Raspberry Pi Camera Research Articles

Vision to the Bi-Sionary

Abstract: Visual impairment is one of the biggest limitations for humanity, especially in this day and age when information is communicated a lot by text messages (electronic and paper based) rather than voice. Facial recognition is category of biometric software that maps an individual’s facial features mathematically and stores the data as a sprint The software uses deep learning algorithms to compare a live capture or digital image to be stored face print in order to verify an individual’s identity vbnnn This project aims to develop a device to help people with visual impairment. In this project, we manufactured a device that converts an image’s text to speech. The basic outline is an embedded system that captures an image, extracts only the area of interest (i.e. region of the image that comprises text) and changes that text to speech. It is incorporated using a Raspberry Pi 3 and a Raspberry Pi camera module. We have two phases in our project that are Text to Speech and Facial Recognition. Every Module for picture handling and voice preparing are available in the device. It likewise can play and stop the output while reading. The expectation is that it has less error rate and less processing time and less cost productivity.

Development of a Noninvasive Blood Glucose Monitoring System Prototype: Pilot Study.

BackgroundDiabetes mellitus is a severe disease characterized by high blood glucose levels resulting from dysregulation of the hormone insulin. Diabetes is managed through physical activity and dietary modification and requires careful monitoring of blood glucose concentration. Blood glucose concentration is typically monitored throughout the day by analyzing a sample of blood drawn from a finger prick using a commercially available glucometer. However, this process is invasive and painful, and leads to a risk of infection. Therefore, there is an urgent need for noninvasive, inexpensive, novel platforms for continuous blood sugar monitoring.ObjectiveOur study aimed to describe a pilot test to test the accuracy of a noninvasive glucose monitoring prototype that uses laser technology based on near-infrared spectroscopy.MethodsOur system is based on Raspberry Pi, a portable camera (Raspberry Pi camera), and a visible light laser. The Raspberry Pi camera captures a set of images when a visible light laser passes through skin tissue. The glucose concentration is estimated by an artificial neural network model using the absorption and scattering of light in the skin tissue. This prototype was developed using TensorFlow, Keras, and Python code. A pilot study was run with 8 volunteers that used the prototype on their fingers and ears. Blood glucose values obtained by the prototype were compared with commercially available glucometers to estimate accuracy.ResultsWhen using images from the finger, the accuracy of the prototype is 79%. Taken from the ear, the accuracy is attenuated to 62%. Though the current data set is limited, these results are encouraging. However, three main limitations need to be addressed in future studies of the prototype: (1) increase the size of the database to improve the robustness of the artificial neural network model; (2) analyze the impact of external factors such as skin color, skin thickness, and ambient temperature in the current prototype; and (3) improve the prototype enclosure to make it suitable for easy finger and ear placement.ConclusionsOur pilot study demonstrates that blood glucose concentration can be estimated using a small hardware prototype that uses infrared images of human tissue. Although more studies need to be conducted to overcome limitations, this pilot study shows that an affordable device can be used to avoid the use of blood and multiple finger pricks for blood glucose monitoring in the diabetic population.

Test and Development of a Low-Cost Solution for Automatic Inspection of PET Bottle Codification

Quality of packaging is a key factor in consumer choice for a particular product. Besides the package appearance, legal requirements demand that certain information is presented to the consumer. The main goal of this work is to evaluate the technical feasibility of using a Raspberry Pi board as a platform for automatic quality inspection for the expiration date and batch information in polyethylene terephthalate (PET) bottles. The system consists in capturing digital images using a Raspberry Pi Camera, processing the image obtained and performing optical character recognition in order to determine if the coding is compliant. Two models of bottles were used, and 24 images of each were captured, 15 of which were examples of compliant bottles and 9 were defective. The tests were divided into two sequences of processing methods. The best sequence achieved 100% specificity, 91.7% accuracy for model A bottle and 83.3% for model B.

Touchless Hand Sanitizer Mobile Robot Application: Survey and Dataset Preparation for Deep Learning Recognition

The COVID-19 pandemic spreads throughout the world, many sanitizer dispenser devices included robots designed to minimize human contact and as less as possible to minimize the speared of this pandemic or any germs among humans. In many positions, these sanitizers dispensers are important to sterilize and help people from infection such as patients and medical staff in hospitals, teachers, and students in schools or universities, etc. In this paper, many studies of sanitizer dispenser devices including mobile robot applications for touchless hand sanitizers especially in the coronavirus pandemic have been explained. The major aim of this survey is to compare and contrast many previous survey methodologies. This study covered the introduction to robot applications, hand sanitizers dispenser device including a mobile robot, and object detection-based deep learning techniques that recognizes people. Object detection with the deep learning method is discussed because it is the most important feature of the hand sanitizer device, which is based on a mobile robot application. Furthermore, in this work, the proposed block diagram of dataset processing has been instigated using the mini-computer Raspberry Pi version 4, Raspberry Pi camera system, and LabelImg graphical tool. These dataset outputs files of each image (label.xml and image.jpg) are prepared and classed into 7 classes to use as inputs to the next future work of deep learning. In future work, we want to create a mobile robot hand sanitizer that recognizes the people using a deep learning approach. The python programing language has been used. The contribution of this work is to create, annotate and prepare the dataset for Deep Learning while the previous related works depended on existing dataset that taken from website .

Design and Development of Wearable Eye for the Visually Impaired

The wearable eye for the blind or visually impaired persons is a technological advancement, which is aided by multidisciplinary courses like software engineering and hardware design. It aids the visually impaired to explore their surroundings as quickly as possible and assuresthem safety by sensing nearby deterrents with the use of ultrasonic waves and alerting them with a beeping sound and audio support. It also incorporates face recognition for identifying known people through a voice message when they appear before the visually impaired person. For a long time, the white stick, despite its power, still possesses a significantamount of weakness. This limitation is overcome by the design and development ofthis wearable innovation. The wearable eye deviceuses a little computer, the Raspberry Pi 4 module, ultrasonic sensors and a Raspberry Pi camera.

Detection Malaria Base Microscope Digital Image with Convolutional Neural Network

Malaria is a tropical disease that infects human red blood cells caused by infection with the plasmodium parasite. Plasmodium parasites spread to humans through female Anopheles mosquitoes and can reproduce in human blood cells. Malaria is a health problem that is at risk of causing other health problems such as anemia and even death. The current gold standard for malaria diagnosis is laboratory diagnosis by microscopic examination to find the malaria parasite through the blood cells of the patient. However, the diagnosis of malaria through microscopic observation of blood cells has the potential to take a long time, because the plasmodium parasite has a very small size. The malaria detection system using the Convolutional Neural Network (CNN) method is designed to detect malaria in human blood cells. CNN is a machine learning method designed to classify objects in an image. The system was built in three stages of development, namely the development of a CNN model for malaria detection, software development and hardware development. The hardware components used in the system include Raspberry pi, Raspberry Pi camera module, and LCD. The results of the malaria detection test using the CNN model gave an accuracy of 98.76% which was tested on blood cell images from a microscope

The Application of Adaptive Tolerance and Serialized Facial Feature Extraction to Automatic Attendance Systems

The aim of this study was to develop a real-time automatic attendance system (AAS) based on Internet of Things (IoT) technology and facial recognition. A Raspberry Pi camera built into a Raspberry Pi 3B is used to transfer facial images to a cloud server. Face detection and recognition libraries are implemented on this cloud server, which thus can handle all the processes involved with the automatic recording of student attendance. In addition, this study proposes the application of data serialization processing and adaptive tolerance vis-à-vis Euclidean distance. The facial features encountered are processed using data serialization before they are saved in the SQLite database; such serialized data can easily be written and then read back from the database. When examining the differences between the facial features already stored in the SQLite databases and any new facial features, the proposed adaptive tolerance system can improve the performance of the facial recognition method applying Euclidean distance. The results of this study show that the proposed AAS can recognize multiple faces and so record attendance automatically. The AAS proposed in this study can assist in the detection of students who attempt to skip classes without the knowledge of their teachers. The problem of students being unintentionally marked present, though absent, and the problem of proxies is also resolved.

A comparison of ImageJ and machine learning based image analysis methods to measure cassava bacterial blight disease severity

BackgroundMethods to accurately quantify disease severity are fundamental to plant pathogen interaction studies. Commonly used methods include visual scoring of disease symptoms, tracking pathogen growth in planta over time, and various assays that detect plant defense responses. Several image-based methods for phenotyping of plant disease symptoms have also been developed. Each of these methods has different advantages and limitations which should be carefully considered when choosing an approach and interpreting the results.ResultsIn this paper, we developed two image analysis methods and tested their ability to quantify different aspects of disease lesions in the cassava-Xanthomonas pathosystem. The first method uses ImageJ, an open-source platform widely used in the biological sciences. The second method is a few-shot support vector machine learning tool that uses a classifier file trained with five representative infected leaf images for lesion recognition. Cassava leaves were syringe infiltrated with wildtype Xanthomonas, a Xanthomonas mutant with decreased virulence, and mock treatments. Digital images of infected leaves were captured overtime using a Raspberry Pi camera. The image analysis methods were analyzed and compared for the ability to segment the lesion from the background and accurately capture and measure differences between the treatment types.ConclusionsBoth image analysis methods presented in this paper allow for accurate segmentation of disease lesions from the non-infected plant. Specifically, at 4-, 6-, and 9-days post inoculation (DPI), both methods provided quantitative differences in disease symptoms between different treatment types. Thus, either method could be applied to extract information about disease severity. Strengths and weaknesses of each approach are discussed.

Deteksi Pelanggaran Social Distancing Menggunakan Raspberry Pi Kamera Berbasis IOT

Social distancing is one of the methods used to keep yourself and others safe during a pandemic and prevent the transmission of Covid-19. With social distancing, the spread of Covid-19 can be minimized. By utilizing two tools, namely the Raspberry Pi to classify using the haar cascade classifier algorithm from data obtained from the pi camera module as a visual raspberry pi used to detect a person's body. Raspberry pi camera will start detecting using crontab unit time. If the Raspberry Pi camera detects a person who is less than one meter away, that person is said to have violated social restrictions and vice versa, the data will be stored on the Raspberry Pi which also becomes a web server. The website is used as a system user interface, Raspberry Pi camera communication uses the machine to machine (M2M) protocol which is applied to a website-based application.

Covid 19 Spread Prevention Based on IoT around ATM machines

COVID-19 has been discovered since 2019. It began in China and expanded over the world; its influence on countries was so severe that it affected the economics, politics, and others, as well as the lives of individuals in all facets of life. This illness is spreading so quickly that seven people out of every ten have it. To decrease losses in all aspects for the entire world, a device was designed to be inserted in ATMs via the Internet of Things, with the recommended approach detecting and preventing COVID-19 spread around ATMs. Picture processing algorithms are used to capture the person's image at the ATM, whether he is wearing a mask or not. If the individual is not wearing a mask, the system will enter a state of freeze and they will be unable to access it. It makes use of the Raspberry Pi and the Raspberry Pi Camera Module. Biometric sensors can scan the thickness of a person's finger, which is typically 4-6 mils thick. When inputting the pin code or using the ATM, the individual should wear gloves, keeping a social distance of about 2 meters (6 feet) with ATMs that use an ultrasonic sensor.

Secure Attendance System using Raspberry Pi Face Recognition

This study aims to develop a machine-learning-based attendance management system using face recognition and Raspberry Pi. The proposed system is composed of two main subsystems. The first is a Raspberry Pi, to be installed in each class, and the second is a web application fed by data from the Raspberry Pi. To take attendance, an instructor commands a Raspberry Pi camera through a web-based subsystem. Then, the camera takes a picture of the whole class and detects faces using trained Haar Cascades. It sends back a file with the class picture and Cartesian coordinates of the detected faces. The web application parses the file, looking for the coordinates of faces. For each Region of Interest, it uses the Support Vector Machine algorithm to recognize faces based on their HOG (Histogram of Oriented Gradients) features. The recognizer uses a pre-built dataset of that particular class containing the students’ personal photos, names and ID numbers. Features of each face were extracted using HOG and trained to construct the model over a given class of students. Once every detected face is recognized, the application generates a report for the instructor showing the list of students’ names and attendance status.

Quantifying the effects of anesthesia on intracellular oxygen via low-cost portable microscopy using dual-emissive nanoparticles.

Intracellular oxygenation is an important parameter for numerous biological studies. While there are a variety of methods available for acquiring in vivo measurements of oxygenation in animal models, most are dependent on indirect oxygen measurements, restraints, or anesthetization. A portable microscope system using a Raspberry Pi computer and Pi Camera was developed for attaching to murine dorsal window chambers. Dual-emissive boron nanoparticles were used as an oxygen-sensing probe while mice were imaged in awake and anesthetized states. The portable microscope system avoids altered in vivo measurements due to anesthesia or restraints while enabling increased continual acquisition durations.

Developing a fluorescent sensing based portable medical open-platform - a case study for albuminuria measurement in chronic kidney disease screening and monitoring

In this work, a portable medical platform is developed to monitor fluorescence assay for in-field and point of care (POC) analysis of albumin levels in urine. The platform can rapidly and efficiently measure the fluorescence intensity yielded from the mixture of recognising reagent and the biomarker. After mixing with the recognising reagent and placing under a certain optical excitation wavelength, the sample containing the target biomarker emits a fluorescent signal, which is captured by a Raspberry Pi Camera and analysed in real time to evaluate the Red Green Blue (RGB) values of the image and give an estimation of the biomarker concentration in the sample. Each biomarker, in testing for fluorescence, requires different excitation wavelengths and sensitivities for detection. The developed platform has been designed with flexibility for customization to suit the different requirements of various fluorescence reactions. In this study, we perform two stages of evaluating the device. In stage 1, we demonstrate the developed platform can detect known concentrations of albumin in artificial urine samples by using different recognising reagents. In stage 2, we confirm the developed platform can detect unknown concentrations of albumin in patients' urine samples and provide comparative accuracy results compared with current laboratory testing results. This study provides proof of concept that the developed device can measure the concentration of different biomarkers if the biomarker detection follows the rules of fluorescence sensing.

Human Image Classification and Identification

Abstract: Face Recognition is in recent times used as a chunk of various applications. It is used as a piece of the makes use of images processing applications. The Raspberry Pi 4 is embedded system. It is low cost, a single-board computer used to lessen the complexity of systems in actual time applications. This project is especially based on python. Raspberry pi carries Camera slot Interface (CSI) to interface the raspberry pi camera. Here, Images captured by using the Raspberry Pi camera module are improved so that it will identify the specific region of image. This is used in the real time application of ‘Smart Attendance System’. We have proposed to implement a “Smart attendance system using Face Recognition”. This system makes use of Face recognition package which saves a number of time than conventional method. This system requires Raspberry Pi 4, Open CV, Python etc. The system uses Face Recognition Package. This system compares the image of the test and the training image and decide who is present and absent. If student is absent a message will be sent to their parent’s phone number. Student will be greeted with the voice when he/she come in front of camera by using text to speech mechanism. The system wishes “Happy Birthday” if student’s birthday is there by checking the birth date and current date. Keywords: Open CV, Face Recognition, Raspberry Pi, Face recognition package.

Multi-Functional Agribot

Abstract: This project aims to design an agricultural robot to perform operations such as plowing, seeding, leveling, pesticide spraying, and plant health monitoring. The proposed Agribot is built by using the Raspberry Pi microcontroller. The microcontroller, the heart of the robotic system can manipulate the whole actions of the system. A motor driving circuit is used to drive the DC motors which in turn control the wheel motion. The Raspberry pi is given with a high-tech web camera for capturing the image, since the resolution of the given Raspberry pi camera is not sufficient to get the clarity image, Wi-Fi is used for the manual control of the robot. The Agribot is powered using a 12V battery. This 12V is used for the functioning of all other components like Relay, Motors, and Motor Drivers. Keywords: Robotic system, Raspberry Pi, Wi-Fi, Web Camera, Plant health monitoring.

Alert System for Driver’s Drowsiness

Monotonous driving for longer distances results in drowsiness and mental fatigue. Consumption of alcohol can also make the driver feel sleepy. Thus, drowsiness and drunken driving cause road accidents. This paper proposes a real-time detection of drivers’ drowsiness and subsequently alerting them. The main aim of this proposed system is to reduce the number of accidents due to driver’s Drowsiness and alcohol intake to increase transportation safety. The proposed system contains the use of the Raspberry Pi system and Pi camera module for drowsiness detection of the driver and alerting the driver using an alarm system.

Background segmentation in difficult weather conditions.

Background segmentation is a process in which an algorithm removes the static background from an image. This allows only a changing section of the image. This process is important for motion detection or object tracking. In this article, an approach is proposed to compare several existing algorithms for background segmentation under severe weather conditions. Three weather conditions were tested: falling snow, rain and a sunny windy day. The test algorithms were executed on a test video containing frames collected by a dedicated Raspberry Pi camera. The frames used in the tests included cars, bicycles, motorcycles, people, and trees. Preliminary results from these tests show interesting differences in detail detection and detection noise.

Development of Computer Vision Algorithms for Multi-class Waste Segregation and Their Analysis

Classification of waste for recycling has been a focal point for scientists interested in the field of conservation of the environment. Recycling consists of numerous steps, of which one of the most crucial is the segregation of recyclables from all other waste. Due to a lack of safety standards in developing countries, waste collection is often done manually by domestic helpers, or "rag-pickers". Such a process risks individual and public health. The waste collection methods may ultimately cause waste to become non-recyclable due to cross-contamination. Literature shows that research in this direction focuses on a single class of waste detection. The proposed work investigates CNN, YOLO, and faster RCNN-based multi-class classification methods to detect different types of waste at the collecting point. The smart dustbin proposed employs these computer vision methods with a Raspberry Pi microcontroller and camera module. The experimental results for multi-class classification show that the CNN has 80% of accuracy with 60% of the loss. Whereas the YOLO algorithm shows an accuracy of 88% and a loss of 40%. But the best results were obtained from faster RCNN object detection with API, with an accuracy of 91% and a loss of 16%. There is already an existing method for making a smart dustbin, so the results are compared to show how computer vision can be used to make a smart dustbin. This shows how computer vision can be used to make a smart dustbin. Doi: 10.28991/ESJ-2022-06-03-015 Full Text: PDF

Human-Wildlife Conflict Early Warning System Using the Internet of Things and Short Message Service

Human-wildlife conflict (HWC) is an important challenge to communities living in areas bordering wildlife game parks and reserves. It is more evident in the United Republic of Tanzania, whose economy depends on wildlife tourism. This paper proposes a low-cost and low-power early warning system using the Internet of Things (IoT) and Short Message Service (SMS) to support HWC respond teams in mitigating these challenges. The system comprises three primary units: sensing, processing, and alerting. The sensing unit consists of a Passive Infrared (PIR) sensor, a Global Positioning System (GPS), and a Raspberry Pi camera. The PIR sensor detects the proximity of the animal using the heat signature, GPS senses and records the current location, while the Raspberry Pi camera has the primary purpose of taking a picture after the PIR sensor detects the proximity of the animal. The processing unit with a Raspberry microcomputer performs data processing and image inferencing using the You Only Look Once (YOLO) algorithm. Last is the alerting unit, which includes a Global System for Mobile (GSM) communications module for sending SMS messages to the human-wildlife conflict response team and the nearer community response team leader whenever wild animals are spotted near the park’s border. The system detects, identifies, and reports the detected wild animals. The GPRS provides internet connectivity to support data collection, storage, and monitoring in the cloud.

Alat Pengukur Ketinggian Air Pada Landasan Pacu Pesawat Dengan Metode Image Processing

An aircraft accident are caused by several factors, one of which is the weather. High rainfall causes the runway to become slippery and wet. This will cause hydroplaning events on the plane. Hyproplaning is a skidding event caused by puddles of water on the runway. The maximum height of puddles on the runway is 3 mm. Currently, to measure the water level is still done in a conventional way and there is no sensor capable of measuring the water level in mm. To prevent accidents due to hydroplaning, a measuring device is needed that can monitor the water level in millimeters and has a long size range and is calibrated on the runway. This water level meter is made using a raspberry Pi 3 B+ miniPC. The stages in making this tool include hardware design and software design. Measurements were carried out using the image processing method with a Raspberry Pi camera and an optical liquid water sensor. The results of the measurements are displayed on the monitor screen with the VNC Viewer software. The measurement results using an optical liquid water level sensor are accurate with a relative error of 0% in each measurement, namely at 1 mm, 2 mm and 3 mm. For measurements using the image processing method, the average error generated is 2.3% at a height of 1 mm, 6.9% at a height of 2 mm, 3.3% at a height of 3 mm, 0.9% at a height of 4 mm and 0 .24% at 5 mm height.