Face Recognition approach via Deep and Machine Learning

The traditional face recognition technology is more complicated for the extraction of facial image features and the selection of classifiers, and the recognition rate is not high. With the continuous maturity of the convolutional neural network from handwritten digit recognition to face recognition, A face recognition algorithm that tests CNN using the Python+Keras framework. The method mainly involves two aspects. One is to observe the influence on the network by changing the number of neurons in the hidden layer; the other is to observe the influence on the network by changing the number of feature maps of the convolutional layer 1 and the convolutional layer 2. The best CNN model is 36-76-1024 through multiple sets of experimental tests. The model can automatically extract facial image features and classify them. Using adam optimizer and softmax classifier for face recognition can make training faster convergence and more. Effectively improve accuracy and use the Dropout method to avoid overfitting. The experimental results show that the recognition rate of the CNN model on the olivettifaces face database is 97.5%. When the optimal CNN model is used, the average recognition rate is close to 100%, which verifies the validity and accuracy of the algorithm and model.

As we all know fingerprint recognition is one of the secure and accurate Biometric Technologies. If think about it in deep even with the Biometric system the virus can be spread during these situations. To overcome this, we need to come up with a secure and contactless way of authentication. So, let’s update to some contactless remedies like Iris authentication which are unique for every individual and they don’t need to have any physical contact. So, we can use this Iris detection for a secure and contactless authentication system. The main aim of this research is to provide contactless remedies for students in Educational institutes like Smart Locking system, Attendance management system, and Library Transaction by using their Iris authentication and Face Recognition. Coming to the outline of the attendance management system, we will first collect the data from the Kaggle repository. Next, we split the data into training and testing, then we will train the data using transfer learning techniques and test the model by using test data. Finally, we integrated the trained model with the flask. If the Iris matches then the attendance of a particular person will be posted. If not matched then we train the model by adding new person’s data. For the construction of modern electronic security systems, real-time face recognition is crucial. Face detection, feature extraction, and face recognition are the three procedures involved. After recognizing the face, it will check whether the person’s face matches the collected database. If it matches it will show the person’s name, the number of books he took, and what those books are for Library transactions and in the same way the locker will be open if the person’s data is matched. The proposed methods are secure and unique contactless ways of authentication for every individual. So, we can use these detection and authentication systems for secure and contactless applications. It can be successfully used for students in Educational institutes like Smart Locking system, Attendance management system, and Library Transaction by using their Iris authentication and Face Recognition. The Covid-19 infection in society will undoubtedly decline if the proposed argument is implemented.

Numerous crime-related security concerns exist in e-commerce transactions recently. User authentication for mobile payment has numerous approaches including face recognition, iris scan, and fingerprint scan to identify user's true identity by comparing the biometric features of users with patterns in the signature database. Existing studies on the face recognition problem focus mainly on the static analysis to determine the face recognition precision by examining the facial features of images with different facial expressions for users rather than the dynamic aspects where images were are often vague affected by lighting changes with different poses. Because the lighting, facial expressions, and facial details varied in the face recognition process. Consequently, it limits the effectiveness of scheme with which to determine the true identity. Accordingly, this study focused on a face recognition process under the situation of vague facial features using deep reinforcement learning (DRL) approach with convolutional neuron networks (CNNs) thru facial feature extraction, transformation, and comparison to determine the user identity for mobile payment. Specifically, the proposed authentication scheme uses back propagation algorithm to effectively improve the accuracy of face recognition using feed-forward network architecture for CNNs. Overall, the proposed scheme provided a higher precision of face recognition (100% at gamma correction γlocated in [0.5, 1.6]) compared with the average precision for face image (approximately 99.5% at normal lighting γ=1) of the existing CNN schemes with ImageNet 2012 Challenge training data set.

Facial feature extraction (FFE) is considered as a challenging area for computer vision and artificial intelligence research community. There are numerous application domains of face recognition such as demographic classification and facial disease classification. In last few years, numerous feature extraction approaches are proposed. This review focuses on studies that exclusively use facial asymmetry as one of the main subject-specific facial characteristics for FFE. This paper provides a review about the related research conducted in the past two decades. First, we summarize the conventional FFE approaches and their main algorithms. Application of deep networks to facial asymmetry based FFE approaches is then presented. Multi-network deep models suitable for asymmetry-based FFE for different applications are also focused in this review. We presented the details about the publicly available face datasets, evaluation metrics, and comparison of the state-of-the-art results is also presented. The directions of asymmetry-based FFE for future research is also presented to provide an awareness about the existing and future trends. This review is presented to provide directions and ideas for future research in the field of facial asymmetry.

Automatic facial feature extraction is one of the most important and attempted problems in computer vision. It is a necessary step in face recognition, facial image compression. There are many methods have been proposed in the literature for the facial feature extraction task. However, all of them have still disadvantage such as not complete reflection about face structure, face texture. Therefore, a combination of different feature extraction methods which can integrate the complementary information should lead to improve the efficiency of feature extraction stage. In this paper we describe a methodology for improving the efficiency of feature extraction stage based on the association of two methods: geometric feature based method and Independent Component Analysis (ICA) method. Comparison of two methods of facial feature extraction: geometric feature based method combined with PCA method (called GPCA) versus geometric feature based method combined with ICA method (called GICA) on CalTech dataset has demonstrated the efficiency of GICA method. Our results show that GICA achieved good performance 96.57% compared to 94.70% of GPCA method. Furthermore, we compare two methods mentioned above on our dataset, with performance of GICA being 98.94% better 96.78% of GPCA method. The experiment results have confirmed the benefits of the association geometric feature based method and ICA method in facial feature extraction.KeywordsFace recognitionindependent component analysis (ICA)principal component analysis (PCA)geometric features

With the rapid development of the era of artificial intelligence, our lives have become more comfortable, and "face scanning" using facial recognition technology has become a new way of life. Facial recognition is a biometric technology that uses devices such as cameras to take photos containing faces, recognize faces in photos, and obtain information about facial features to match. Facial recognition technology belongs to a broad category of biometric technologies used by government and private institutions to identify people. The system includes the collection and recognition of facial images, extraction of key points, image processing, extraction of facial features, and comparison of facial recognition results. This article describes the advanced multiband Retinex algorithm, which allows processing images with uneven lighting and is integrated into the Yolov5 object detection pipeline. To evaluate this method, a dataset was collected from photographs of 3,045 students in various lighting scenarios with controlled changes in illumination achieved using a software light source. This method preserves image details and increases contrast, resulting in better detection accuracy while maintaining computational efficiency. The experimental results showed that the proposed approach can be more effective than traditional methods of obtaining images of faces in uneven lighting conditions.

This paper obtains the contour map related to the facial features of the face by extracting important information such as facial features of the face, so as to complete the task of extracting the facial features of the face. With the rapid development of computer software and hardware technologies, facial feature extraction technology has become a research hotspot in computer image processing application scenarios such as face recognition and short video sketch filters. However, the current facial feature extraction technology based on deep learning still has problems such as insufficient contours of the extracted facial features and excessive noise. Therefore, aiming at the shortcomings of the original facial feature extraction methods, this paper proposes a facial feature extraction method based on semantic segmentation. The content of the Larticle is mainly expanded from the following main aspects: First, the development status of semantic segmentation is introduced. Then, an improvement to the semantic segmentation network model is proposed. Finally, the average intersection ratio is used as the evaluation index of the segmentation accuracy of the network model. By comparing the feature maps obtained by different methods, it is found that the improved semantic segmentation network model in this paper can realize the complete extraction of facial features.

There are many applications for systems coping with the problem of face localization and recognition, e.g. model-based video coding, security systems and mug shot matching. Due to variations in illumination, back-ground, visual angle and facial expressions, the problem of machine face recognition is complex. In this paper we present a robust approach for the extraction of facial regions and features out of color images. First, face candidates are located based on the color and shape information. Then the topographic grey-level relief of facial regions is evaluated to determine the position of facial features as eyes and month. Results are shown for two example scenes.

The complexity and applicability of facial recognition in the growing domains of security and authentication, payment, advertising and health care have accelerated the research and development of this niche in the artificial intelligence (AI) field. A facial recognition system utilizes technologies to recognize a human face through mapping of distinct facial features from raw data such as photography and video to information of known faces stored in the database. Recognizing faces in real-world images is a challenging task. Generally, a facial recognition system involves multiple processes such as facial detection, feature extraction, face matching and confidence scoring in which various techniques and algorithms are available in the form of libraries and frameworks. In this paper, an investigation is conducted using two pipelines to identify the effectiveness of two prevalent open-source libraries, OpenCV and OpenFace, on real-time face recognition system. In the OpenCV pipeline, Viola –Jones algorithm is chosen for face detection, while feature extraction is conducted using local binary pattern histogram (LBPH). Face detection is performed using dlib, while feature extraction is conducted using deep learning algorithm in the OpenFace pipeline. Performance measures of both pipelines are evaluated using Labelled Faces in the Wild (LFW) as a benchmark data set. In addition, a locally populated data set consisting of images of personnel who are given access to the office door system is used to experiment on the applicability of these pipelines on real streaming data. OpenFace achieved an AUROC of 0.98, while OpenCV scored 0.94. Both experiments inferred that facial recognition system with OpenFace pipeline outperforms OpenCV in all aspects of performance measures. Further development demonstrates the successful implementation of OpenFace pipeline to a functional prototype in replacing the manual door access control.

<p>This Paper proposes a new facial feature extraction approach, Wash-Hadamard Transform (WHT). This approach is based on correlation between local pixels of the face image. Its primary advantage is the simplicity of its computation. The paper compares the proposed approach, WHT, which was traditionally used in data compression with two other known approaches: the Principal Component Analysis (PCA) and the Discrete Cosine Transform (DCT) using the face database of Olivetti Research Laboratory (ORL). In spite of its simple computation, the proposed algorithm (WHT) gave very close results to those obtained by the PCA and DCT. This paper initiates the research into WHT and the family of frequency transforms and examines their suitability for feature extraction in face recognition applications.</p>

Face recognition as an important biometric identification method, with its friendly, natural, convenient advantages, has obtained more and more attention. This paper intends to research a face recognition system including face detection, feature extraction and face recognition, mainly through researching on related theory and the key technology of various preprocessing methods in face detection process, using KPCA method, focuses on the different recognition results in different preprocessing methods. In this paper, we choose YCbCr color space for skin segmentation and choose integral projection for face location. We use erosion and dilation of the opening and closing operation and illumination compensation method to preprocess face images, and then use the face recognition method based on kernel principal component analysis method for analysis and research, and the experiments were carried out using the typical face database. The algorithms experiment on MATLAB platform. Experimental results show that integration of the kernel method based on PCA algorithm under certain conditions make the extracted features represent the original image information better for using nonlinear feature extraction method, which can obtain higher recognition rate. In the image preprocessing stage, we found that images under various operations may appear different results, so as to obtain different recognition rate in recognition stage. At the same time, in the process of the kernel principal component analysis, the value of the power of the polynomial function can affect the recognition result.

A comprehensive account of almost all the feature extraction methods used in current face recognition systems is presented. Specifically we have made distinction in the holistic and local feature extraction and differentiate them qualitatively as opposed to quantitatively. It is argued that a global feature representation should be preferred over a bag-of-feature approach. The problems in current feature extraction techniques and their reliance on a strict alignment is discussed. Finally we have introduced to use face-GLOH signatures that are invariant with respect to scale, translation and rotation and therefore do not require properly aligned images. The resulting dimensionality of the vector is also low as compared to other commonly used local features such as Gabor, LBP etc. and therefore learning based methods can also benefit from it. In a typical multi-view face recognition task, where it is assumed to have several examples of a subject available for training, we have shown in an extensive experimental setting the advantages and weaknesses of commonly used feature descriptions. Our results show that under more realistic assumptions, most of the classifiers failed on conventional features. While using the introduced face-GLOH-signature representation is relatively less affected by large in-class variations. This has been demonstrated by providing a fair performance comparison of several classifiers under more practical conditions such as misalignments, large number of subjects and large pose variations. An important conclusion is to be drawn from the results on FERET is that conventional multi-view face recognition cannot cope well with regards to large pose variations. Even using a large number of training examples in different poses for a subject do not suffice for a satisfactory recognition. In order to solve the problem where only one training example per subject is available, many recent methods propose to use image synthesis to generate a given subject at all other views and then perform a conventional multi-view recognition (Beymer and Poggio, 1995; Gross et al, 2004). Besides the fact that such synthesis techniques cause severe artefacts and thus cannot preserve the identity of an individual, a conventional classification cannot yield good recognition results, as has been shown in an extensive experimental setting. More sophisticated methods are therefore needed in order to address pose invariant face recognition. Large pose differences cause significant appearance variations that in general are larger than the appearance variation due to identity. One possible way of addressing this is to learn these variations across each pose, more specifically by fixing the pose and establishing a correspondence on how a person’s appearance changes under this pose one could reduce the in-class appearance variation significantly. In our very recent work (Sarfraz and Hellwich, 2009), we demonstrate the usefulness of face-GLOH signature in this direction.

Personality computing lies on the effort of designing computational models to recognize personality traits from different sources of input such as visual (image), verbal (text) and vocal (audio). To recognize personality traits from facial images, the recognition model needs to extract facial features such as eyes, mouth, nose, etc. Facial features are relevant for personality judgements where they are providing information about human expression and behaviours. For example, by detecting eye’s movement, dimension and size, machines can describe people’s personality. Basically, people with higher score of conscientiousness have greater fluctuations in their pupil size while people who blink faster are more neurotic. The potential of each facial feature to automatically describe human personality has prompted research in personality recognition using CNN-based techniques. On the other hand, convolutional neural networks (CNN) have proven to be greatly success in the field of image processing including face recognition and detection. Since face detection is a key task in personality recognition using facial features, adoption of CNN model is a reliable choice. This study aimed to explore CNN-based models, which have been used and modified in the personality computing field. In this paper, we review several CNN-based models which have been employed for personality traits recognition, with an emphasis on extraction of facial features. Based on the finding, there are four models (VGGNet, ResNet, FaceNet and OpenFace) which are widely used and frequently adopted by previous studies in personality trait recognition. The adoption of CNN- based models in facial features extraction for personality traits recognition helps in achieving a good accuracy result. Thus, there is a huge potential to enhance and modify CNN-based model to generate more efficient model for facial features extraction tasks. Initially, this paper briefly explains personality computing and facial features extraction for personality recognition task. Next, this paper discusses the characteristics of network layer in CNN-based models for facial features extraction and personality recognition. Finally, this paper concludes that each of these models has its own features strength that are potentially useful for facial features extraction in development of personality traits recognition model.

Facial expression methods play a vital role in human-computer interaction and other fields, but there are factors such as occlusion, illumination, and pose changes in wild facial recognition, as well as category imbalances between different datasets, that result in large variations in recognition rates and low accuracy rates for different categories of facial expression datasets. This study introduces RCL-Net, a method of recognizing wild facial expressions that is based on an attention mechanism and LBP feature fusion. The structure consists of two main branches, namely the ResNet-CBAM residual attention branch and the local binary feature (LBP) extraction branch (RCL-Net). First, by merging the residual network and hybrid attention mechanism, the residual attention network is presented to emphasize the local detail feature information of facial expressions; the significant characteristics of facial expressions are retrieved from both channel and spatial dimensions to build the residual attention classification model. Second, we present a locally improved residual network attention model. LBP features are introduced into the facial expression feature extraction stage in order to extract texture information on expression photographs in order to emphasize facial feature information and enhance the recognition accuracy of the model. Lastly, experimental validation is performed using the FER2013, FERPLUS, CK+, and RAF-DB datasets, and the experimental results demonstrate that the proposed method has superior generalization capability and robustness in the laboratory-controlled environment and field environment compared to the most recent experimental methods.

Face recognition has been one of the most studied researches in computer vision, and facial feature extraction, is one of the cores of face recognition. In this paper, we focus on semantic segmentation methods for facial feature extraction. However, the structure and number of parameters of the model usually affect the accuracy of semantic segmentation tasks in facial feature extraction. High-resolution representation learning can bring better accuracy to semantic segmentation, and large convolutional kernels, which bring a larger effective receptive field and better shape feature extraction to the model, can also improve the performance of the segmentation model. In this paper, we propose a novel lightweight model, HRModel (HRM), for optimizing the accuracy and parameters of semantic segmentation tasks in face recognition. From the perspective of multi-scale fusion, large perceptual fields, and gradient segmentation using high-resolution parallel streaming networks as a framework, we use a multi-scale feature extraction module with a large convolutional kernel to reduce the number of parameters while maintaining accuracy. In the feature extraction block, we use a channel attention mechanism to aggregate feature maps of different depths and different receptive fields. At the same time, we apply depthwise separable convolution and gradient flow splitting to reuse the gradient information and hence reduce the number of parameters and computational effort of the network effectively. We compare our proposed model HRM with other single-model networks on semantic segmentation tasks for face recognition. The experimental results show that HRM significantly reduces the number of parameters and achieves an accuracy of 95.52% in the application of the CelebAMask-HQ dataset.