are equal. Table 5

Fig. 16. Scatter plots for the subjects belonging to three groups of fatness: level 1, in red, level 5, in green, and level 10, in blue) in the embedding space given by the features f1 and f2, f3 and f6, f11 and f12, Lgeod, and Lgeod,, meanLZ and meanAZ. (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article).

Fig. 17. Graphs of a selection of the features (f3,Lgeoda, meanLZ), computed on the whole dataset; with a zoom on the 7th seed

Fig. 18. Selected geometric features: f3, f6, Lgeoda, meanLZ, computed on a set of 10 subjects. Results are visualised as scatter plot of each feature vs BMI (blue) and weight (red). (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article).

Fig. 19. Eye opening average distance calculation between the two upper and lower eye-lid points (a) and variability of eye average distance and blink threshold (b).

Fig. 20. Spatial distribution of landmarks on human face.

Fig. 21. Landmarks distribution (a); landmarks distribution after GPA alignment (b).

Fig. 22. Flowchart of head motion algorithm.

Sensitivity (True positive rate, TPR) and accuracy (Positive predictive value, PPV) experiments. First row contains the different thresholds used to consider a detection true positive. If the distance between the detected nose position and the ground truth is smaller than the thresh- old, it is a true positive, otherwise it is considered a false negative. A to- tal of 607 images were processed. RF represents the method described in Fanelli et al. (2011), whereas WM represents the proposed method. Fig. 4). Furthermore, in order to keep the real-time processing con- straint at a high frame rate, only four iterations of the ICP are exe- cuted as the results showed to be suitable for the post-processing by other functionalities of the system.

Results sample for 4 subjects. For each subject BMI and weight were collected ; and some of the geometric fea- tures implemented were computed: f2, f3, f6, Lgeoda, meanLZ. studies. For extracting the blink rate, the AAM is used in order to segment the eyelid area and to mark out the eyeball perime- ter with specific landmarks (six landmark points for each eye). Then, the average distance between the two upper and lower eye- lid points as shown in Fig. 19(a) is calculated. Eye blinks can be seen as sharp negative spikes in the extracted signal as shown in Fig. 19(b).

Detailed performance results of the lip twitching detection algorithm. Table 7

Results of the head motion algorithm, the ground truth and the accuracy. ered to be the ground truth. The duration of the videos was also pre-defined in order to extract the ground truth of speed. Eight different videos were captured with horizontal and vertical move- ments at various speeds (mm/s) and distances (mm).

descriptionView Paper arrow_downwardDownload

IoT based Smart Mirror using Raspberry Pi

by Chandana Priya

2023, International Journal for Research in Applied Science and Engineering Technology

This project depicts the design and development of smart mirror that represents an elegant interface for glancing information and also used for thief detection in a home environment. A smart mirror is a system that functions as mirror... more

descriptionView Paper arrow_downwardDownload

Artificially Intelligent Smart Mirror using Raspberry Pi

by Abdullahil Kafi

2023, International Journal of Computer Applications

descriptionView Paper arrow_downwardDownload

Reflecta: Smart Mirror Using Arduino

by International Journal of Advances in Engineering Architecture Science and Technology (IJAEAST)

2023, International Journal of Advances in Engineering Architecture Science and Technology

Background: In this world, everybody keeps running behind solitude and comfort. Presentday
man has diverse Innovations for a similar purpose. A Brilliant Mirror is proposed, which
is an interactive system that keeps the user updated on the day-to-day happenings. Think about
a situation in which you could examine the mirror and discover something other than yourself.
It will inform you of the time and date each time you investigate it. It will be interesting if the
Mirror recognises the user and reminds them of important meetings on that day. Imagine a
scenario in which the mirror could disclose that it’s drizzling outside and prescribe taking an
umbrella. It sounds fascinating, isn’t that so? An intuitive Mirror is offered as a result. The
Smart Mirror gives a close experience that enables the user to simply stroll up and be greeted
with information.
Objectives: The Smart Mirror system, which is based on the concept of the Internet of Things
(IoT), was developed specifically to allow users to manage and control house appliances
through voice recognition. A Smart Mirror can display the weather, time, date, and traffic
conditions on the mirror. These features can all be implemented by using the laptop with
libraries and data from the Internet. The standard method for creating a Smart Mirror involves
covering the LC-monitors with an acrylic sheet. The Web browser and JavaScript or Python
are used for the display.
Methods / Statistical Analysis: The mirror shows the time of the CPU, and the international
calendar is also integrated to show the upcoming holidays of any location. Open-Source
Websites are used to fetch the calendar. The news functionality is also implemented, which
will generate the RSS feed of any newspaper in the world. We have also implemented speech
recognition for controlling the home appliances in the Smart Home System. The Intrusion
Detection System uses a cascade algorithm. Human Emotion Detection uses the Human
Landmark Algorithm, followed by CNN.
Application / Improvements: The display can show anything you want on the mirror’s surface,
such as current time, weather forecast, news feed, and news feed headlines. Improvements can
also be made in this field, like updating it to become a touch screen and including maps in
offices, schools, colleges, and Industries.

Figure 1. Outer Structure Hardware and software components make up the system as a whole. The hardware model consists of a two-way mirror covering an LC-screen with a diagonal measurement of about

23". Instead of the regular Raspberry Pi OS, with regard to the software, we run Magic-mirror modules on a local server that create web content that is seen on the screen. To gather audio input, a microphone is connected to the Arduino for home automation purposes. A wooden frame contains all of the components. Layered architecture and client-server architecture are both used in the system's design. The GUI, which is based on the OS we utilize for system development, is where the user interacts ey iy yy a ry When users attempt to directly alter their settings, they will be sent an application call to the underlying OS, which will change the system accordingly. The system uses the Internet to communicate with remote clients. The system operates as a client for the web services while receiving information for interface modules. When communicating with other smart devices, the system will operate as an information server.

Figure 5. Home Automation Mart mirrors are straight from science fiction. They are a component of a positive future vision n which screens and data are pervasive and available to provide you with any information you equire at any time. In essence, the mirror appears to be a regular mirror, but as someone pproaches it, the scene changes. The mirror offers its users a practical, approachable, and nteractive user interface (UI) for accessing their social media accounts, messaging services, tc. It contains widgets for showing the time, events, weather, and most recent news headlines. ‘he Smart Mirror would assist in creating smart homes with embedded artificial intelligence nd locating its uses in many sectors of the economy. Switching home appliances becomes asy with the mirror. Virtual dressing is a clever method to test your sense of style, and it makes ife in malls much simpler. Such an intelligent mirror will only increase the home's beauty. ‘he home appliances in the Home Control module are managed via voice commands. Since ve utilised an Arduino, a microphone should be connected to a Bluetooth module, and the tome control module is used to operate all of the appliances in the house. We've connected he voice commands for home automation to the mirror. The mirror accepts commands from he user to carry out actions like turning on a light, turning off a light, or turning on and off a an as input and executes the corresponding duties.

The FER in standard FER methods consists of three main processes, as indicated in Figure.6: (1) detection of the face and facial components, (2) feature extraction, and (3) expression classification. The process begins with the detection of a face picture from an input image, followed by the identification of facial landmarks or facial components (such as the eyes and nose). The facial components are then used to extract a variety of spatial and temporal data. Third, the FE classifiers that have already been trained, like a support vector machine (SVM),

The project presents different information in such a way that it seamlessly blends with the task of morning grooming.

descriptionView Paper arrow_downwardDownload

Robust face tracking with a consumer depth camera

by Jimmy Huang

2023, 2012 19th IEEE International Conference on Image Processing

We address the problem of tracking human faces under various poses and lighting conditions. Reliable face tracking is a challenging task. The shapes of the faces may change dramatically with various identities, poses and expressions.... more

descriptionView Paper arrow_downwardDownload

Energy Saving Solution using IoT

by IJRASET Publication

2023, International Journal for Research in Applied Science & Engineering Technology (IJRASET)

Now a days the home environment is introduced with a network enabled digital technology. This type of home automation increases the connectivity of smart equipment within the room. With the continuity of home automation, we have designed... more

Table 1 Relevant studies on advantages and disadvantages of Smart Appliances

In conclusion, it is the privilege of every person to utilise smart electrical appliances systems that will automaticallywarn users when a switch is ON or OFF and have the ability to significantly increase the efficiency of how we use electricity. When a need is sensed, switches are monitored and automatically turned on. In some instances, we notice only a few people seated in one corner of the room while the fan, light, and air conditioner are all functioning. All of these amount to wasteful energy waste that depletes the nation's energy supply. Several studies have been done on automated lighting systems with visitor counters, which are used in smart lighting systems. Overall, using smart electrical appliance technologies could significantly increase savings. By automatically turning on the appliances that are essential based on the amount of people present in the hall, you can save electricity from being wasted when it's not necessary.

descriptionView Paper arrow_downwardDownload

Smart Mirror using Raspberry Pi

by IJRASET Publication and

2023, International Journal for Research in Applied Science & Engineering Technology (IJRASET)

This project has been developed within the context of a time where every day we see more and more connected devices. The Internet transformed our lives by connecting us more easily to information and other people in the virtual world.... more

Every mirror works on different technologies and platforms. The functionalities of these mirrors also differ. So, we had proposed a mirror which works in a simple structure and has all the required functions for the user such as news, time & date, weather and many more.

descriptionView Paper arrow_downwardDownload

Robust Model-Based 3D Head Pose Estimation

by Iuri Frosio

2023, 2015 IEEE International Conference on Computer Vision (ICCV)

We introduce a method for accurate three dimensional head pose estimation using a commodity depth camera. We perform pose estimation by registering a morphable face model to the measured depth data, using a combination of particle swarm... more

descriptionView Paper arrow_downwardDownload

Smart Aquarium Monitoring System Using IoT

by IJRASET Publication

2023, International Journal for Research in Applied Science & Engineering Technology (IJRASET)

Smart aquarium monitoring system is an automatic system that is taking care of the pet fish in the aquarium is a tedious process and should be properly set up and maintained in a healthy manner or else the fish will be destined for an... more

descriptionView Paper arrow_downwardDownload

A virtual individual's model based on facial expression analysis: A non-intrusive approach for wellbeing monitoring and self-management

by Ειρήνη Χριστινάκη

2023, 13th IEEE International Conference on BioInformatics and BioEngineering

Facial expressions are visible signs of the affective and psychological state of a person, which is strictly correlated with the pathogenesis of clinically relevant diseases and more in general with individuals' wellbeing. The main idea... more

descriptionView Paper arrow_downwardDownload

A Smart Mirror for Emotion Monitoring in Home Environments

by Raimondo Schettini

2023, Sensors

Smart mirrors are devices that can display any kind of information and can interact with the user using touch and voice commands. Different kinds of smart mirrors exist: general purpose, medical, fashion, and other task specific ones.... more

descriptionView Paper arrow_downwardDownload

Smart Mirror for Security and Home Appliances

by siva nagaraju

2023

The aim of the paper is design and develop a smart mirror for security and home appliances.The present generation devices are built with smart capabilities. The intelligence is embedded in themto act wise in deployed environment. Mirrors... more

descriptionView Paper arrow_downwardDownload

Healthcare Monitoring System Using IOT

by Vansh Garg

2023, International Journal for Research in Applied Science & Engineering Technology (IJRASET)

The last ten years have seen a shift in the healthcare monitoring systems, making them one of the most major systems. Even though there are millions of medical facilities worldwide, it is challenging to attend to each and every patient,... more

descriptionView Paper arrow_downwardDownload

IoT based Smart Mirror Using Raspberry PI

by IJRASET Publication

2023, International Journal for Research in Applied Science & Engineering Technology (IJRASET)

This paper describes the design, construction and working of an IoT based smart mirror. Every morning our day begins by watching ourselves at least once in mirror before leaving our homes. We interact with it psychologically to find out... more

descriptionView Paper arrow_downwardDownload

Healthcare Monitoring System for Remote Areas

by IJRASET Publication

2023, International Journal for Research in Applied Science & Engineering Technology (IJRASET)

Doctors now place a high importance on ongoing patient health monitoring since it gives them the chance to save a patient's life. So, the primary objective is to develop a patient monitoring system that can monitor a patient's various... more

Fig.1 Arduino Board(A Tmega 328P Microcontroller) B. Luigi Atzori-[ Department of Electrical and Electronic Engineering, University of Cagliari] The implementation and integration of technologies, wired and wireless sensors, tracking technologies, identification, communication options, and the promising paradigm are all topics covered in this study. The primary objective of this essay is the work done in a variety of domains, including information science, telecommunication, and electronics. The survey in this work enhances the tracking sensors, identification sensors, and communication protocols..

B. Sensors: The sensors used here are: DHT11 sensor The thermistor for measuring temperature and a capacitive humidity detector make up the DHT11 sensor. The dielectric in moisture-detecting capacitors is made up of two electrodes and a moisture-retention substrate. These changing resistance values are measured, processed, and converted to digital format by the IC.

Fig.5 Multilayer Preceptron Neural Network(MLPNN) After receiving accurate information from the patient, the doctor can access a website where they can view the patient's parameters and give real-time comments based on the patient's medical requirements. On dynamic webpages, sensor data is received. Columns can be used to display all sensor data. Patients should monitor the data to look for probable cardiovascular problems and should see a doctor if the results are not favourable. The Information and Timing column additionally contains information and data timing. Every two minutes, the server site sends the data to the dynamic website. As a result, every patient's medical history is kept, which can be used for improved remote healthcare and diagnosis.

descriptionView Paper arrow_downwardDownload

Voice Activated Desktop Assistant Using Python

by IJRASET Publication

2022, International Journal for Research in Applied Science & Engineering Technology (IJRASET)

The development in science over time has been unmeasurable. From the first digital laptop constructed by using Eniac having a clock pace of 100KHz to Summit developed by the US Department of Energy has an overall performance of 148.6... more

descriptionView Paper arrow_downwardDownload

Smart Mirror using IoT and Raspberry Pi

by IJRASET Publication

2022, International Journal for Research in Applied Science & Engineering Technology (IJRASET)

Smart mirrors as a concept are growing rapidly. These mirrors directly affect the day to day lives of the people as it provides customization and a luxurious lifestyle. With the help of devices like smart mirrors people are getting... more

descriptionView Paper arrow_downwardDownload

Research and Analysis of Smart Mirror

by sahil yadav

2022

descriptionView Paper arrow_downwardDownload

Smart Mirror for Vehicular System Using Raspberry Pi

by dipali gadakh

2022, International Journal of Innovative Research in Technology

Intelligent mirrors, which continue the works today and will take its place in the future technology, provide both mirror and computer aided information services to its users. Thanks to the micro-controller cards onboard, these systems,... more

descriptionView Paper arrow_downwardDownload

IoT Based Smart Mirror Using Raspberry Pi 4 and YOLO Algorithm: A Novel Framework for Interactive Display

by Dr.Viswanatha V .

2022, INDIAN JOURNAL OF SCIENCE AND TECHNOLOGY

Objectives: The primary goal of this device is to support the user in a variety of ways, and by enabling communication between the user and the gadget, we can demonstrate the user’s control over the location where the device will be Built... more

In the modern world, practically every piece of equipment has been transformed into a smart device thanks to technological advancements. From everyday objects to the most cutting-edge electronic equipment, almost all electronics are becoming intelligent. Modern products’ *smart” characteristics are a result of the inclusion of prediction algorithms and artificial intelligence (AI). In light of this, a smart device that may present personalized data displayed on the screen and behave intelligently by offering security as required is suggested. The technology can be used to provide security in a deployed setting. It can also keep an eye on people. Typically, people use mirrors to get ready for the day’s work. According to some research, an average person spends at least 28 minutes every day looking in the mirror“!), The primary idea is to use this time to notify a person of the most recent news, weather, date, time, and calendar adjustments as a result. It is quite difficult to find time to check the news and other updates, like the weather, because of how hectic life has become. Additionally, there is a lack of a package that compiles and shows all of this information on a single screen. The suggested system is interactive, that Smart Mirror even as you are getting ready to display relevant and necessary information. There have been many different systems offered up to this point, but the way the product is used makes a significant difference °->), The majority of the items on the market are informational, passive, and barely interactive. Such a system's main function is to show information on the mirror, and it may be operated with any type of input, including keyboard, or mobile instructions. A two-way acrylic sheet, a mirror, an LCD (liquid crystal display), or an LED display can all be used as displays for these smart mirrors. The proposed system is capable of responding to orders issued from mobile devices °®) . The proposed work functions as a security precaution, a tool for human monitoring, and a means of information dissemination. The system helps in detecting intrusions. The camera attached to the Raspberry Pi is triggered as soon as the PIR (Passive Infrared Sensor) sensor detects activity, motion, or movement. The camera attached to the Raspberry Pi4 latest model is taking pictures. Using image processing methods like Background Subtraction and the Simple Frame Difference Approach, the invasion is found. The administrator of the mirror will receive notification of the incursion through an alert message along with a photo of the offender. Additionally, the technology is being developed for human monitoring. Families are becoming smaller in size today. Thus, it becomes challenging to keep an eye on kids, the elderly, and the ill). It is challenging to watch over children when they get home from school due to busy schedules and working parents. An alarm message will be issued to the Smart Mirror administrator if the person moves out of the camera’s field of view. The proposed methodology will be useful for employee monitoring in jewelry stores, prisoner monitoring in jails, and monitoring prisoners in hospitals“! (11),

in this case, commands can also be supplied through mobile phones using the appropriate interface

This proposed architecture shown in Figure 4 uses raspberry pias the core of it, and we design a system in such a way that al the notifications which are preloaded are available to the defined user so that he can avail of the latest news or the web service: in an instant, so the defined user can avail all the necessary service. So the architecture works basically in the following way, first, the camera will be placed in the required area so that it can capture the necessary image, and the captured image will processed inside a raspberry pi which will be in the core and it does all the necessary calculations and it identifies the requirec portions and it will split the processed information to perform the two actions they are human detection and intrusion detectior so at first it will identify a person in the image and it will process the pre-loaded data and matches the captured image so if t match synchronizes then it will move forward to the next stage, and in the intrusion detection, it will just sense the object anc alerts if the object is an unauthorized one using PIR sensors. So here it can also be controlled using the mobile phones using the respective interface, and all the information which are already included in the device is processed and displayed over t screen. a Dé ne ne

Fig 6. Actual Detection Prediction Process The bounding box followed for the grid cell is as shown in Figure 5. b,, and b;, represent the prediction’s width and height, whereas b, and by are the predictions x and y center coordinates. The network outputs are denoted by the words ty, ty, t,, and ty. The top-left grid coordinates are represented by the words c, and cy. py and p, stand for the box’s anchor dimensions. Figure 5 explains the real procedure of detection and prediction 97) 2),

Fig 7. Schematic Diagram of the YOLO algorithm

Fig 11. Yolo object Detection output Figure 11 illustrates how the human in the input image is recognized by its classes and assigns each object by its tag and ha dimensions on the detected Image. Figure 12 illustrates how each object by its tag has dimensions on the detected image and sends the message to the owner via email.

descriptionView Paper arrow_downwardDownload

Smart information desk system with voice assistant for universities

by Dabiah alboaneen

2022, International Journal of Electrical and Computer Engineering (IJECE)

This article aims to develop a smart information desk system through a smart mirror for universities. It is a mirror with extra capabilities of displaying answers for academic inquiries such as asking about the lecturers’ office numbers... more

descriptionView Paper arrow_downwardDownload

Stress and anxiety detection using facial cues from videos

by Eleni Kazantzaki

2022, Biomedical Signal Processing and Control

This study develops a framework for the detection and analysis of stress/anxiety emotional states through video-recorded facial cues. A thorough experimental protocol was established to induce systematic variability in affective states... more

descriptionView Paper arrow_downwardDownload

Wize Mirror - a smart, multisensory cardio-metabolic risk monitoring system

by Eleni Kazantzaki

2022, Computer Vision and Image Understanding

descriptionView Paper arrow_downwardDownload

Gym Trainer Application using Machine Learning

by IJRASET Publication

2022, International Journal for Research in Applied Science & Engineering Technology (IJRASET)

Human pose estimation localizes body key points to accurately recognizing the postures of individuals given an image. This step is a crucial prerequisite to multiple tasks of computer vision which include human action recognition, human... more

Figure 2: Human Pose Estimation (HPE) For the pose estimation component, we utilize a pre-trained real-time system, called Blaze Pose, that can detect human body key points in videos. (More detail on BlazePose and our reasoning for choosing this system can be found in Technical Approach.) This model is functional out of the box, and thus is very simple to install for users of our application. Using BlazePose allows us to take advantage of the state of the art in pose estimation algorithms for our task, and lets us focus on the actual evaluation of exercise posture. For the posture evaluation (pose training) component, we have recorded videos of ourselves performing exercises. Our videos include our best effort to correctly perform the exercise, as well as intentionally incorrect examples. The evaluation of our posture identifier is dependent on the performance of the pose estimator. We work under the assumption that the pose estimator is accurate a majority of the time, with small measurement deviances due to noise, which we correct for. We evaluate our posture identifier in different ways depending on the algorithm: for heuristic. algorithms, we feed in all videos for evaluation, while for machine learning algorithms, we evaluate by splitting our video dataset into train and test sets, and report results on the test set. To design the basic Curl counter we have to select three points from the basic 33 key-points that are responsible for the movement eee. go ee ous

Figure 3: Key-points used in curl counter Here we select 3 points, shoulder joint X1 Y1, Elbow joint X2 Y2, Wrist joint X3 Y3

Thus we added a new constant, “a - arctangent’ to remove this instability. We also got this function working from -pi/2 - +pi/2 In ‘a tan2’ we get a much bigger range of written values, so that it can work for a versatility process. Therefore we chose this function. This function returns the value in range 0 - 2pi.

We used Tlinker for building an interactive UI/UX for the application.

descriptionView Paper arrow_downwardDownload

Implementation of Magic Mirror Using Raspberry Pi 3

by Ashay Mandwarya

2022

This paper describes the designing and implementation of an voice controlled wall mirror, called “Magic Mirror”. It is a device that can function both as a mirror and an interactive display displaying multimedia content such as time,... more

descriptionView Paper arrow_downwardDownload

A smart mirror to promote a healthy lifestyle

by Ovidio Salvetti

2022, Biosystems Engineering

descriptionView Paper arrow_downwardDownload

Personalized Guidance for People Empowerment and Self-efficacy towards Healthy Lifestyles - The Solution Proposed in SEMEOTICONS

by Massimo Martinelli

2022, Proceedings of the International Conference on Health Informatics

This paper discusses the problem of fostering lifestyle changes towards healthier habits by means of coaching and supportive messages in the frame of a tailored users' guidance. Starting from the importance of behavioural changes to... more

descriptionView Paper arrow_downwardDownload

IoT Based Elderly Healthcare Monitoring System

by IJRASET Publication

2022, VI

Now a days continuous patient health monitoring is becoming a key concern for the doctors since it can help them save patient's life. So, the main objective is to design a patient monitoring system which can monitor various physiological... more

descriptionView Paper arrow_downwardDownload

Internet of Things (IOT) Based Mini -Weather Station using Arduino

by IJRASET Publication

2022, International Journal for Research in Applied Science & Engineering Technology (IJRASET)

IOT or Internet of Things is one the most developing and flourishing fields upcoming in the future. It now plays an important role in daily weather detection too. IOT is defined as the collection of devices that interacts with the user as... more

[OT or Internet Of Things in our day to day life plays an important role and life without it can’t be imagined even. Wireles networking adds more flexibility to the system as it is now worldwide availa ble through network technology. Weather condition impact our lives through various factors so it is very important for us to gather information related to it accurately and effectively Relying on the weather reports available on the internet nowadays is not a good idea, because it shows the weather of a vast area an fails to provide warnings and alarms ahead of time. With the help of IOT we can solve this problem which can be life saving for : nuge number of people around the globe. Instant weather analysis and sharing the parameters collected by the device around th network will be useful to every individual living in the area. IOT ensures the d Par the 1ce of evervone evice to be cost efficient, trustworthy, and affordabl The block diagram shows the system that is designed for the IOT based weather monitoring system. Sensors used in this system help to collect the related data to monitor the weather on a daily basis. Using the Wifi module and the Microcontroller to predict the weather and sending the corresponding output on the internet. And storing them on a server using the Blynk mobile application to get the weather related information and updates in understandable format which can be viewed on any browser over the internet.

7) Dust Sensor: It indicates the air quality around the environment by measuring the dust concentration

descriptionView Paper arrow_downwardDownload

BLPnet: A New DNN model for Automatic License Plate Detection with Bengali OCR

by Tareque Ovi and

2022

Deep Neural Network (DNN) models with image processing and object localization have the potential to advance the automatic traffic control and monitoring system. Despite some notable progress in developing robust license plate detection... more

descriptionView Paper arrow_downwardDownload

Smart Mirror Using Raspberry PI

by IJRASET Publication

2022, International Journal for Research in Applied Science & Engineering Technology (IJRASET)

People's lives are clearly being transformed by the impact of emerging technologies. Everything around us has become smart in the last few years. Smart phones, smart cars, and smart watches have become ubiquitous in today's culture. A... more

Figure 1:components of smart mirror display Histaled dClOss Ils LeirtOly, With its rapid growth, the internet of things has transformed people's environments by transforming their homes into smart homes. A smart house is one that is connected to smart devices and communicates with them over the internet. Our style of life has progressed to the point where the most important thing is to save time. Because of the rapid advancement of technology, the use of smart gadgets is growing every day. Every day, we examine ourselves in the mirror to assess our appearance and outfit. We are psychologically connecting with the mirror in this way. So, everyone can be excited by the prospect of a mirror that can answer to any of your commands. The normal mirror is transformed into an arrogant mirror, which is then employed as an information system to collect data. On a single user interface, several tasks can be completed. In a matter of seconds, the smart mirror device may check regular activities, critical meetings, and worksheets on a pc, tab, cell phone, or other device. The smart mirror is an internet of things (iot)-based intelligent technology that can be used to facilitate and improve the user's awareness of numerous functions. With the help of interactive computing systems and embedded systems, the level of living and quality is changing dramatically by using this smart mirror. A smart mirror can be utilized as a commonplace item to alter a person's perception of themselves in the mirror

The architecture is modular, and it is built on function-specific modules that can be combined on a single platform. Many functions, such as the clock, calendar, current weather, and news feed, and many more third-party functionalities, can be grouped in this way. The server module is in charge of all processes, including user contact via sensors and the mirror user interface (UI), information visualization via the mirror UI, and so on.

Figure 3: Default smart mirror display layout Since we're creating a voice assistant app, one of the most critical features is that your assistant knows your voice (and hence understands what you want to say/ask). As a third-party module, we use Google Assistant.

descriptionView Paper arrow_downwardDownload

Jarvis a PC Voice Assistant

by jash vora

2022

The project aims to develop a private assistant for Computer. PC Personal Assistant draws its inspiration from virtual assistants like Google Assistant for Android, Siri for iOS. It provides a user-friendly interface for completing a... more

descriptionView Paper arrow_downwardDownload

Health Mirror

by IJRASET Publication

2022, International Journal for Research in Applied Science & Engineering Technology (IJRASET)

descriptionView Paper arrow_downwardDownload