Webcam Camera Research Articles

One-Phase Smart Switch using OpenCV Hand Gesture Recognition

The need for simplicity in various activities encourages further technological development. One of them is a system to turn lights on and off with just a hand gesture. This hand gesture-based One-phase smart switch uses OpenCV, Arduino Nano, relays, and webcam cameras to recognize hand gestures. Static finger movements are used as buttons to turn on the lights. The results show that the algorithm used has high reliability with a precision score of 0.90, sensitivity of 0.90, accuracy of 0.96, and F1-score of 0.90. The accuracy of the system is affected by light intensity, distance, and hand tilt angle. At a light intensity of 70 LUX, the accuracy reaches 100%, while at 40 LUX the accuracy ranges from 98-99%. A distance of 30-60 cm gave the best accuracy of 100%, but decreased at longer distances. A hand tilt of 0° gives 100% accuracy, while at an angle of 60° the accuracy drops significantly, especially for the fifth finger with 64% accuracy. The average response time of the light to finger movement is 0.133 seconds. This device can recognize a variety of finger patterns well, thus meeting the desired needs.

A robust non-contact heart rate estimation from facial video based on a non-parametric signal extraction model

Remote photoplethysmography (rPPG) is a non-contact method to extract heart rate (HR) pulse signals from facial videos. However, challenges persist due to head motion disturbances and ambient illumination variations. To address these issues, a novel non-parametric signal extraction model is proposed for HR estimation using the webcam camera. We first select the better-quality RGB signal from the divided face regions through the ranking of signal-to-noise ratio (SNR). Then, we use blind source separation and skin reflection modeling to eliminate the effect of ambient illumination. Finally, we employ a non-parametric signal extraction model named circulant singular spectrum analysis (CiSSA), with frequency-based decomposition and energy-driven reconstruction, to extract the HR-related pulse signal effectively. To evaluate the performance of our method, we conducted the validation experiments on three datasets, including two public datasets (UBFC and PURE dataset) and one self-collected dataset (ILVA dataset). Our method outperformed significantly on all three datasets, achieving Mean Absolute Deviation (MAD) of 2.42, 1.36, and 2.84 bpm, Root Mean Square Error (RMSE) of 1.89, 2.24, and 3.58 bpm, and Pearson Correlation Coefficients (PCC) of 0.98, 0.98, and 0.93, respectively. The experimental results demonstrate that our method achieves comparable performance, particularly in scenarios involving severe head motion disturbances and variations in ambient illumination.

Low-Cost CCTV for Home Security With Face Detection Base on IoT

Monitoring is a necessary part of Home surveillance that can be done through the internet network as a security measure. Many CCTV cameras on the market today continue to employ analog and conventional technology, specifically coaxial wire. As a result, extra expenditures for CCTV system wiring are required; besides being more expensive, the installation takes more handling, as the picture data cable and control signal cable cannot be merged. This project aims to develop a security system capable of detecting object movement in real-time utilizing a webcam camera attached to a raspberry pi. The findings of this study enable the development of a low-cost CCTV system that can be monitored remotely via the Internet of Things.

An automatic waste cleaning system in shrimp ponds with digital image processing using the internet of things

Super intensive shrimp pond wastewater with a stocking density of 750-1,250 individuals/m2 contains an average total suspended solids (TSS) of 798-924 mg/L, dissolved organic matter (BOT) of 81,227-88,641 mg/L; total nitrogen (TN) 9.8389-14.4260 mg/L; and total phosphate (TP) 7.8770-11.8720 mg/L. This value has exceeded the threshold limit of the permissible pond wastewater standard so it has the potential to hurt the environmental quality of water bodies receiving the waste load. making a more intensive vannamei shrimp farming pond cleaning system using turbidity sensors to read turbidity in shrimp farming ponds and ultrasonic sensors as readers of the water level in shrimp farming ponds and using a camera to detect the presence of foam waste in shrimp farming ponds and the Raspberry Pi microcontroller as a center system control on control devices and monitoring of all sensors then the output data will activate the drainage of leftover shrimp feed and shrimp waste from drainage to disposal using PVC pipes and automatic faucets that are driven using DC power window motors. The Internet of Things (IoT) automatic system in the construction of a waste cleaning device for shrimp ponds was built using a turbidity sensor that can detect the level of turbidity in water with an accuracy of 0.51%. The need for additional water in the pond is assisted by an ultrasonic sensor which provides information to the water pump with an average accuracy of 0.56%. To detect foam waste using a webcam camera as a foam detector.

Low-Cost Webcam Camera and GNSS Integration for Updating Home Data using AI Principles

PDAM Surya Sembada Surabaya City responds to Surabaya's water service demand by pioneering a cost-effective mobile mapping tech. This innovation integrates 3 MP webcams, GNSS, and IMU sensors to update customer building data efficiently. Precise photo data with location and movement info within 1-meter proximity captures accurate building coordinates. Applying georeferencing and Cosine Similarity reduces redundant data by 50%. GNSS, IMU sensors, and VGG-16 model aid data collection and analysis. This comprehensive approach optimizes PDAM Surabaya's operations, ensuring timely and accurate customer updates amid Surabaya's population growth, promising enhanced service delivery while managing costs.

SISTEM MONITORING KEAMANAN LINGKUNGAN PERUMAHAN MENGGUNAKAN RASPBERRY PI DAN MOTION EYE OS

Problems that often arise in residential areas are theft or housebreaking. the case above can be solved by using a surveillance camera, but rarely does anyone use it and the drawback of the existing surveillance cameras is that they cannot make direct notifications. In this study, the above problems can be solved by designing a security monitoring tool for the environment around housing based on webcam cameras and Raspberry Pi by utilizing Motioneye OS as a remote monitoring application, recording and capturing images and video results from motion detect and also notifications from pushover app. This study uses the SDLC method, namely the prototype model, in which this method is able to address real needs. The results in testing this study were that MotionEye OS captures and detects movement well and sends the detection results to pushovers in almost all conditions. for an alternative tool to replace the old system, this is quite good where this new system can monitor remotely and use any device and can receive state updates with notifications. With this security monitoring system tool, it is hoped that it can reduce criminal acts in residential areas.

Utilization of Webcam Cameras as X-Ray Image Capture (kV Settings and Shutter Sensors)

The result of x-ray imagery is generally in the form of film sheets. To obtain an image, the film must pass through the process of processing with chemicals. Departing from these problems, efforts were made to develop digital x-ray detectors using much cheaper devices. By using voltage variations and also sensors that aim to find out the difference in the quality of the resulting image. The contribution of this study is that the system can display negative image results from webcam camera captures that have previously passed the image processing process with the Matrix Laboratory (MATLAB) Application. The measurement ranges used are 60, 65, and 70 kV. with a set mA of 25mA, a duration of irradiation of 1 second, and a moderate intensity of illumination light. From the measurement results, it shows that the X-ray Image Capture Tool can be compared with the image results from the Philip brand DR with the MSE value obtained, which is 34.8775 with parameters Phototransistor BPT1331, 70kV, and 25mA. And the lowest MSE value is 61.7615 with parameters LDR, 66kV, 25mA. The results of this study indicate that the tool can be used to capture X-rays.

Implementation And Design of Security System On Motorcycle Vehicles Using Raspberry Pi3-Based GPS Tracker And Facedetection

One of the nations where land transportation is frequently employed is Indonesia, particularly on motorbikes or two-wheeled vehicles. Since there is not much economic growth to maintain the high level of sales, there are many people without jobs, which leads to criminality, particularly motorcycle theft. The rate of motorbike theft in society is currently rising. The researchers developed a security system using a GPS Tracker whose control was handled by a two-channel relay in response to the rise in motorbike theft. The webcam camera produces the greatest images when it is hidden by a tree. 100% of the time, Relay Components work to control the horn and electricity. Due to the short read-time of the location the first time, GPS has a high accuracy. The Raspberry Pi3 can send, receive, and process commands to the motorcycle security system. The motion sensors, vibration sensors, raspberry pi microcontrollers, relays, and servo motors make up the system architecture in general. This method operates when the motor produces a lot of vibration. The sensor will relay the vibration to the Raspberry Pi microcontroller's output and the microcontroller will then deliver a warning notification message. In the event of a theft, the motorcycle will be immediately within the owner's control. In addition, with security using facedetection, the public can detect the perpetrators of theft and it takes quite a long time to work on it. The security system on motorbikes using facedetection takes a long time to produce, but it can't be done optimally. The purpose of this creation is to improve the security system on motorcycles to make it more efficient and effective in identifying the perpetrators of theft. This system consists of a Raspberry Pi3 as the control center, a picamera as a face detector, and a buzzer as an alarm.

Sistem Identifikasi Kesegaran dan Jenis Ikan dengan Metode K-Nearest Neighbor Berdasarkan Citra Mata dan Bentuk Ikan

Fish is a food commodity that needs attention, to improve the quality of food production, especially the fish itself. The level of freshness of fish greatly affects the quality of food production both at the household and industrial levels, as well as determining the feasibility of the fish for processing and consumption. Currently, to determine the level of quality of fish freshness, it is still done conventionally by humans, while those who have used tools but still have deficiencies in both the level of accuracy and also the features they have are still small. In this study, a tool or system design was carried out that could identify the freshness level of a fish based on eye images taken using a webcam camera or the like as input from data to be processed using image processing. In addition, the system is given additional features to be able to identify the type of fish. So that this additional feature can help facilitate identification all at once. To classify the method used is the K-Nearest Neighbor method. The results of the data processing will be displayed in the form of a sorting system for output. In the research results obtained from the system this time from 280 datasets for identification of freshness were tested on 50 images with a success rate of 96% for fresh and 84% for rotten. While the results of identification of fish species from 50 images of test data from three types of fish obtained a success rate of 97.7% with a value of k = 5.

Designing a Facial Expression Detection System to Determine the Level of Customer Satisfaction with K-Nearest Neighbor Method

Facial expressions are one of the ways humans communicate to convey one's emotions to their communication partner nonverbally. Therefore, human facial expressions can be used for various purposes, one of which is knowing customer satisfaction. So far, customers of Bank Rakyat Indonesia (BRI) provide feedback on service quality using only a polling system, namely by filling out a criticism and suggestion form and then entering it in a suggestion box which is distinguished between satisfied and dissatisfied. However, such a method is less effective because it can be easily manipulated by customers and customers are often indifferent to the feedback. So that the improvement of service quality tends to be less effective. This research will design a system that can recognize human facial expressions to determine the level of customer satisfaction with input data in the form of video data taken by a webcam camera with the viola-jones method to detect faces and determine facial patterns. Then the facial data will be classified using the K-Nearest Neighbor method to determine the type of facial expression. Determination of the value of k will determine the success rate of facial expression detection. The processed data will be displayed on a liquid crystal display (LCD) and then stored in a MySQL database. The results showed that the accuracy of facial expression detection was 80.77% from 52 facial expression data.

Machine vision system for real-time debris detection on mechanical wild blueberry harvesters

Improving fruit quality is important to wild blueberry producers. Plant debris like leaves and stems caused a reduction in fruit quality during mechanical harvesting. A debris detection system was developed using two Logitech C920 webcam cameras mounted before and after the blower fan on a commercial mechanical wild blueberry harvester. Images were collected from two commercially managed wild blueberry fields located in central Nova Scotia to develop a dataset of 1000 images. Two convolutional neural networks (CNNs), YOLOv3 and YOLOv3-SPP, were used and compared for performance analysis. The CNNs were trained using no augmented images, images with five augmentations (sharpening, brightness, contrast, gamma correction, and saturation), and images with five augmentations that were more heavily weighted towards gamma. Four different computer hardware packages (Hewlett-Packard, Shuttle XPC, Jetson TX2, and GPU-based Desktop) were used to determine the appropriate hardware and CNN model combination for real-time performance. YOLOv3 and YOLOv3-SPP were trained to mAP scores of 72.87 and 74.38% using the dataset with more gamma-augmented images. This was an improvement over the dataset with no augmentation (67.75; 68.49%) and equally numbered augmentations (71.26%; 73.03%). YOLOv3-SPP combined with an Intel® Core™ i9-7900X CPU and Nvidia GeForce RTX™ 2080 Ti GPU in a desktop computer achieved the fastest detection rate of 33.30 ms. The detection speed on all other hardware configurations exceeded 33.30 ms, indicating that a powerful desktop GPU is required for real-time performance of this task. With adequate processing hardware, the developed technology could be integrated into a control system to automatically adjust brushes based on conveyor information from mechanical wild blueberry harvesters to make cleaning berries easier and enhance fruit quality.

Perancangan Aplikasi Absensi Karyawan Dengan Deteksi Wajah Menggunakan Metode Eigenface

Attendance is one of the most important repetitive transactions, because it is related to the productivity of employees and is one of the indicators of controlling human resources (HR) which aims to increase the potential of human resources and is used for efficiency. Current technological developments make it possible to create a system that can assist humans in recognizing a digital image. One area that is currently being developed is pattern recognition. This technology identifies a person's special physical characteristics. Examples of pattern recognition, for example, are face recognition, iris recognition, and fingerprint recognition. specific databases. Broadly speaking, the process of facial recognition is that the webcam camera captures the face. Then obtained a value of R, G, B. By using the initial processing, after that the facial processing stage is carried out using the eigenface method. In this eigenface method there are several core stages, namely: converting faces into matrices, calculating the FlatVector average, determining the eigenface values ??and carrying out the face identification process by looking for the eigenface values ??that are close to it. One of these facial recognition can be developed to become an attendance application that can be applied in the company to prevent manipulation of absenteeism by employees.

Identifikasi Masker pada Face Detection dengan Menggunakan Metode Haar Cascade dan CNN

The World Health Organization (WHO) provides standard recommendations for the prevention and spread of COVID-19 with the importance of face masks for protection from the virus. Technology can be used to help prevent viruses from spreading quickly through direct contact. Utilizing Internet of Things (IoT) based technology tools for public place entrances can be designed to perform rapid inspections. This can be done using image classification methods, namely Haar Cascade and Convolutional Neural Network (CNN). This study aims to detect masks on the face using the python programming language and input data via a webcam camera. A total of 500 datasets of photos of faces without masks and 500 datasets of photos of faces with masks were used as training data. The test results using the Haar Cascade method have an accuracy of 80% while using CNN the accuracy is 100%. So that this study becomes a reference in identifying obedience in wearing masks.

Designing a Real-Time-Based Optical Character Recognition to Detect ID Cards

This research 0aims to design a Real-time ID card detection based on Optical Character Recognition (OCR). OCR detects and records information into CSV files using a camera. Hopefully, it can become one of the administrative solutions in Indonesia by using existing identity cards using OCR in real time. This research method was carried out independently in August 2021 using ID cards as objects. The tool involved was a 320x320 pixel webcam camera on an HP Intel Core i5 7th Gen notebook. The software used by Easy OCR was Pytorch-based. ID cards were detected using an algorithm by TensorFlow object detection with SSD MobileNet V2 FPNLite 320x320 as the pre-trained model of Tensorflow. The researchers collected ID card images using a webcam with various light conditions and orientations and label them using labeling. The researchers trained it with only 20 photos. After 3000 training steps, the researchers obtained about 0.17 loss and 0.95. Thus, the ID card detection tool using OCR runs well.

Crack Detection of Eggshell using Image Processing and Computer Vision

This article presents an eggshell crack inspection using image processing techniques. This approach uses the concept of industrial 4.0 to reduce manual coordination in the egg industry’s manufacturing process. The method started with receiving images from a webcam camera. Then, we rescaled the image to 1147 x 633 for faster computation. Next, divide the image into the red and green channels. The red channel image was converted to grayscale using a Gaussian blur filter with a kernel filter 11 x 11 to reduce noise, followed by turning the image to binary. After that, multiply the binary image with the grayscale of the green channel to remove the background. By that time, a morphological operation was used to enhance the quality of the image. Finally, use the contour matrix to find the area of the object and then build the condition to detect the crack in the eggshell. These techniques of image processing are used to inspect the eggshell crack with a high accuracy of more than 98% as well as the high performance of computing.

Classification of Overlapping Eggs Based on Image Processing

This paper presents a method for classifying the overlapped eggs and counting the number of eggs on the conveyor belt using image processing techniques. The image was acquired by a webcam camera that connected to the computer and then rescaled. The image was then converted to grayscale and noise was reduced using a Gaussian blur filter. Otsu’s Binarization is used to convert the image to binary. The binary image is then subjected to morphological operations. Following that, using the Watershed Algorithm, separate the egg’s overlapped area. Finally, the prepared image is ready to be counted using the contour matrix method. This method independently classifies each egg segmentation and can count up to 18 eggs per frame with a processing time of less than 1 second.

RANCANG BANGUN ALAT MONITORING TANAMAN HIDROPONIK PAKCOY MEMANFAATKAN MIKROKONTROLER DAN TEKNIK COMPUTER VISION

Technology in agriculture is growing, one of them is hydroponic techniques because it uses anInternet of Things (IoT) based system. One of the plants used in hydroponic techniques is thepakcoy vegetable plant. Pakcoy is one of the vegetables that has the widest distribution in Asia.In addition, the characteristics of pakcoy vegetables are almost the same as mustard greens.Pakcoy vegetables are also easy to cultivate because they only require a small amount of landand a short harvest period. This system is built using a microcontroller and computer visiontechniques as a control center and uses a Raspberry Pi 4 type B mini PC as a visual notificationand is equipped with a dc motor gearbox, L298N motor driver and webcam camera. Thissystem works automatically to control which plants are healthy and which plants are sick. Thisstudy aims to detect diseased plants and healthy plants on pakcoy plants with a hydroponicpakcoy plant monitoring tool that uses a microcontroller and computer vision techniques. Thistool works by taking pictures directly through a webcam camera, then processing them with atrained model. The output of this tool displays the probability value of pakcoy plants showinghealthy plants and sick plants. From the results of testing the validation data using 60 validationdata, based on the accuracy of the detection tool healthy and sick plants were able to correctlyidentify 38 validation data and 22 data were not recognized properly, so the accuracy of thevalue was 63%. and produces an f1-score of 0,87

DRONE HUNTER AND FIRE USE FIRE EXTINGUISHER BALL-BASED IMAGE PROCESSING AND MACHINE LEARNING METHODS

Burning activities are still common in Indonesia, but the handling by the government has not been able to maximize performance in extinguishing fires that are difficult to achieve with standard equipment. The drone that the author developed is named Zerologic which is designed to use a remote monitoring system with machine learning algorithms and image processing methods in finding hotspots using a webcam camera. This camera sends object data which is then processed on the Raspberry Pi 4 using the OpenCV Python software. Besides being designed to search for hotspots, this drone can also minimize the spread of smoke by using a fire extinguisher ball that functions as a fire extinguisher that will be carried directly by the drone. ZEROlogic drones are useful for making it easier for forest firefighters to handle forest fires by finding and extinguishing hotspots that are difficult to reach by humans. In addition to being able to search for and search for fire, this drone ZEROlogic goes directly to the hotspots.
 
 Keywords: Drone; Fire Extingusher Ball; Image Processing; Machine Learning

RANCANG BANGUN HIDROPONIK TANAMAN PAPRIKA DENGAN DRIP SYSTEM BERBASIS INTERNET OF THINGS

Technological advances have been utilized in various fields, including in agriculture.The technology that is currently widely used is the Internet of Things (IoT). With this technology,farmers can monitor and control remotely so that their work becomes more efficient and optimal.In this study, a control and monitor system was developed for paprika hydroponics. This systemwas built using a Rasberry Pi as a data processing center equipped with Arduino uno as ananalog data reader and relay control, a DS18B20 sensor as a water temperature reader, a pH4502C sensor as a water acidity reader, and a TDS/EC sensor as a water nutrient ppm valuereader. This system is realized in the form of a prototype system for hydroponic paprika. Thesystem works automatically to monitor and control water temperature, water pH, nutrient ppmvalue, water level and automatic watering. The system is also equipped with a notificationfeature so that farmers can obtain information via telegram media such as water temperature,water pH, nutrient ppm value, water level, and watering notifications. This prototype is alsoequipped with a webcam camera as a feature that functions to detect ripe peppers in terms offruit color. The camera will detect the color of the peppers, and if the peppers are red, thepeppers are categorized as ripe, and farmers will receive notifications via telegram in the formof image data and notifications that ripe peppers have been detected.

The Design of Facial Expression Detection System to Determine the Level of Customer Satisfaction using K-Nearest Neighbor Method

Facial expressions are one of the ways humans communicate to convey personal emotions to their communication partner nonverbally. Therefore, human facial expressions can be used for various purposes, one of which is knowing customer satisfaction. So far, customers of Bank Rakyat Indonesia (BRI) provide feedback on service quality using only a polling system, namely by filling out a criticism and suggestion form and then entering it in a suggestion box which is distinguished between satisfied and dissatisfied. However, such a method is less effective because it can be easily manipulated by customers and customers are often indifferent to the feedback. So that the improvement of service quality tends to be less effective. This research will design a system that can recognize human facial expressions to determine the level of customer satisfaction with input data in the form of video data taken by a webcam camera with the viola-jones method to detect faces and determine facial patterns. Then the facial data will be classified using the K-Nearest Neighbor method to determine the type of facial expression. Determination of the value of k will determine the success rate of facial expression detection. The processed data will be displayed on a liquid crystal display (LCD) and then stored in a MySQL database. The results showed that the accuracy of facial expression detection was 80.77% from 52 facial expression data.