Face Detection In Images Research Articles

Research on video image face detection and recognition technology based on improved MTCNN algorithm

With the development of modern computer technology and artificial intelligence, face image processing technology has been widely used in people's life and work. In order to realise face image detection and recognition in dynamic video, this paper proposes a face detection and recognition technology based on MTCNN algorithm. MTCNN algorithm includes R-Net, O-net and P-net deep network models, which can realise face image deep processing in dynamic video. In order to train MTCNN algorithm deeply, Wider_Face and CelebA database training sets were used to train the additional test tasks and regression key points of the model. After setting the main parameters of MTCNN algorithm, the algorithm is simulated and analysed. Through the comparative simulation analysis of traditional algorithm, SVM algorithm and 2DPCA algorithm, it can be seen that MTCNN algorithm has more excellent performance and can meet the needs of face image detection and recognition in dynamic video.

DeepFake Detection for Human Face Images and Videos: A Survey

Techniques for creating and manipulating multimedia information have progressed to the point where they can now ensure a high degree of realism. DeepFake is a generative deep learning algorithm that creates or modifies face features in a superrealistic form, in which it is difficult to distinguish between real and fake features. This technology has greatly advanced and promotes a wide range of applications in TV channels, video game industries, and cinema, such as improving visual effects in movies, as well as a variety of criminal activities, such as misinformation generation by mimicking famous people. To identify and classify DeepFakes, research in DeepFake detection using deep neural networks (DNNs) has attracted increased interest. Basically, DeepFake is the regenerated media that is obtained by injecting or replacing some information within the DNN model. In this survey, we will summarize the DeepFake detection methods in face images and videos on the basis of their results, performance, methodology used and detection type. We will review the existing types of DeepFake creation techniques and sort them into five major categories. Generally, DeepFake models are trained on DeepFake datasets and tested with experiments. Moreover, we will summarize the available DeepFake dataset trends, focusing on their improvements. Additionally, the issue of how DeepFake detection aims to generate a generalized DeepFake detection model will be analyzed. Finally, the challenges related to DeepFake creation and detection will be discussed. We hope that the knowledge encompassed in this survey will accelerate the use of deep learning in face image and video DeepFake detection methods.

Studi Pengenalan Teknologi Artificial Intelligence Bagi Guru dan Siswa SMK Nurul Islam Larangan

SMK Nurul Islam is a vocational high school located in Larangan sub-district, Brebes district, which was founded by the Nurul Islam Slatri educational foundation. Based on the results of an initial survey conducted at partners, that students, teachers, and employees (+- 80%) have heard of the industrial revolution 4.0, but only 30% have heard of Artificial Intelligence. And from the survey, it was found that only 2% have understood and understood Artificial Intelligence technology, which has been applied in almost all sectors of life. The survey results also show that all teachers, employees, and students are familiar with the use of information technology, such as: laptops, smartphones, and the internet. However, the current trend of information technology development is that many do not understand, especially regarding the application of the concept of Artificial Intelligence technology, such as: Face Recognition, Speech Recognition, Expert System, Chatboot, Image Detection, and others. Therefore, community service activities were carried out with the theme Introduction to Artificial Intelligence Technology. The methods of presentation, dialogue and demonstration are carried out in the implementation of these community service activities. Based on community service activities and the comparison between the results of the pre-test and post-test, it is obtained that the knowledge and understanding of partners, namely: students and teachers of SMK Nurul Islam Prohibition on Artificial Intelligence is increasing.

Detecting fake images by identifying potential texture difference

Fake detection has become an urgent task. Generative adversarial networks (GANs) extended to deep learning has shown its extraordinary ability in the fields of image, audio, and speech. But advanced technology benefits us, it also poses a threat to us when used in Cyber Crime. The Deepfake (common name for face manipulation methods) based on GANs can realize the replacement of different faces. Due to the development of GANs, faces generated by Deepfake can already be visually real. Deepfake can purposely replace any face to a different person, so that a fabricated event may be widely spread because of the convenience of the Internet, causing serious impacts such as personal attacks and cyber crime. Based on cutting-edge research , this paper proposes a intelligence forensic method of Deepfake detection. We first discover the subtle texture differences between real and fake image in image saliency, which shows difference in the texture of faces. To amplify this difference, we exploit guided filter with saliency map as guide map to enhance the texture artifacts caused by the post-processing and display the potential features of forgery. Resnet18 classification network efficiently learns the exposed difference and finally realizes the real and fake detection of face images. We evaluate the performance of the method and experiments verify that the proposed method can achieve the state-of-the-art detection accuracy .

Face Detection based approach to combat with COVID-19

The global problem at the moment is COVID-19 caused by corona-virus which led to the worldwide lockdown. However there are still people who are not taking proper precautions and maintaining social-distancing while going out for emergency situations. To ensure this the government is trying to monitor the actions of each and every citizen. It is not realistically possible to monitor the actions of each and every citizen. This problem can be possibly solved by the use of machine learning. In this paper we have presented face detection based technique to combat with COVID-19. At first this technique captures the image and detects the face using viola zones method. Then the detected face images are classified to detect the mask. It actually detects whether every person have used mask or not. If there present anyone without mask then the system starts alarm to inform it to the responsible authority and to alert the public. Here Principal Component Analysis (PCA) has been used to extract the feature from the detected face images and for the detection of mask K-Nearest Neighbor (KNN) classifier has been used.

AN EMPIRICAL STUDY AND EVALUATION ON AUTOMATIC EAR DETECTION

Biometric is one of the growing fields used in security, forensic and surveillance applications. Various types of physiological and behavioral biometrics are available today. Human ear is a passive physiological biometric. Ear is an important biometric trait due to many advantages over other biometric modalities. Because of its complex structure, face image detection is very challenging. Detection deals with finding or localizing the position of ear in the given profile face image. Various methods like manual, semiautomatic and automatic techniques are used for ear detection. Automatic ear localization is a complex process compared to manual ear cropping. This paper presents an empirical study and evaluation of four different existing ear detection techniques with our proposed method based on banana wavelets and circular Hough transform. A comparative analysis of the five algorithms in terms of detection accuracy is presented. The detection accuracy was calculated by means of manual as well as automatic verification.

Research of Face Detection Based on Skin Color Feature

Face image contains many pattern features and this paper studies a face detection algorithm based on skin color features. Through the analysis of the face detection method based on skin color features, the calculation process and principle are understood, and the algorithm and detection techniques such as color space, preprocessing face image detection technology. Building a corresponding skin color model based on face characteristics are analyzed in depth. Because the skin color only occupies a specific range in the primary color of color space, the probability likelihood graph of skin color is obtained by calculating skin color similarity. Then the binary image of the possible face region is obtained by smooth filtering, threshold segmentation, and other operations. Then the area center and height ratio are used to calculate the center of mass and deflection angle, and the correlation coefficient is matched with the face module. Finally, the face area is detected and marked. Test results show that the algorithm can achieve face detection well.

Application of Ear Detection in Non-frontal Face Recognition

Face gesture recognition is a research hotspot in the field of machine vision and pattern recognition.In this paper, we use the Haar-Like feature-based Gentle Adaboost algorithm to detect the ear of non-frontal face. An ear sample library for ear detection of non-frontal face images was constructed. Through zoom detection window and determining the ROI area, it can successfully detect ear and work better than the basic Adaboost algorithm. The detection rate of the algorithm in the experiment reached 82%. It is suitable for most of the non-frontal faces we photographed.It still has a good detection effect for images with a small amount of hair or eyeglass frame interference.Based on the contour information of the ear, an approximate method for determining the lower end of the ear based on edge detection and a head and neck boundary determination algorithm based on the lower end of the human ear are proposed, which is more complete than the previous algorithm based on the determination of the concave points on both sides of the neck. The face area is segmented to make the face contour finally applied on the fitted ellipse more accurate.

Optimization-Driven Kernel and Deep Convolutional Neural Network for Multi-View Face Video Super Resolution

One of the major challenges faced by video surveillance is recognition from low-resolution videos or person identification. Image enhancement methods play a significant role in enhancing the resolution of the video. This article introduces a technique for face super resolution based on a deep convolutional neural network (Deep CNN). At first, the video frames are extracted from the input video and the face detection is performed using the Viola-Jones algorithm. The detected face image and the scaling factors are fed into the Fractional-Grey Wolf Optimizer (FGWO)-based kernel weighted regression model and the proposed Deep CNN separately. Finally, the results obtained from both the techniques are integrated using a fuzzy logic system, offering a face image with enhanced resolution. Experimentation is carried out using the UCSD face video dataset, and the effectiveness of the proposed Deep CNN is checked depending on the block size and the upscaling factor values and is evaluated to be the best when compared to other existing techniques with an improved SDME value of 80.888.

Face re-identification challenge: Are face recognition models good enough?

Face re-identification (Re-ID) aims to track the same individuals over space and time with subtle identity class information in automatically detected face images captured by unconstrained surveillance camera views. Despite significant advances of face recognition systems for constrained social media facial images, face Re-ID is more challenging due to poor-quality surveillance face imagery data and remains under-studied. However, solving this problem enables a wide range of practical applications, ranging from law enforcement and information security to business, entertainment and e-commerce. To facilitate more studies on face Re-ID towards practical and robust solutions, a true large scale Surveillance Face Re-ID benchmark (SurvFace) is introduced, characterised by natively low-resolution, motion blur, uncontrolled poses, varying occlusion, poor illumination, and background clutters. This new benchmark is the largest and more importantly the only true surveillance face Re-ID dataset to our best knowledge, where facial images are captured and detected under realistic surveillance scenarios. We show that the current state-of-the-art FR methods are surprisingly poorfor face Re-ID. Besides, face Re-ID is generally more difficult in an open-set setting as naturally required in surveillance scenarios, owing to a large number of non-target people (distractors) appearing in open ended scenes. Moreover, the low-resolution problem inherent to surveillance facial imagery is investigated. Finally, we discuss open research problems that need to be solved in order to overcome the under-studied face Re-ID problem.

Development of technique for face detection in image based on binarization, scaling and segmentation methods

A technique for face detection in the image is proposed, which is based on binarization, scaling, and segmentation of the image, followed by the determination of the largest connected component that matches the image of the face. Modern methods of binarization, scaling, and taxonomic image segmentation have one or more of the following disadvantages: they have a high computational complexity; require the determination of parameter values. Taxonomic image segmentation methods may have additional disadvantages: they do not allow noise and outliers selection; clusters can’t have different shapes and sizes, and their number is fixed. Due to this, to improve the efficiency of face detection techniques, the methods of binarization, scaling and taxonomic segmentation needs to be improved. A binarization method is proposed, the distinction of which is the use of the image background. This allows to simplify the process of scaling and segmentation (since all the pixels in the background are represented by the same color), non-uniform brightness of the face, and not to use the threshold settings and additional parameters. A binary image scaling method is proposed, the distinction of which is the use of an arithmetic mean filter with threshold processing and fast wavelet transform. This allows to speed up the image segmentation process by about P 2 times, where P is the scaling parameter, and not to use the time-consuming procedure for determining. A binary scaled image segmentation method is proposed, the distinction of which is the use of density clustering. This allows to separate areas of the face of non-uniform brightness from the image background, noise and outliers. It also allows clusters to have different shapes and sizes, to not require setting the number of clusters and additional parameters. To determine the scaling parameter, numerous studies were conducted in this work, which concluded that the dependence of the segmentation time on the scaling parameter is close to exponential. It was also found that for small P, where P is the scaling parameter, the quality of face detection deteriorates slightly. The proposed technique for face detection in image based on binarization, scaling and segmentation can be used in intelligent computer systems for biometric identification of a person by the face image

Comparative Study of Different Classifiers Based on Extracted Facial Features for Supervised Age Estimation

Estimating a person age is a major concern for many researchers due to his importance in many applications, whereas finding a person age is crucial in making specific decision. This paper conducts a comparative study between two classification-algorithms for age estimation which applied on extracted Local Binary Patterns (LBP). It was also divided dataset into 3 classes in order to improve results and increasing accuracy of system, Root Mean Squared Error, Mean Absolute Error and other parameters are used to measure the precision of the system. The proposed methodology of this work is divided into three phases. First phase consists pre-processing methods in which selected image is handled using color to gray scale image conversion and histogram equalization. Result image of which is manipulated by standard Viola-Jones algorithm to detect and crop face area from the whole image. While to ensure same size for all images, detected face image is resized to 256 × 256. Second phase tends to extract LBP features to be fed in the next classification phase. In third phase, two classifiers Logistic Model Tree (LMT) as well as Sequential Minimal Optimization (SMO) have been applied on the extracted features for age estimation.

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.

Performance Evaluation of MadBoost on Face Detection

Adaboost Viola-Jones method is indeed a profound discovery in detecting face images mainly because it is fast, light and one of the easiest methods of detecting face images among other techniques of face detection. Viola Jones uses Haar wavelet filter to detect face images and it produces almost 80%accuracy of face detection. This paper discusses proposed methodology and algorithms that involved larger library of filters used to create more discrimination features among the images by processing the proposed 15 Haar rectangular features (an extension from 4 Haar wavelet filters of Viola Jones) and used them in multiple adaptive ensemble process of detecting face image. After facial detection, the process continues with normalization processes by applying feature extraction such as PCA combined with LDA or LPP to extract our week learners’ wavelet for more classification features. Upon the process of feature extraction proposed feature selection to index these extracted data. These extracted vectors are used for training and creating MADBoost (Multiple Adaptive Diversified Boost)(an improvement of Adaboost, which uses multiple feature extraction methods combined with multiple classifiers) is able to capture, recognize and distinguish face image (s) faster. MADBoost applies the ensemble approach with better weights for classification to produce better face recognition results. Three experiments have been conducted to investigate the performance of the proposed MADBoost with three other classifiers, Neural Network (NN), Support Vector Machines (SVM) and Adaboost classifiers using Principal Component Analysis (PCA) as the feature extraction method. These experiments were tested against obstacles of POIES (Pose, Obstruction, Illumination, Expression, Sizes). Based on the results obtained, Madboost is found to be able to improve the recognition performance in matching failures, incorrect matching, matching success percentages and acceptable time taken to perform the classification task.

Face image manipulation detection based on a convolutional neural network

Facial image manipulation is a particular instance of digital image tampering, which is done by compositing a region from one facial image into another facial image. Fake images generated by facial image manipulation now spread like wildfire on news websites and social networks, and are considered the greatest threat to press freedom. Previous research relied heavily on handcrafted features to analyze tampered regions which were inefficient and time-consuming. This paper introduces a framework that accurately detects manipulated face image using deep learning approach. The original contributions of this paper include (1) a customized convolutional neural network model for Manipulated Face (MANFA) identification; it contains several convolutional layers that effectively extract features of multi-levels of abstraction from a tampered region. (2) A hybrid framework (HF-MANFA) that uses Adaptive Boosting (AdaBoost) and eXtreme Gradient Boosting (XGBoost) to deal with the imbalanced dataset challenge. (3) A large manipulated face dataset that is manually collected and validated. The results from various experiments proved that proposed models outperformed existing expert and intelligent systems which were usually used for the manipulated face image detection task in terms of area under the curve (AUC), computational complexity, and robustness against imbalanced datasets. As a result, the presented framework will motivate the finding of a more powerful altered face images detection method and encourages the integration of the proposed model in applications that have to deal with manipulated images regularly.

Hybrid framework for detection of human face based on haar-like feature

Augmentation in computer technology has made attainable to prompt incipient video processing practices in territory of biometric identification. Applications embroil face detection and face recognition consolidated to examination framework, signal investigation etc. Face detection is broadly utilized as a part of intuitive user interfaces and assumes an essential part in the area of computer vision. In order to build a fully automated system that can analyze the information in face image, there is a requirement for powerful and productive face detection algorithms. In this paper a framework is proposed for human face detection in images acquired under various illumination conditions. The features established on Gabor filters extracted from local image are applied to be the input of the Haar like classifier. At last, the experiment indicates elite in both accuracy and speed of the created framework.

RETRACTED ARTICLE: Video Face Detection Based on Deep Learning

In recent years, with the development of Internet plus concept, online identity has become a major problem based on the continuous expansion of network applications. The online authentication technology based on biometric features can maintain the consistency of human digital identity and physical identity, so people pay more attention to it. This paper studies the problem of human face detection. The main tasks are as follows: an active body detection algorithm for convolution neural networks based on dynamic feature is proposed. First, the Pyramid LK optical flow method is used to track the video, and the dynamic information of the image is obtained. Then, the information of the optical flow is analysed, and the horizontal and vertical displacement are calculated. According to the two displacements, the displacement amplitude diagram is calculated, that is, the dynamic feature graph. The dynamic feature graph is used as the input of the convolution neural network. Finally, the feature extraction and the living detection are carried out. A face authentication system with living face detection function is designed. The system includes the registration phase and the authentication phase. The registration phase includes face image detection and feature extraction module. The authentication phase includes face detection, human face discrimination, feature extraction and similarity calculation module.

Face-based Document Image Retrieval System

Many of the documents such as passport, identity card, property documents, voter ID and certificates include face image of a person. These types of documents are used in various off-line and on-line applications. Retrieval of such documents based on face image is a useful application in government offices, various companies, and organizations. This paper proposes a method to retrieve documents from the database pertaining to a person based on face image. The proposed method includes three steps: (1) Detecting face image from query document (ii) Extracting the face image features and (iii) Retrieving all documents that contain face image similar to that of the query document. The proposed method extends the concept of grey level co-occurrence matrix to color images for feature extraction. Experiments are carried out on the database of 810 document images, in which face images are borrowed from face94 [1]. Mean Average Precision (MAP) of 82.66% is achieved with proposed method and the results are compared with current state of art including Haralick features associated with Grey Level Co-occurrence Matrix (GLCM) [2]. It is found that the results are encouraging compared with existing methods.

Measurement of Face Detection Accuracy Using Intensity Normalization Method and Homomorphic Filtering

One of the factors that affects the detection system or face recognition is lighting. Image color processing can help the face recognition system in poor lighting conditions. In this study, homomorphic filtering and intensity normalization methods used to help improve the accuracy of face image detection. The experimental results show that the non-uniform of the illumination of the face image can be uniformed using the intensity normalization method with the average value of Peak Signal to Noise Ratio (PSNR) obtained from the whole experiment is 22.05314 and the average Absolute Mean Brightness Error (AMBE) value obtained is 6.147787. The results showed that homomorphic filtering and intensity normalization methods can be used to improve the detection accuracy of a face image.

Face Detection in Image and Video using Neural Network

Face Detection in Image and Video using Neural Network