Facial Feature Extraction Research Articles

Kinship verification through facial images using multiscale and multilevel handcrafted features

We address kinship verification, which is a challenging problem in computer vision and pattern discovery. It has several applications, such as organizing photoalbums, recognizing resemblances among humans, and finding missing children. We present a system for facial kinship verification based on several kinds of texture descriptors (local binary patterns, local ternary patterns, local directional patterns, local phase quantization, and binarized statistical image features) with pyramid multilevel (PML) face representation for feature extraction along with our proposed paired feature representation and our proposed robust feature selection to reduce the number of features. The proposed approach consists of the following three main stages: (1) face preprocessing, (2) feature extraction and selection, and (3) kinship verification. Extensive experiments are conducted on five publicly available databases (Cornell, UB KinFace, Family 101, KinFace W-I, and KinFace W-II). Additionally, we provided a wide experiment for each stage to find the best and most suitable settings. We present many comparisons with state-of-the-art methods and through these comparisons, it appears that our experiments show stable and good results.

Implementation of Facial Feature Extraction Using Viola-Jones Method for Mobile Robot System

To be able to detect faces, the system must be able to identify the characteristics of the face, so that the camera can distinguish which parts of the face and non-faces. In identifying facial features performed on certain parameters, such as skin color, facial contours, lighting, facial pose. At this time face detection system uses an algorithm Viola-Jones is considered the most accurate in the detection and face tracking. In this research, we will discuss the application of interactions between humans and machines with image media in the form of faces. Interactions between humans and computers can be found in various places. One of the media interaction between humans and computers is with the image. This time the system will indicate to find how r o bot can act through the position of a person’s face recorded on camera robot. This system uses the Viola-Jones algorithm method which is a fairly popular object detection method because the detection process is carried out very quickly. Besides, the bot will also follow the face based on the identity it stores in the database. In recognizing the human face this system uses the Eigenface method. Both of these algorithms will adjust the robot’s motion as it should. The results of the experiment will show the robot can move quite well following the face stored in the database.

Design of IOT based facial recognition door access control locker services at tourist attractions in Bali

Safety and comfort are things that everyone wants to get on a trip. Every tourist who wants a vacation to one of the tourist destinations will prioritize these two things. Leisure in travel is influenced by the availability of supporting facilities. From accommodation, restaurants to facilities provided by tourism actors in each tourism object. One problem is the lack of facilities in attractions such as luggage storage (lockers), many tourists in enjoying tourism objects carrying luggage such as backpacks; groceries to backpacks for tourists are classified as backpackers. Of course this will disrupt the comfort of traveling. In the research conducted, researchers wanted to design a system of goods storage services as a form of supporting industry 4.0 in the tourism environment. By designing an image of the storage media of goods by implementing access control for doors in each locker based on image processing supported by a microcontroller. The method used that focuses on facial recognition as image input using the PCA (Principal Component Analysis) method, which can measure the Euclidean distance in an object’s face image. The design as a blueprint makes it easier to develop the next item of storage media (lockers).The results of this study indicate that the facial recognition method used is able to extract facial features and be recalibrated to activate the locker that is owned by the face object.

Emotion Recognition with Music using Facial Feature Extraction and Deep Learning

Listening to music is a very common thing. Nowadays, users pick music manually on their own i.e. the music has to be chosen manually. So, to ease the work of the users, expression recognition plays an important role in predicting and deciding the mood. It uses different facial features to detect mood. After a certain mood is detected, the system will play music according to the mood. In this system, machine learning techniques and algorithms such as SVM, Neural Networks, Image Preprocessing are used. Till now, the research has shown accuracy up to 72.4% by using SVM.

A Conceptual Model for Automated Attendance Marking System using Facial Recognition

The project represents an automated attendance system based on face recognition using discriminative local binary pattern and local directional pattern descriptors. The proposed system involves face detection, Features extraction and matching. The face detection is to detect faces based on Viola Jones algorithm . In feature extraction stage, the discriminative local binary pattern is used for different object texture feature extraction process. The proposed method with new features retain the contrast information of image patterns. The Facial recognition (or face recognition) is a type of biometric application that can identify a specific individual in a digital image by analyzing and comparing patterns based on the data stored in database. Smart attendance is a real time face recognition used for handling day to day activities of the employees and students. In manual attendance system there are several issues like fake attendance and mistakenly marked absent by carelessness of the faculty/teachers/lectures. In order to overcome these problems we are using this smart attendance system. Here multiple faces are detected and recognized with trained with various features. The automated face attendance marking system gives accurate performance.

A Discriminative Multi‐Channel Facial Shape (MCFS) Representation and Feature Extraction for 3D Human Faces

AbstractBuilding an effective representation for 3D face geometry is essential for face analysis tasks, that is, landmark detection, face recognition and reconstruction. This paper proposes to use a Multi‐Channel Facial Shape (MCFS) representation that consists of depth, hand‐engineered feature and attention maps to construct a 3D facial descriptor. And, a multi‐channel adjustment mechanism, named filtered squeeze and reversed excitation (FSRE), is proposed to re‐organize MCFS data. To assign a suitable weight for each channel, FSRE is able to learn the importance of each layer automatically in the training phase. MCFS and FSRE blocks collaborate together effectively to build a robust 3D facial shape representation, which has an excellent discriminative ability. Extensive experimental results, testing on both high‐resolution and low‐resolution face datasets, show that facial features extracted by our framework outperform existing methods. This representation is stable against occlusions, data corruptions, expressions and pose variations. Also, unlike traditional methods of 3D face feature extraction, which always take minutes to create 3D features, our system can run in real time.

A Teaching Evaluation System Based On Visual Recognition Technology

This paper designs and implements a student-centered teaching evaluation system based on face recognition and pose estimation technology. Our work firstly combines classroom attendance and behavior analysis in an evaluation system. For checking attendance, we select student faces as the identification object, employing a multi-task cascaded convolutional networks (MTCNN) as a face detector and a deep learning network FaceNet to extract face features. Then the head pose information is analyzed using Ensemble of Regression Trees (ERT) algorithm, which is able to detect 68 key feature points of faces. At last, we design and implement the whole system, including designs of functional modules, service software, database and telecommunication of various parts. This system can check attendance and collect student behavior information automatically, enhancing the intelligent level of the learning and teaching system.

Deep learning for face recognition on mobile devices

Mobility implies a great variability of capturing conditions, which is not easy to control and directly affects to face detection and the extraction of facial features. Deep learning solutions seem to be the most interesting choice for automatic face recognition, but they are highly dependent on the model generated during the training stage. In addition, the size of the models makes it difficult for their integration into applications oriented to mobile devices, particularly when the model must be embedded. In this work, a small-size deep-learning model was trained for face recognition on low capacity devices and evaluated in terms of accuracy, size and timings to provide quantitative data. This evaluation is aimed to cover as many scenarios as possible, so different databases were employed, including public and private datasets specifically oriented to recreate the complexity of mobile scenarios. Also, publicly available models and traditional approaches were included in the evaluation to carry out a fair comparison. Moreover, given the relevance of template matching and face detection stages, the assessment is complemented with different classifiers and detectors. Finally, a JAVA-Android implementation of the system was developed and evaluated to obtain performance data of the whole system integrated on a mobile phone.

An Enhanced Eye-Tracking Approach Using Pipeline Computation

Tracking and authentication at a low cost and in a convenient way is an important issue nowadays as opposed to using high cost for specified hardware and complex calibration process. In the paper, the prime concentration is divided into two: (i) eye tracking and (ii) parallelism in execution. First part has been subdivided as: Firstly, human face is taken from video sequence, and this is divided into frames. Eye regions are recognized from image frames. Secondly, iris region and pupils (central point) are being identified. In identifying pupil, the energy intensity and edge strength are taken into account together. Iris and eye corners are considered as tracking points. The famous sinusoidal head model is used for 3-D head shape, and adaptive probability density function (APDF) is proposed for estimating pose in facial features extraction. Thirdly, iris (pupil) tracking is completed by integrating eye vector and head movement information gained from APDF. The second part focuses on reducing execution time (ET) by applying pipeline architecture (PA). So the entire process has been subdivided into three phases. Phase-I is tracking eyes and pupils and preparing an eye vector. Phase-II is completing the calibration process. Phase-III is for matching and feature extraction. PA is integrated to improve performance in terms of ET because three phases are running in parallel. The experiment is done based on CK + image sets. Indeed, by using PA, the ET is reduced by (66.68%) two-thirds. The average accuracy in tracking (91% in left eye pupil (LEP)) and 93.6% in right eye pupil (REP)) is a robust one.

Face Identification Using HAAR Wavelet Transform

Face identification is the process of matching one or more people by analyzing and comparing the patterns of their faces. Algorithms for face identification typically extract facial features and compare them to a database to find the best match. The Haar wavelet transform has been mainly used for image processing and pattern identification due to its low computing requirements and quality to conserve and to compact the energy of a signal. In discrete wavelet transform, an image signal can be analyzed by passing it through an analysis filter bank followed by a decimation operation. Face identification has been performed in terms of correlation coefficient, Euclidean distance and sum of absolute difference.

An end-to-end face recognition method with alignment learning

Many effective methods have been proposed for face recognition in the past decade and the face recognition accuracy is also gradually improved, but these algorithms usually need to perform face alignment process based on the prior knowledge of facial structure before extracting facial features. The face recognition system usually consists of face detection, face alignment, facial feature extraction, etc., which are independent of each other, and it is difficult to design and train the end-to-end face recognition model. In this paper, an end-to-end face recognition method based on spatial transformation layer is proposed. Specifically, the spatial transformation layer is placed in front of the feature extraction layer of the face recognition network, and the face region is aligned by alignment learning which requires neither prior knowledge nor artificially defined geometric transformation. The face identity category information allows the convolutional neural network to automatically learn the most appropriate face alignment. Simulation experiments on CASIA-WebFace, LFW (Labeled Face in the Wild) and YTF (Youtube Face) face database have shown that the suggested alignment learning algorithm in this paper can realize the end-to-end face recognition and can effectively improve the face recognition rate as well.

Age-invariant face recognition based on deep features analysis

Age-invariant face recognition is one of the most crucial computer vision problems, e.g., in passport verification, surveillance systems, and missing individuals identification. The extraction of robust face features is a challenge since the facial characteristics change over age progression. In this paper, an age-invariant face recognition system is proposed, which includes four stages: preprocessing, feature extraction, feature fusion, and classification. Preprocessing stage detects faces using Viola–Jones algorithm and frontal face alignment. Feature extraction is achieved using a CNN architecture using VGG-Face model to extract compact face features. Extracted features are fused using the real-time feature-level multi-discriminant correlation analysis, which significantly reduces feature dimensions and results in the most relevant features to age-invariant face recognition. Finally, K-nearest neighbor and support vector machine are investigated for classification. Our experiments are performed on two standard face-aging datasets, namely FGNET and MORPH. Rank-1 recognition accuracy of the proposed system is 81.5% on FGNET and 96.5% on MORPH. Experimental results outperform the current state-of-the-art techniques on same data. These preliminary results show the promise of the proposed system for personal identification despite aging process.

R2DS: A novel hierarchical framework for driver fatigue detection in mountain freeway.

Fatigue driving is one of the main factors which affect the safety of drivers and passengers in mountain freeway. To improve the driving safety, the application of fatigue driving detection system is a crucial measure. Accuracy, speed and robustness are key performances of fatigue detection system. However, most researches pay attention to one of them, instead of taking care of them all. It has limitation in practical application. This paper proposes a novel three-layered framework, named Real-time and Robust Detection System. Specifically, the framework includes three modules, called facial feature extraction, eyes regions extraction and fatigue detection. In the facial feature extraction module, the paper designs a deep cascaded convolutional neural network to detect the face and locate eye key points. Then, a face tracking sub-module is constructed to increase the speed of the algorithm, and a face validation submodule is applied to improve the stability of detection. Furthermore, to ensure the orderly operation of each sub-module, we designed a recognition loop based on the finite state machine. It can extract facial feature of the driver. In the second module, eyes regions of the driver were captured according to the geometric feature of face and eyes. In the fatigue detection module, the ellipse fitting method is applied to obtain the shape of driver's pupils. According to the relationship between the long and short axes of the ellipse, eyes state (opening or closed) can be decided. Lastly, the PERCLOS, which is defined by calculating the number of closed eyes in a period, is used to determine whether fatigue driving or not. The experimental results show that the comprehensive accuracy of fatigue detection is 95.87%. The average algorithm rate is 32.29 ms/f in an image of 640×480 pixels. The research results can serve the design of a new generation of driver fatigue detection system to mountain freeway.

3D Face Authentication Software Test Automation

The 3D face authentication has become a hot trend for researchers and developers in the recent years, due to its many advantages over the 2D face recognition feature. The 3D reconstruction of a human face using both near-infrared and depth sensors is a complex process on mobile phones. It commonly involves algorithms like face detection, face landmark detection, facial feature extraction, and depth information analysis. The 3D face authentication feature is critical for the user as per as security and also providing a convenient way to authenticate by the correct user. Therefore, the testing of 3D face authentication algorithms and applications in terms of functionality, performance, and stability is critical. However, the research on 3D face authentication application level validation and testing method is lacking in the field. Most testers are still validating the application manually. In this paper, we propose a robotic-arm-based test automation for testing the 3D face authentication feature on mobile phones. We programmed a 6 degree of freedom (6-DOF) robotic arm to perform 3D face authentication automated tests that were executed manually before. Our test automation also benchmarked the performance of an in-house developed 3D face authentication application and a 3 rd party application which yielded promising latency and accuracy comparison results under different performance-impacting test scenarios.

Kriging Predictor for Facial Emotion Recognition Using Numerical Proximities of Human Emotions

Emotion recognition from facial expressions has gained much interest over the last few decades. In the literature, the common approach, used for facial emotion recognition (FER), consists of these steps: image pre-processing, face detection, facial feature extraction, and facial expression classification (recognition). We have developed a method for FER that is absolutely different from this common approach. Our method is based on the dimensional model of emotions as well as on using the kriging predictor of Fractional Brownian Vector Field. The classification problem, related to the recognition of facial emotions, is formulated and solved. The relationship of different emotions is estimated by expert psychologists by putting different emotions as the points on the plane. The goal is to get an estimate of a new picture emotion on the plane by kriging and determine which emotion, identified by psychologists, is the closest one. Seven basic emotions (Joy, Sadness, Surprise, Disgust, Anger, Fear, and Neutral) have been chosen. The accuracy of classification into seven classes has been obtained approximately 50%, if we make a decision on the basis of the closest basic emotion. It has been ascertained that the kriging predictor is suitable for facial emotion recognition in the case of small sets of pictures. More sophisticated classification strategies may increase the accuracy, when grouping of the basic emotions is applied.

Adaptive Convolution Local and Global Learning for Class-Level Joint Representation of Facial Recognition With a Single Sample Per Data Subject

Due to the absence of training samples and intraclass variation, the extraction of discriminative facial features and construction of powerful classifiers have bottlenecks in improving the performance of facial recognition (FR) with a single sample per data subject (SSPDS). In this paper, we propose to learn regional adaptive convolution features that are locally and globally discriminative to facial identity and robust to facial variation. Then, a novel class-level joint representation framework is presented to exploit the distinctiveness and class-level commonality of different facial features. In the proposed class-level joint representation with regional adaptive convolution features (CJR-RACF), both discriminative facial features that are robust to facial variations and powerful representations for classification with generic facial variations have been fully exploited. Furthermore, the gallery discrimination is extracted by our proposed weight-embedded supervision in the training phase (denoted by CJR-RACF w ), which is conducive to more specific features for FR with SSPDS. CJR-RACF and CJR-RACF w have been evaluated on several popular databases, including the large-scale CMU Multi-PIE, LFW, Megaface, and VGGFace datasets. Experimental results demonstrate the much higher robustness and effectiveness of the proposed methods compared to the state-of-the-art methods.

A Novel Facial Thermal Feature Extraction Method for Non-Contact Healthcare System

The non-contact healthcare system is a system that can avoid germ infection, and can also provide comfortable and convenient health care services for the caregivers. In the current thermal imaging research, local or small area images are used to represent the overall temperature information of the participants, but the temperature feature of the face should not only be used in a small part and ignore other parts. The facial thermal image can show clear temperature feature but is not conducive to meaningful feature extraction. Therefore, this research proposed a novel facial thermal image feature extraction method, which is used facial landmarks to detect and cut 12 blocks to establish a new feature matrix based on color mean values and standard deviation values. It can establish clear features on facial thermal images. The core part of the proposed healthcare system is the use of a deep learning framework, which is based on CAFFE under the DIGITS platform. The CAFFE runs the classic CNN, GoogLeNet. Based on the acquired images and new feature types, four models were trained, which were used for the raw RGB image, raw thermal image, RGB feature image, and thermal feature image. In the experiment, 800 images were used for training and validation, and 200 images were used for testing. An additional 40 images were used for random testing. The experimental results show that RGB images cannot be effectively used, thermal images can effectively predict the health status, and thermal feature images have the highest prediction accuracy.

Person-Independent Facial Expression Recognition Based on Improved Local Binary Pattern and Higher-Order Singular Value Decomposition

The recognition rate of person-independent facial expression is generally not high, which limits the practical application of facial expression recognition. Aiming at this problem, this paper analyzes the reasons for the low recognition rate of person-independent facial expression, and proposes a recognition algorithm of person-independent facial expression based on improved LBP (Local Binary Pattern) and HOSVD (Higher-Order Singular Value Decomposition). The algorithm has the following contributions of facial expression recognition framework. In the stage of facial expression feature extraction, the transient features extracted by LDP(Local Directional Pattern) and the persistent features extracted by CBP(Centralized Binary Pattern) are integrated to improve the discrimination of facial expression features. Moreover, in the stage of facial expression classification and recognition, the traditional nearest neighbor classification is changed into k-nearest neighbor pre-classification, and the regional energy calculated by HOSVD is used to determine the similarity of two images for secondary classification. Finally, in the extended Cohn-Kanade dataset and Oulu-CASIA NIR&VIS facial expression database, the theoretical analysis and experimental results show that the method has better recognition effect for solving the problem of person-independent facial expression recognition.

Face Identification Using HAAR Wavelet Transform

Face identification is the process of matching one or more people by analyzing and comparing the patterns of their faces. Algorithms for face identification typically extract facial features and compare them to a database to find the best match. The Haar wavelet transform has been mainly used for image processing and pattern identification due to its low computing requirements and quality to conserve and to compact the energy of a signal. In discrete wavelet transform, an image signal can be analyzed by passing it through an analysis filter bank followed by a decimation operation. Face identification has been performed in terms of correlation coefficient, Euclidean distance and sum of absolute difference.

Attendance automatic recognition and learning behavior of web-based course attendance based on machine learning algorithms

At present, the automatic attendance mode of distance education is not conducive to the confirmation and analysis of information after class. In order to study the effective automatic recognition algorithm of remote education classroom, this study takes the educational classroom of intelligent innovation and entrepreneurship of Internet + as an example for analysis. Moreover, this paper adopts facial features as the basis of recognition, establishes corresponding positioning points, and constructs precise positioning methods for real-time feature capture. At the same time, the ASM algorithm is used to extract facial features, and the algorithm is improved to improve the extraction effect. In addition, this paper proposes Gabor-wavelet packet set and Gabor beamlet set for auxiliary recognition, which improves the recognition rate. Finally, this paper designs experiments to analyze the performance of the algorithm of this study. The results show that the proposed algorithm has certain practical effects and can provide theoretical reference for subsequent related research.