Multi-face Detection Research Articles

Automatic approach for mask detection: effective for COVID-19.

The outbreak of coronavirus disease 2019 (COVID-19) occurred at the end of 2019, and it has continued to be a source of misery for millions of people and companies well into 2020. There is a surge of concern among all persons, especially those who wish to resume in-person activities, as the globe recovers from the epidemic and intends to return to a level of normalcy. Wearing a face mask greatly decreases the likelihood of viral transmission and gives a sense of security, according to studies. However, manually tracking the execution of this regulation is not possible. The key to this is technology. We present a deep learning-based system that can detect instances of improper use of face masks. A dual-stage convolutional neural network architecture is used in our system to recognize masked and unmasked faces. This will aid in the tracking of safety breaches, the promotion of face mask use, and the maintenance of a safe working environment. In this paper, we propose a variant of a multi-face detection model which has the potential to target and identify a group of people whether they are wearing masks or not.

Single and Multiface Detection and Recognition System

Face detection has drawn the interest of numerous research groups because to its vast application in various domains such as surveillance and security systems, as human-computer interaction, and many more. Face identification is the important phase involving several factors such as lighting, facial expression, and ageing effects. It’s more tough as detection takes a lot of time to detect and distinguish a single face at a time. Moreover, most of the existing technology cannot accurately detect many faces simultaneously. This study therefore presents a system that can recognize and identify multiple face image simultaneously with various expressions. Face-recognition procedure consists of data gathering, face detection, extraction, and classification feature. The face dataset is obtained from 10 participants with varied backgrounds and expressions. Subsequently, the viola-jones technique together with threshold technique is utilized in face detection to detect face presents while removing the unnecessary background to reduce face recognition time processing further. The Principal Component Analysis (PCA) is then employed to extract features while maintaining as much information as possible from enormous image data set. After formulating each face’s representation, the classification process is considered to recognize the identities of users’ faces. Here, a non-parametric classifier i.e. Support Vector Machine (SVM) is applied in this process. Conclusively, the system is able to detect around 90 percent multi-face user in different conditions.

Multi-face detection and alignment using multiple kernels

Multi-face detection and alignment techniques under unlimited environment are challenging issues. In recent years, the demand for face detection and alignment techniques has increased in many areas, including automatic drive and security. However, some mainstream algorithms, such as the Multi-task Cascaded Convolutional Networks (MTCNN) algorithm cannot transfer to multi-face detection and alignment, which introduces new multi-size, multi-resolution, and multi-angle challenges. This paper proposes an improved algorithm—Multi-face-MTCNN for precise original face detection and alignment algorithm when there is an overlapping face scenario. We design two new network structures: Pixelfusion-MTCNN and Twoconv-MTCNN. Moreover, we propose new data augmentation method and optimized detection process which are applied in the Multi-face-MTCNN algorithm. The limitations associated with single-scale kernel size in MTCNN are solved to obtain a satisfactory performance. Compared to the MTCNN algorithm, experimental analysis of the FDDB dataset show that 1.766% improves Multi-face-MTCNN. Meanwhile, on the WIDER FACE verification benchmark, respectively, with regards to the three sub-datasets, the proposed algorithm’s performance is improved by 3.426%, 2.776%, and 21.576%. Besides, average alignment error of the left eye, right eye, nose, left mouth, and right mouth is performed on the proposed algorithm.

Glasses-free Three Dimensional Endoscopic Display System with Multi-face Detection

The glasses-free three dimensional(3D) endoscopic display system provides the surgeon with the depth information of the minimally invasive surgery scene obtained from the binocular perspective, which can effectively relieve the surgeon's posture fatigue and visual fatigue during the long-term surgery, and assist in the operation of surgical instruments more accurately to reduce the damage to the surrounding tissues of the operation area. However, the glasses-free 3D display device currently has the problem of a narrow optimal viewing zone and easy crosstalk, especially in the surgical teaching application scenario, which performs poorly. In order to overcome the limitation of the narrower field of view, we introduce deep learning algorithms to detect and locate multiple faces, fine-tune the 3D display grating of the endoscope, rearrange pixels, and change the best view area, so that more people can get the best view. The experimental results show that the face detection accuracy of the method is 97.88%, and the detection time is 135 frames/ms, which achieves high accuracy while maintaining real-time performance.

Multi-face Recognition for the Detection of Prisoners in Jail using a Modified Cascade Classifier and CNN

Identifying the identity of a prisoner in a detention cell, through facial recognition automatically is a big, exciting problem and there are many different approaches to solve this problem because it must detect multiple faces (multi-face). Especially in uncontrolled real-life scenarios, faces will be seen from various sides and not always facing forward, which makes classification problems more difficult to solve. In this research, one method is combined deep neural networks that is Convolutional Neural Networks (CNN) and Haar Cascade Classifier as real-time facial recognition, which has proven to be very efficient in face classification. Methods are implemented with assistance library Open-CV for multi-face detection and 5MP CCTV camera devices. In preparing the architectural model Convolutional Neural Networks Do configuration parameter initialization to speed up the network training process. Test results on 51 test data using constructs Convolutional Neural Networks VGG16 models up to a depth of 16 layers of convolution layers with input from the extraction of the Haar Cascade Classifier resulting in facial recognition system performance reaching an accuracy rate of about 87%.

Multi-face detection based on improved YCbCr color space

Face recognition has become a popular means of recognition. It is required in image retrieval, video monitoring, entrance and exit control of military bases or other sensitive areas and other occasions. Face recognition has three key steps: face detection, feature extraction and feature matching. Face detection plays an important role in face recognition. Skin color segmentation is an important part of face detection. The traditional skin color modeling rules of YCbCr color space still have some defects, so we made some improvements. We changed the parameters of the conversion matrix used in the conversion from RGB space to YCbCr color space, so that the chosen skin color region is closer to the face skin color region. By this way, the system can detect the face most accurately.

Hierarchical Skin-AdaBoost-Neural Network (H-SKANN) for multi-face detection

Face is one of the important parts of the human body that can be used in video surveillance security (VSS) system for identity recognition purposes. However, systems that work under uncontrolled environment such as VSS system suffer from illumination changes, unpredictability of face appearance due to the presence of accessories such as sunglasses and scarf, connected face and multiple face sizes. In this paper, a novel algorithm known as Hierarchical Skin-AdaBoost-Neural Network (H-SKANN) is introduced to overcome these problems. Skin is used to roughly locate face candidates. Then, AdaBoost is used to filter out non-face candidates. Subsequently, an artificial neural network is utilized as the main filter to finally detect the face. In order to handle multiple face sizes, all these algorithms are arranged in hierarchical manner. On top of this, face skin merging (FSM) is also introduced to connect blobs of skin regions to form a face. Experiments conducted on six single-face databases (AR, FERET, IMM, Georgia, Caltech, and Talking-PIE) and one multi-face benchmark database (ChokePoint) demonstrated that 98.07% and 95.48% of averaged accuracy have been achieved for single- and multi-face detection, respectively, using the proposed method.

Improved AdaBoost Algorithm for Face Detection and Its Application

Face detection plays a crucial role in developing human-robot interaction (HRI) for Intelligent Educational Robot (IER) to recognize users or speakers. In this paper, we introduce an intelligent vision algorithm that is able to detect human face from complex scene and filter out all the non-face but face-like images. The human face is detected in real time using the approach called AdaBoost-based Haar-Cascade Classifier[1-2], and the real human face detection is improved to implement from single-face detection to multi-face detection. Furthermore, variable head pose is taken into account, such as pitch, roll, yaw, etc. The proposed robot vision algorithm for human detection is tested to be effective and robust through real-time experiments.

Enhancing lifetime of visual sensor networks with a preprocessing-based multi-face detection method

Recently, advances in hardware such as CMOS camera nodes have led to the development of Visual Sensor Networks (VSNs) that process sensed data and transmit the useful information to the base station for completing subsequent tasks. Today, object detection and sending useful information to the base station for object recognition is emerged as an important challenging issue in VSNs. Our investigations show that the face’s information is adequate for completing object recognition. According to literature, many approaches have been proposed for object detection and sending useful information to the base station to be completed subsequent tasks like object recognition. However, in most of them, lack of preprocessing methods in camera nodes causes network to be faced with large volume of data. For example when there is more than one object within the each camera node filed-of-view, conventional works deliver empty spaces among objects to the base station. Also, most of them send whole information about each object to the base station, while sending only face’s information of each object is adequate for completing object recognition. Therefore, in this paper, a preprocessing method in camera nodes named Preprocessing-based Multi-Face Detection (PMFD) is proposed. Our method works based on the extracting bounding box of each object’s face, using Boosting-based face detection algorithm, and sending only the faces’ information to the base station. The simulation results show that PMFD method has acceptable preprocessing time complexity and injects low volume of traffic into the network. Consequently, PMFD method prolongs the network lifetime in comparison with state-of-the-art algorithms.

Real-time multi-face detection on FPGA for video surveillance applications

In the field of face recognition and in the establishment of a face database, face detection is a crucial step. In current security and surveillance systems, most of the face detection proposed now is focused on software algorithms to improve the detection rate and decrease false alarms. However, these more complex algorithms require more computation time, which hinders real-time applications. In this paper, we propose a real-time multi-face detection system based on hardware design to enhance processing time. The proposed hardware architecture is implemented on an Altera DE2-70 field-programmable gate array development board to test the feasibility of our hardware design. To implement, our system requires 15,223 logic elements. The proposed system can operate in real-time at a frame rate of 30 fps, and detects up to five faces simultaneously. Our experimental results show that the proposed face detection architecture provides a reliable real-time system operating at low cost and providing a high detection rate.

The TA2 Database – A Multi-Modal Database From HomeEntertainment

This paper presents a new database containing high-definition audio and video recordings in a rather unconstrained video-conferencing-like environment. The database consists of recordings of people sitting around a table in two separate rooms communicating and playing online games with each other. Extensive annotation of head positions, voice activity and word transcription has been performed on the dataset, making it especially useful for evaluating automatic speech-recognition, voice activity detection, speaker localisation, multi-face detection and tracking, and other audio-visual analysis algorithms.

Multi-face detection algorithm in complex background

Face detection based on skin color has a higher detection rate,but it also has a higher false detection rate.AdaBoost face detection algorithm is a fundamental solution to the real-time issue,but its detection rate is not satisfactory.For these reasons,the algorithm that combined skin color division and AdaBoost method was proposed.Firstly,color division was used for rough location of human faces,and after that the candidate region was put as the input of AdaBoost face detection window.In the pretreatment processing,the structure of adjustable elements was used to solve the problem that the human faces were lost because of the different size in the different images.The experimental results show that the proposed method improves the detection rate and also reduces the false rate.

Multi-face detection based on downsampling and modified subtractive clustering for color images

This paper presents a multi-face detection method for color images. The method is based on the assumption that faces are well separated from the background by skin color detection. These faces can be located by the proposed method which modifies the subtractive clustering. The modified clustering algorithm proposes a new definition of distance for multi-face detection, and its key parameters can be predetermined adaptively by statistical information of face objects in the image. Downsampling is employed to reduce the computation of clustering and speed up the process of the proposed method. The effectiveness of the proposed method is illustrated by three experiments.