Face Detection Application Research Articles

Multi-model fusion of DSFD and Zero-DCE for low-light face detection

Due to the wide application of face detection, face recognition task under extreme lighting conditions inevitably becomes one of the challenges. Under low-light conditions, the face detection task becomes more complex and difficult due to the presence of more noise and lower visibility in the image. For this extreme environment, this paper proposes a multi-model-assisted solution that combines image enhancement and face detection models to handle this task. The DarkFace dataset was used in this study's validation of a number of distinct face identification models and picture enhancement techniques. The experimental findings demonstrate that, on this dataset, the DSFD (Dual Shot Face Detector) and Zero-DCE (Zero-Reference Deep Curve Estimation) methods perform noticeably better than the other techniques, achieving a recall of 24.61%. Therefore, these two algorithms are selected as the core processing flow in this paper to improve the facial detection system's low-light performance. This combination offers a workable answer to the problem of face detection in low light by effectively increasing the visibility of the picture and raising the accuracy of face detection.

An Overview Review of Artificial Intelligence with Real-Time Face Detection Application

An Overview Review of Artificial Intelligence with Real-Time Face Detection Application

A Lightweight Face Detector via Bi-Stream Convolutional Neural Network and Vision Transformer

Lightweight convolutional neural networks are widely used for face detection due to their ability to learn local representations through spatial induction bias and translational invariance. However, convolutional face detectors have limitations in detecting faces under challenging conditions like occlusion, blurring, or changes in facial poses, primarily attributed to fixed-size receptive fields and a lack of global modeling. Transformer-based models have advantages on learning global representations but are insensitive to capture local patterns. To address these limitations, we propose an efficient face detector that combines convolutional neural network and transformer architectures. We introduce a bi-stream structure that integrates convolutional neural network and transformer blocks within the backbone network, enabling the preservation of local pattern features and the extraction of global context. To further preserve the local details captured by convolutional neural networks, we propose a feature enhancement convolution block in a hierarchical backbone structure. Additionally, we devise a multiscale feature aggregation module to enhance obscured and blurred facial features. Experimental results demonstrate that our method has achieved improved lightweight face detection accuracy with an average precision of 95.30%, 94.20%, and 87.56% across the easy, medium, and hard subdatasets of WIDER FACE, respectively. Therefore, we believe our method will be a useful supplement to the collection of current artificial intelligence models and benefit the engineering applications of face detection.

Extending the Capacity of IoT Devices with Serverless Services for a Face Detection Application: A practical evaluation

IoT systems have limitations and challenges in many ways, such as performance, energy consumption, memory footprint and data storage. One possible solution to minimize these limitations is to integrate IoT devices with the serverless cloud computing model. In this context, this work aims to analyze the integration of these two technologies to determine if it can help overcome the limitations of IoT devices, most notably energy consumption and performance. A face detection application was adapted to run on an IoT device and the AWS Serverless Lambda service. Through experimentation, some metrics like latency, execution time and energy consumption were collected to evaluate the impact of serverless technology on the scope of IoT systems development. Results show that serverless technology is superior to the IoT device used in terms of performance, but it is directly related to the quality of the network connection to which the device is connected. Serverless technology can also be very useful when power supply to an IoT device is an issue, as these devices are usually battery-connected and have limited power source.

GS-AGC: An Adaptive Glare Suppression Algorithm Based on Regional Brightness Perception

Existing algorithms for enhancing low-light images predominantly focus on the low-light region, which leads to over-enhancement of the glare region, and the high complexity of the algorithm makes it difficult to apply it to embedded devices. In this paper, a GS-AGC algorithm based on regional luminance perception is proposed. The indirect perception of the human eye’s luminance vision was taken into account. All similar luminance pixels that satisfied the luminance region were extracted, and adaptive adjustment processing was performed for the different luminance regions of low-light images. The proposed method was evaluated experimentally on real images, and objective evidence was provided to show that its processing effect surpasses that of other comparable methods. Furthermore, the potential practical value of GS-AGC was highlighted through its effective application in road pedestrian detection and face detection. The algorithm in this paper not only effectively suppressed glare but also achieved the effect of overall image quality enhancement. It can be easily combined with the embedded hardware FPGA for acceleration to improve real-time image processing.

MTIE-Net: Multi-technology fusion of low-light image enhancement network.

Images obtained in low-light scenes are often accompanied by problems such as low visibility, blurred details, and color distortion, enhancing them can effectively improve the visual effect and provide favorable conditions for advanced visual tasks. In this study, we propose a Multi-Technology Fusion of Low-light Image Enhancement Network (MTIE-Net) that modularizes the enhancement task. MTIE-Net consists of a residual dense decomposition network (RDD-Net) based on Retinex theory, an encoder-decoder denoising network (EDD-Net), and a parallel mixed attention-based self-calibrated illumination enhancement network (PCE-Net). The low-light image is first decomposed by RDD-Net into a lighting map and reflectance map; EDD-Net is used to process noise in the reflectance map; Finally, the lighting map is fused with the denoised reflectance map as an input to PCE-Net, using the Fourier transform for illumination enhancement and detail recovery in the frequency domain. Numerous experimental results show that MTIE-Net outperforms the comparison methods in terms of image visual quality enhancement improvement, denoising, and detail recovery. The application in nighttime face detection also fully demonstrates its promise as a pre-processing means in practical applications.

Cattle face detection method based on channel pruning YOLOv5 network and mobile deployment

The detection and identification of individual cattle plays an integral role in precision feeding and insurance claims, among others. Most current research is based on high-performance computing devices, which limits the application of deep learning techniques to mobile terminals. To this end, in this paper, we propose a channel-pruned YOLOv5 network-based method for cattle face detection on mobile terminals, referred to as NS-YOLO. First, the original model is sparsely trained and a sparse regularization penalty term is applied to the BN layers, then the corresponding mask values are labeled according to different weight thresholds, and the channels are pruned with global thresholds. Second, the detection precision is recovered by fine-tuning the model. Finally, the NCNN forward inference framework is used to quantize the model and an Android-based cattle face detection application is developed. Experimental results show that the model size, number of parameters and FLOPs are reduced by 86.10%, 88.19% and 63.25%, respectively, and the inference time is reduced by 35.53% compared to the original model, while mAP0.5 is reduced by only 1.6%. In particular, the 16-bit quantized model reduces the model size by 93.97% and the inference time by 34.97% compared to the original model on the mobile side. The results show that the proposed method can be easily deployed in resource-constrained mobile devices and has great advantages in practical engineering applications.

The Study of Performance for Face Detection Based on Multiple Representative Convolutional Neural Networks

Due to the diversity of deep learning models, choosing the suitable model for a specific task can be rather onerous. In this paper, the performance of three deep convolutional neural networks, namely VGG16, ResNet50, and MobileNetV2 on face detection were compared. Each model was trained on a dataset of 11,900 images from the FDDB dataset that included various face sizes and orientations with multiple augmentations, including color alteration, blurring, and flipping. The final layers of the models were modified into a binary classification model and a regression model indicating face found and coordinates of the facial bounding box. The models were trained on the same basis of 40 epochs with batch size 64 with binary cross entropy loss and DIoU loss and a learning rate of 0.0001 with a learning rate decay of 0.8 per epoch. The experimental results demonstrated that VGG16 outperformed ResNet50 and MobileNetV2 in terms of accuracy, with VGG16 achieving the highest score of 0.9240, followed by ResNet50 with a score of 0.8568, and MobileNetV2 with an accuracy of 0.6028. The results suggest that VGG16 is a more suitable choice for face detection applications than ResNet50 and MobileNetV2, while ResNet50 and MobileNetV2 may provide higher accuracy for other image recognition tasks or real time face detections. The findings in this paper can contribute to the selection of appropriate deep learning models for face detection.

Intensity matching through saliency maps for thermal and visible image registration for face detection applications

Intensity matching through saliency maps for thermal and visible image registration for face detection applications

Technique for recognizing faces using a hybrid of moments and a local binary pattern histogram

<p><span>The face recognition process is widely studied, and the researchers made great achievements, but there are still many challenges facing the applications of face detection and recognition systems. This research contributes to overcoming some of those challenges and reducing the gap in the previous systems for identifying and recognizing faces of individuals in images. The research deals with increasing the precision of recognition using a hybrid method of moments and local binary patterns (LBP). The moment technique computed several critical parameters. Those parameters were used as descriptors and classifiers to recognize faces in images. The LBP technique has three phases: representation of a face, feature extraction, and classification. The face in the image was subdivided into variable-size blocks to compute their histograms and discover their features. Fidelity criteria were used to estimate and evaluate the findings. The proposed technique used the standard Olivetti Research Laboratory dataset in the proposed system training and recognition phases. The research experiments showed that adopting a hybrid technique (moments and LBP) recognized the faces in images and provide a suitable representation for identifying those faces. The proposed technique increases accuracy, robustness, and efficiency. The results show enhancement in recognition precision by 3% to reach 98.78%.</span></p>

A Review on Face Detection Based on Convolution Neural Network Techniques

Face detection is one of the important applications of biometric technology and image processing. Convolutional neural networks (CNN) have been successfully used with great results in the areas of image processing as well as pattern recognition. In the recent years, deep learning techniques specifically CNN techniques have achieved marvellous accuracy rates on face detection field. Therefore, this study provides a comprehensive analysis of face detection research and applications that use various CNN methods and algorithms. This paper presents ten of the most recent studies and illustrate the achieved performance of each method.

Context-aware distribution of fog applications using deep reinforcement learning

Fog computing is an emerging paradigm that aims to meet the increasing computation demands arising from the billions of devices connected to the Internet. Offloading services of an application from the Cloud to the edge of the network can improve the overall latency of the application since it can process data closer to user devices. Diverse Fog nodes ranging from Wi-Fi routers to mini-clouds with varying resource capabilities makes it challenging to determine which services of an application need to be offloaded. In this paper, a context-aware mechanism for distributing applications across the Cloud and the Fog is proposed. The mechanism dynamically generates (re)deployment plans for the application to maximise the performance efficiency of the application by taking operational conditions, such as hardware utilisation and network state, and running costs into account. The mechanism relies on deep Q-networks to generate a distribution plan without prior knowledge of the available resources on the Fog node, the network condition, and the application. The feasibility of the proposed context-aware distribution mechanism is demonstrated on two use-cases, namely a face detection application and a location-based mobile game. The benefits are increased utility of dynamic distribution by 50% and 20% for the two use-cases respectively when compared to a static distribution approach used in existing research.

Effective Face Detector Based on YOLOv5 and Superresolution Reconstruction.

The application of face detection and recognition technology in security monitoring systems has made a huge contribution to public security. Face detection is an essential first step in many face analysis systems. In complex scenes, the accuracy of face detection would be limited because of the missing and false detection of small faces, due to image quality, face scale, light, and other factors. In this paper, a two-level face detection model called SR-YOLOv5 is proposed to address some problems of dense small faces in actual scenarios. The research first optimized the backbone and loss function of YOLOv5, which is aimed at achieving better performance in terms of mean average precision (mAP) and speed. Then, to improve face detection in blurred scenes or low-resolution situations, we integrated image superresolution technology on the detection head. In addition, some representative deep-learning algorithm based on face detection is discussed by grouping them into a few major categories, and the popular face detection benchmarks are enumerated in detail. Finally, the wider face dataset is used to train and test the SR-YOLOv5 model. Compared with multitask convolutional neural network (MTCNN), Contextual Multi-Scale Region-based CNN (CMS-RCNN), Finding Tiny Faces (HR), Single Shot Scale-invariant Face Detector (S3FD), and TinaFace algorithms, it is verified that the proposed model has higher detection precision, which is 0.7%, 0.6%, and 2.9% higher than the top one. SR-YOLOv5 can effectively use face information to accurately detect hard-to-detect face targets in complex scenes.

FIN-GAN: Face illumination normalization via retinex-based self-supervised learning and conditional generative adversarial network

Illumination normalization is one of the most challenging issues for facial analysis. To be specific, the variation of environmental illumination influences the visual quality of an image and drastically degrades the performance of face recognition, detection, landmark and other related applications. Retinex theory provides an important concept for processing illumination variation, which supposes that a face image can be decomposed into [an invariant reflectance component and a variant illumination component. Enlighten by this theory, in this paper, we put forward a novel deep learning approach which combines self-supervised learning and adversarial training for face illumination normalization (FIN-GAN). The proposed FIN-GAN framework can be implemented by two steps. Firstly, self-supervised learning is employed to decompose the original face image into the illumination component and the illumination-invariant component with Retinex constraint. Then, we employ the conditional generative adversarial network for face image reconstruction. For network optimization, we design the combined loss to ensure visual quality and preserve identity information. Experiments are performed on Extended-YaleB, CAS-PEAL, CMU-PIE and Multi-PIE datasets. Through multiple quantitative criteria, we demonstrate that the proposed FIN-GAN obtains promising performance in face illumination normalization.

Study on face detection based on an improved Gaussian skin color model

An improved Gaussian skin color model is proposed for face detection applications. It overcomes the issue that the traditional models become ineffective in extracting the skin color region in the presence of diverse skin colors and illuminations. It is a two-dimensional gaussian mixture model based on H-SV (i.e., an improved HSV) and YCbCr color spaces. Experimental results from several face image databases show that the detection accuracy is improved by 35.8% and 6.3%, respectively, compared to a traditional gaussian skin model and Adaboost algorithm.

Exploitation whale optimization based optimal offloading approach and topology optimization in a mobile ad hoc cloud environment

Widespread availability of network technologies, mobile user request is increased day by day. The larger amount of energy utilization and resource sufficiency of cloud computing is to create the maximum capacity of exploration and exploitation as troublesome. In this paper, we proposed the formation of mobile user behavior based topology and its optimization. During the offloading process, the minimization of response time and the energy consumption is the major goal of this paper. The topology node formations are performed via improved text rank algorithm (ITRA) and neural network (NN) classifiers with Euclidian distance. In this paper, we introduced an effective optimization algorithm of the exploitation whale optimization algorithm (EWOA) and it is the combination of differential evaluation (DE) and whale optimization algorithms (WOA). The offloading process of proposed EWOA produces an optimal outcome of minimized energy consumption and response time. The implementation works of the proposed EWOA are carried out in the VMware platform. The performance of the proposed method is evaluated using different size puzzles, face detection applications, and state-of-art methods. Ultimately, our proposed method produces optimal accuracy and convergence speed with the minimized offloading process.

Online Attendance Management System Based on Face Recognition Using CNN

Due to the growing trend of online classes, there is a pressing need to create an efficient system that can keep track of the students’ regular presence in these lectures. The traditional method of manual calculation of attendance proves to be ineffective and time-consuming. Hence, this problem can be addressed by building a system which will perform the task of marking the attendance of students by matching their faces in the multiple frames of an online class with their respective images present in the database. In this paper, face detection and recognition is being done on a video given as input to our program. Multiple faces are detected and recognised simultaneously in a class lecture. Face detection and recognition application is implemented using an open source computer vision called OpenCV. The paper doesn’t venture into real time application though it has a future in real time detection. The essential algorithms that have been extensively used are Convolution Neural Network and VGG16 architecture along with Haar features. Moreover, significant changes are to be integrated in order to bring an upheaval in the major image analysis modules such that the framework incorporates accuracy and robustness even when other variations on poses are imposed. Our framework has been evolved to detect and recognise faces in fixed time periods and mark the student’s attendance according to the average value of the faces detected and recognised within those fixed time periods such that the online attendance system can’t be evaded or cheated.

Cascaded Stripe Memory Engines for Multi-Scale Object Detection in FPGA

Object detection in embedded systems is important for many contemporary applications that involve vision and scene analysis. In this paper, we propose a novel architecture for object detection implemented in FPGA, based on the Stripe Memory Engine (SME), and point out shortcomings of existing architectures. SME processes a stream of image data so that it stores a narrow stripe of the input image and its scaled versions and uses a detector unit which is efficiently pipelined across multiple image positions within the SME. We show how to process images with up to 4K resolution at high frame rates using cascades of SMEs. As a detector algorithm, the SMEs use boosted soft cascade with simple image features that require only pixel comparisons and look-up tables; therefore, they are well suitable for hardware implemenation. We describe the components of our architecture and compare it to several published works in several configurations. As an example, we implemented face detection and license plate detection applications that work with HD images (1280 ×720 pixels) running at over 60 frames/s on Xilinx Zynq platform. We analyzed their power consumption, evaluated the accuracy of our detectors, and compared them to Haar Cascades from OpenCV that are often used by other authors. We show that our detectors offer better accuracy as well as performance at lower power consumption.

A Heterogeneous Processor Design for CNN-Based AI Applications on IoT Devices

This paper proposes a heterogeneous processor design for CNN-based AI applications on IoT devices. The heterogeneous processor contains an embedded RISC-V CPU that works as a general processor and an efficient CNN-accelerator that supports a variety of CNN models with a list of macro instructions. For demonstration, we implement a prototype on an FPGA platform with the RISC-V CPU working under 20 MHz and the CNN accelerator working under 100 MHz. As a case study, we run a CNN-based face detection and recognition application on this prototype. The prototype can process one image in 0.72 seconds and an ASIC implementation working under 400 MHz can process one image in less than 0.15 seconds by estimation, which can satisfy the needs for many IoT scenarios such as access control systems and check-in systems.

Application of face image detection based on deep learning in privacy security of intelligent cloud platform

The application of deep learning-based face detection in the privacy and security of intelligent cloud platforms is studied, in order to resolve the risk of private photo leakage on such platforms. Five key feature points of human faces (two eyes, two noses and two corners of mouth) are sought using the multitask cascaded convolution network (MTCNN). The algorithm utilizes the intrinsic links among Proposal Network (P-Net), Refine Network (R-Net) and Output Network (O-Net) to improve their face detection performances substantially. Since many existing data encryption methods, such as DES, RSA and AES, are applicable only to test data instead of digital images, the encryption of eigenvalues is achieved with a combination of chaotic logic diagrams and RC4 stream ciphers. Meanwhile, the MTCNN-generated face coordinates and user passwords are hash-converted and double-encrypted using hash table. The results show that the face detection accuracy of MTCNN reaches 95.04%, and that the image encryption method is suitable for network transmission. The chaotic logic diagrams increase the security of S-box initialization in the RC4 algorithm. The hash structure accelerates the file reading, whereas the hash conversion improves the security of critical data. In conclusion, the proposed encryption scheme is computationally fast and highly secure.