Haar Cascade Research Articles

Advancements in Real-Time Face Recognition Algorithms for Enhanced Smart Video Surveillance

Smart video surveillance systems are essential for guaranteeing security in a variety of settings. The capacity to recognize and follow people of interest inside video feeds is made possible by real-time face recognition, which is a key component of these systems. The refinement of a real-time face recognition system designed for video surveillance applications is the focus of this research. We proposed a technique that can effectively recognize faces in a variety of lighting situations, poses, and occlusions by utilizing innovative combination of Haar Cascade and Convolutional Neural Networks. To balance computational difficulties and increase scalability, the merging of edge computing and cloud-based solutions are also investigated. The performance of the proposed system is evaluated by vigilant evaluation, demonstrating its applicability in real-world circumstances. Our research aims to advance video surveillance technology with an emphasis on the synergy of real-time face recognition for more secure and effective surveillance systems.

Design of Boosted Cascade and RTLBP Features based Face Recognition Module Using ML in OpenCV

Over the past ten years, face recognition in images has become more and more important. Since facial recognition is a natural talent for humans, it could be challenging to train a computer to recognize faces. The detecting difficulty comprises three stages. Without the requirement for picture difference or skin color identification, the detector operates in real-time at fifteen frames per second. Proposed and developed is a face recognition system based on Real Time Local Binary Pattern (RTLBP) and Boosted Cascade of Simple Features (BCSF). Preprocessing, face identification and recognition, and annotation are the three stages of the system. Segmentation, filtering, thresholding, and improving image quality are all part of preprocessing. The face, which is crucial for identification, is identified using the BCSF approach. Every face in the database has a correlation and RTLBP calculation. Correlation and RTLBP analysis between the captured face and the database face is then used to conduct recognition. One statistical technique that falls within the large category of factor analysis is the Boosted Cascade of Simple Features. By reducing the massive quantity of data stored to the extent of the feature space needed to represent the data efficiently, the BCSF seeks to achieve this goal. The RTLBP is designed to recognize faces by using a wide 1-D pixel vector consisting of a 2-D face picture in compact main parts of the space function. This is referred to as self-space projection. The identity of the vectors in the covariance matrix, which is centred on a set of fingerprint images, helps determine the proper space. Using OpenCV, Open Computer Vision (OpenCV), Python, Eigen-face, Fisher Face, LBPH, and Haar Cascade programming, an algorithm for a camera-based, real-time face recognition system is developed in this project. The name of the detected individual appears in the top left corner of a highlighted rectangle that annotates the face. The process of recognition takes 10.18 seconds, with a 99.93% success rate.

Face Recognition using Deep Learning

Identifying a person primarily relies on their facial features, which even distinguish identical twins. As a result, facial recognition and identification become crucial for distinguishing individuals. Biometric authentication technology, specifically facial recognition systems, are utilized to verify one’s identity. This technology has gained popularity in modern applications, such as phone unlock systems, criminal identification systems, and home security systems. Due to its reliance on a facial image rather than external factors like a card or key, this method is considered more secure. The process of recognizing a person involves two primary steps: face detection and face identification. This article delves into the concept of developing a face recognition system utilizing Python’s OpenCV library through deep learning. Due to its exceptional accuracy, deep learning is an ideal method for facial recognition. The proposed approach involves utilizing the Haar cascade techniques for face detection, followed by the following steps for face identification. To begin with, facial features are extracted through a combination of CNN methods and the linear binary pattern histogram (LBPH) algorithm. For attendance to be marked as “present,” the check-in and check-out times of the detected face must be legitimate. If not, the face will be displayed as “unknown.”

Discover and safe: an automated security management system for educational institutions

In this paper, we proposed discover and safe (DaS) automatic security system by the help of face recognition. The focus of this automated system is to provide high-level security to manage the entry of people with face detection. This paper proposes haar cascade algorithm with dip libraries to create a camera-based real-time security management system through face detection and recognition. Haar cascade algorithm is an object detection algorithm which is mainly used in identifying face of any image or a real-time video (by webcam or building camera). The DaS framework worked on two phases: 1) to locate whether the VM is an unintended security; 2) to secure mission critical applications. The DaS access system implemented the face encoding scheme to detect the face and eye which works effectively on light and illumination changes. The results show that DaS framework can Armor the VM from obscured security problems and steal hidden doors against the attackers.

Smart and Sustainable Surveillance System

Safety and security are major concerns in the modern day. People and organizations can employ security mechanisms to safeguard their property for their homes or commercial enterprises. Present security systems involve the utilization of Assorted Sensors in cameras for video surveillance. This paper aims at providing one such idea to ensure the protection and security of one’s property. This technique performs Face Recognition as an authentication procedure when a new face is detected by a snapshot. We propose to present a sensible, smart and sustainable Closed - Circuit Television (CCTV) camera with intrusion detection using the LBPH-Local binary pattern histogram algorithm, SIM-Structural Similarity Index Measure, Haar Cascade Classifier, and TKinter. By utilizing intrusion detection, CCTV cameras record real-time videos and process the video at the time of recording to search out the unwanted people arriving within the surveillance area. Our GUI has different buttons supported with features. Adding DL support would create broad scope in this paper such as with DL we would be able to add up much more functionality. We can have future enhancements on this paper such as creating Portable CCTV, Deadly weapon detection, Accident Detection, Fire Detection.

An Automated Attendance System Using Facial Detection and Recognition Technology

The proposed system utilizes Haar Cascade algorithms for facial detection and recognition. The system accurately detects and recognizes individuals based on their unique facial features. Facial detection algorithms identify and extract facial regions from input images or video frames, isolating the necessary facial details for further analysis. Subsequently, facial recognition algorithms, LBPH, compare these features with pre-registered faces stored in the system's database, calculating confidence scores to determine individual identities. The system incorporates a user-friendly interface, enabling administrators to easily manage attendance records. They can effortlessly add or remove students from the system's database, access attendance reports, and monitor real-time attendance data. The proposed Attendance Management System revolutionizes the conventional attendance tracking process by offering enhanced accuracy, efficiency, and security while providing real-time monitoring and comprehensive reporting capabilities. With the potential for adoption in various educational institutions, organizations, and industries, this system represents a significant advancement toward streamlined and intelligent attendance management. Keywords: face detection, face recognition, attendance, LBPH

Weightless Neural Networks Face Recognition Learning Process for Binary Facial Pattern

The facial recognition process is normally used to verify and identify individuals, especially during the process of analyzing facial biometrics. The face detection algorithm automatically determines the presence or absence of a face. It is, however, theoretically difficult to analyze the face of a system with limited resources due to the complex pattern of a face. This implies an embedded platform scheme which is a combination of several learning methods supporting each other is required. Therefore, this research proposed the combination of the Haar Cascade method for the face detection process and the WNNs method for the learning process. The WNNs face recognition Algorithm (WNNs-FRA) uses facial data at the binary level and for binary recognition. Moreover, the sample face data in the binary were compared with the primary face data obtained from a particular camera or image. The parameters tested in this research include detection distance, detection coordinates, detection degree, memory requirement analysis, and the learning process. It is also important to note that the RAM node has 300 addresses divided into three face positions while the RAM discriminator has three addresses with codes (00), (10), and (10). Meanwhile, the largest amount of facial ROI data was found to be 900 pixels while the lowest is 400 pixels. The total RAM requirements were in the range of 32 , 768 bytes and 128 bytes and the execution time for each face position was predicted to be 33.3% which is an optimization because it is 66.67% faster than the entire learning process

Traffic Density Prediction using IoT-based Double Exponential Smoothing

The number of vehicles and currents that tend to increase causes traffic density. A system is proposed to calculate the number of vehicles and predict real-time traffic density. This research uses Haar Cascade to detect the number of cars and motorcycles and the Double Exponential Smoothing (DES) for forecasting the number of vehicles on the road. MAPE describes forecasting accuracy as a base for selecting the best smoothing constant (Alpha). The best test results from June 13 to 20, 2020, are cars on June 14, 2020 (alpha 0.5, MAPE 0%) and Motorcylecycles on June 18, 2020 (alpha 0.5, MAPE 0.1134% ). The most significant MAPE results of the car were on June 15, 2020, with alpha 0.5 and MAPE 2.1073%. The 3 minutes haar cascade detects 72.58% of cars and 81.90% of motorcycles.

Industry 4.0: Intelligent Quality Control and Surface Defect Detection

Quality Control (QC) has recently emerged as a significant global trend among manufacturers, adopting intelligent manufacturing practices in view of Industry 4.0 requirements. Intelligent manufacturing is the process of enhancing production through the use of cutting-edge technologies, sensor integration, analytics, and the Internet of Things (IoT). The proposed paper mainly focuses on the study of the scope and the evolution of quality control techniques from conventional practices to intelligent approaches along with the state of art technologies in place. The challenges faced in building intelligent QC systems, in terms of security, system integration, Interoperability, and Humanrobot collaboration, are highlighted. Surface defect detection has evolved as a critical QC application in modern manufacturing setups to ensure high-quality products with high market demand. Further, the recent trends and issues involved in surface defect detection using intelligent QC techniques are discussed. The methodology of implementing surface defect detection on cement wall surfaces using the Haar Cascade Classifier is discussed.

Machine Learning Techniques for Vehicle Detection

The traffic surveillance system is a type of intelligent system of traffic control. Traffic control provides solutions to most problems faced by people. It helps to monitor, detect traffic congestion and traffic accidents. As science evolved, it became possible to control traffic using video surveillance. Video surveillance is the most economical option that does not involve high costs or changes in infrastructure. Vehicle detection is one of the main parts of the traffic surveillance system. In this paper, vehicles will be detected using two different artificial intelligence methods (the YOLO method and the HAAR cascade classifier method). The first one is smarter than the second method, and both of them contain machine learning. The first processing step will read the video. Then vehicle detection algorithms are applied using two different ways. The comparison between them depends on the results to find the most effective and applicable vehicle detection method. After implementing the two methods, results were obtained using YOLO, that the accuracy is 91.31% and the error rate is 8.69%, in time 10 sec. As for using the XML (HAAR cascade classifier method) method, the accuracy is 86.9%, the quality is 86.9%, completeness is 90.9%, and the error rate is 13%, in time 17 sec. Thus, we conclude that the YOLO method has better results than the second method. Index Terms— Artificial Intelligence, Machine Learning, Vehicle Detection, Yolo Method.

Employee Presence Using Body Temperature Detection and Face Recognition

Employee performance can be measured by their presence or attendance, which applies to both civil servants and non-civil servants. Because the attendance system still uses the manual technique, it is considered inefficient due to the potential for data fraud and attendance problems. In addition, the government is adopting precautions against viruses in office buildings to maintain business continuity while the pandemic is being addressed. The goal of this study was to employ a facial recognition system and temperature measurement to lower the danger of COVID 19 transmission while also minimizing paper use by using a facial recognition system as a substitute for presences. It has so far permitted the digitization of formerly manual sights. The OpenCV library allows computers to detect faces using the haar cascade classifier approach and Python as a programming language. A Logitech C930e webcam with a resolution of 1080p at 30fps was used to capture facial data, which was then processed on a Raspberry Pi 4 microprocessor. It uses an MLX90614 sensor to monitor body temperature, which is controlled by anArduino Uno microcontroller. It is well integrated into the database based on body temperature testing and facial recognition. The development of a more accurate temperature sensor reading method for distance and employee body temperature is a priority for future research.

An Improved Method to Obtain Fish Weight Using Machine Learning and NIR Camera with Haar Cascade Classifier

The calculation of weight and mass in aquaculture systems is of great importance, since with this task, it is decided when to harvest; generally, the above is manipulating the body manually, which causes stress in the fish body. Said stress can be maintained in the fish body for several hours. To solve this problem an improved method was implemented using artificial intelligence, near-infrared spectroscopy camera, Haar classifiers, and a mathematical model. Hardware and software were designed to get a photograph of the fish in its environment in real conditions. This work aimed to obtain fish weight and fish length in real conditions to avoid the manipulation of fish with hands for the process mentioned, avoiding fish stress, and reducing the time for these tasks. With the implemented hardware and software adding an infrared light and pass band filter for the camera successfully, the fish was detected automatically, and the fish weight and length were calculated moreover the future weight was estimated.

Face Recognition using Video and Live Stream a Machine Learning Approach

One of the top computer vision technologies at the moment is facial recognition. In computer vision, recognising faces is always an extremely challenging process due to lighting, stance, and facial expression. Target objects are tracked by face recognition in live streaming or through video. It is a system application that, in simplest terms, automatically recognises a person from a live capture through camera or video frame. We suggested an automatic face recognition system in this project. When the person in front of the camera recognises him, this application, which is based on face detection, feature extraction, and recognition algorithms, automatically detects the human face. Although the camera is continuously identifying the face in every frame, we employed the Haar cascade classifier to detect human faces. We have utilised the CNN method to train the system using the dataset that is currently accessible, and using real-time face capture, we will store the face data in a database. It was trained using the LBPH recognizer. Face recognition has done through Harr cascade algorithm.

Towards Automatic Detection of Social Anxiety Disorder via Gaze Interaction

Social anxiety disorder (SAD) is an extreme fear of underperformance in various social situations. It is necessary to detect people with or without SAD for counseling and treatment. A few manual techniques in the existing literature show the possibility of SAD detection from gaze interaction. However, an automated prediction of SAD is scarce. In this research, an automatic technique to predict SAD using gaze interaction/avoidance is proposed, where a custom application was developed that used the Haar Cascade classifier to predict gaze interaction/avoidance. The experiments were conducted on 50 participants in a live environment using the developed application. SAD classes were predicted by using decision tree classifiers from the created gaze dataset. The results proved that SAD could be predicated with an overall accuracy of 80%. Furthermore, four classes of SAD (Mark, Moderate, Severe, Very Severe along with ‘No SAD’) could be predicted with an accuracy of 80%, 70%, 90%, 80%, and 80%, respectively. The research proved the possibility to predict SAD using computer-based methods without human intervention. Furthermore, it created the possibility of aiding a subjective Liebowitz Social Anxiety Scale (LSAS) with an objective technique described in this research.

Development of surveillance robot based on face recognition using Raspberry-PI and IOT

The advancement in recent technologies such as artificial intelligence (AI), computer vision (CV) and internet of things (IoT) extends to various areas, especially surveillance systems that require real-time facial recognition processing to ensure safety. In fact, mobile robots are widely used in surveillance systems to perform dangerous tasks that humans cannot.In this context, we propose a prototype of a low-cost mobile surveillance robot based on Raspberry PI 4 which can be integrated into any industrial area. This intelligent robot checks about the presence of intruder using IoT and face recognition technology.The system is equipped with passive infrared (PIR) sensor and camera to record live streaming video and photos, which are transmitted to the room control via IoT.Thanks to facial recognition algorithms, the system can distinguish between company personnel and intruders. Haar Cascade Classifier and LBPH (Local Binary Pattern Histogram) algorithm are used in image processing to detect and identify individuals. When a stranger is detected, alert notifications and email with captured image are sent to the room control via IoT. A web interface was developed to remotely control the designed robot via a WiFi connection. This application allows monitoring of a wide area and can improve the robot's perception system. Performance evaluations will be conducted to demonstrate the effectiveness and robustness of the face recognition algorithms used in this framework.

Facial Images Improvement in the LBPH Algorithm Using the Histogram Equalization Method

In face recognition research, detecting several parts of the face becomes a necessary part of the study. The main factor in this work is lighting; some obstacles emerge when the low light's intensity falls in the process of face detection because of some conditions, such as weather, season, and sunlight. This study focuses on detecting faces in dim lighting using the Local Binary Pattern Histogram (LBPH) algorithm assisted by the Classifier Method, which is often used in face detection, namely the Haar Cascade Classifier. Furthermore, It will employ the image enhancement method, namely Histogram Equalization (HE), to improve the image source from the webcam. In the evaluation, different light intensities and various head poses affect the accuracy of the method. As a result, The research reaches 88% accuracy for successful face detection. Some factors such as head accessories, hair covering the face, and several parts of the face, like the eye, mouth, and nose that are invisible, should not be extreme.

Development of Real-Time Landmark-Based Emotion Recognition CNN for Masked Faces.

Owing to the availability of a wide range of emotion recognition applications in our lives, such as for mental status calculation, the demand for high-performance emotion recognition approaches remains uncertain. Nevertheless, the wearing of facial masks has been indispensable during the COVID-19 pandemic. In this study, we propose a graph-based emotion recognition method that adopts landmarks on the upper part of the face. Based on the proposed approach, several pre-processing steps were applied. After pre-processing, facial expression features need to be extracted from facial key points. The main steps of emotion recognition on masked faces include face detection by using Haar-Cascade, landmark implementation through a media-pipe face mesh model, and model training on seven emotional classes. The FER-2013 dataset was used for model training. An emotion detection model was developed for non-masked faces. Thereafter, landmarks were applied to the upper part of the face. After the detection of faces and landmark locations were extracted, we captured coordinates of emotional class landmarks and exported to a comma-separated values (csv) file. After that, model weights were transferred to the emotional classes. Finally, a landmark-based emotion recognition model for the upper facial parts was tested both on images and in real time using a web camera application. The results showed that the proposed model achieved an overall accuracy of 91.2% for seven emotional classes in the case of an image application. Image based emotion detection of the proposed model accuracy showed relatively higher results than the real-time emotion detection.

REAL-TIME DETECTIONS OF OPENED-CLOSED EYES USING CONVOLUTIONAL NEURAL NETWORK

The sleepy condition can affect changing behaviors in the human body, and one part of the human body that gets this effect is the eye; eyes are narrower than in normal conditions, and the frequency of blinking eyes is going to increase when people are sleepy. In this study, we will study the behavior of eyes, opened and closed eyes that the camera can capture in real-time, and tools of image processing that can capture and track eyes. Data images from this treatment are fed into Convolutional Neural Network (CNN) as data learning, so CNN can recognize opened and closed eyes from those eyes. In this study, we will characterize tools of image processing (Haar cascade Method) combined with CNN and their performance to detect opened-closed eyes in real-time detections.
 In this study, we use two CNN models as a comparison; the first CNN model uses 1 layer with 2 nodes, and the second CNN model uses 2 layers, with the first layer with 500 nodes and the second layer with 2 nodes; the output of each CNN has two targets namely 'open-label eyes and 'close' label eyes. The image dataset contains 20000 eye images, i.e., 10000 'open' eye images and 10000 'close' eye images. The image dataset is trained into two CNNs so that we have two CNN models: the one-layer CNN model and the two-layer CNN model. Each of those models has a pre-trained network.
 Each pre-trained model CNN is tested to detect opened-eyes and closed-eyes in real time. There are ten different people. For example, in this experiment, each person was subjected to ten trials of 'opening' and 'closing' eye detection and counted successfully detecting and failing to detect; from all the sample people tested, it can be concluded that the percentage was successful in detecting and percentage failed to detect. The Two-layers CNN model has a 55 % success rate in this experiment.

MASK DETECTION ANALYSIS USING HAAR CASCADE AND NAÏVE BAYES

Coronavirus Disease (COVID-19) is a new virus variant that emerged in 2019. The World Health Organization (WHO) states that 394,381,395 people have been infected with COVID-19, and 5,735,178 have died. This epidemic has been found in Indonesia since March 2020. New cases in Indonesia are still increasing every day as a whole. The Government as a policy has imposed a policy on anyone who will be required to wear a mask and also carry out physical distancing so that they can work without the maker being exposed to the virus. In the midst of a pandemic, the use of masks has increased to prevent transmission. Various types of masks are easy to find, but not all masks are recommended to avoid transmission. Among them are the N-95 masks, which are recommended to prevent transmission. This application uses the haar cascade and naive bayes methods. The pycharm edition 2021.2 tools and python 3.8 are the detection systems used in this mask. The haar cascade method is also used in detecting objects with masks or not and naive Bayes, which is used as an accuracy calculation. This study uses a dataset of 1092, which is divided into 192 positive images and 900 negative images. Accuracy results using the haar cascade method are 100% more accurate, while the nave Bayes method is 76.6% less accurate.

Real-Time Face Recognition Civil Servant Presence System Using DNN Algorithm

Facial recognition has become a growing topic among Computer Vision researchers because it can solve real-life problems, including during the COVID-19 pandemic. The pandemic is why the Indonesian government has imposed social restrictions and physical contact in public places. Before the pandemic, most touch-based attendance systems used fingerprints or Radio Frequency Identification (RFID) cards. The solution proposed in this study is to identify real-time facial recognition of the Civil Service presence system using a Deep Neural Network. The goal is to minimize physical contact. The research stages include data collection, augmentation and preprocessing, CNN modeling and training, model evaluation, converting to OpenCV DNN, implementation of transfer learning, and identification of test data. This research contributes to testing variations in distance and position so it can recognize a person's face even when wearing a mask and glasses. This DNN model produces a validation accuracy value of 99.48% and a validation loss of 0.0273 with a data training process of 10 times. Tests for variations in distance, position, use of masks, and glasses on MTCNN detection provide an average accuracy for each trial of 100%, 96%, and 100%, respectively. Therefore, the average accuracy of the Haar Cascades detection test is 100%, 85%, and 100%.