A Comparison of Transfer Learning Models for Face Recognition

Nowadays, computer-based face recognition is a mature and reliable mechanism that is significantly used in many access control scenarios along with other biometric methods. Face recognition consists of two subtasks including Face Verification and Face Identification. By comparing a pair of images, Face Verification determines whether those images are related to one person or not; and Face Identification has to identify a specific face within a set of available faces in the database. There are many challenges in face recognition such as angle, illumination, pose, facial expression, noise, resolution, occlusion and the few number of one-class samples with several classes. In this paper, we are carrying out face recognition by utilizing transfer learning in a siamese network which consists of two similar CNNs. In the siamese network, a pair of two face images is given to the network as input, then the network extracts the features of this pair of images and finally, it determines whether the pair of images belongs to one person or not by using a similarity criterion. The results show that the proposed model is comparable with advanced models that are trained on datasets containing large numbers of samples. furthermore, it improves the accuracy of face recognition in comparison with methods which are trained using datasets with a few number of samples, and the mentioned accuracy is claimed to be 95.62% on LFW dataset.

This research aims to develop artificial intelligence (AI) algorithms in the context of facial recognition with a focus on increasing accuracy in difficult environmental conditions. Although facial recognition technology has made great progress, challenges such as poor lighting, variations in facial expressions, and head rotation are still problems that must be overcome. The research methodology involved collecting a wide dataset covering a wide variety of faces under various environmental conditions. This data is then processed and its features are extracted using computer image processing techniques. Furthermore, several deep neural network architectures, such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), were developed, trained, and evaluated for face recognition tasks. The expected result is the development of an AI algorithm that is able to overcome challenges in facial recognition with higher accuracy than existing methods. In particular, significant improvements in facial recognition accuracy are expected especially under low lighting conditions and variations in facial expressions. This research has a major impact in a variety of security applications, such as border surveillance, building access control, and corporate security. With higher facial recognition accuracy, security risks can be significantly reduced, resulting in safer and more efficient security solutions. In conclusion, this research aims to bring innovation in facial recognition technology through advanced AI approaches, with the potential to improve security in various contexts.

Nowadays, Machine-based face recognition is becoming very commonplace, robust and dependable system that is widely employed in numerous cases for access control. As in traditional approach, face recognition needs the extraction of face features prior to classification and recognition, which affects recognition rate. We employ Face Verification checks whether the pictures are associated with a single individual, whereas Face Identification must identify a specific face from a collection of known profiles in the system. To tackle this question, this paper incorporates the CNN structure Alexnet to obtain face identification.Throughout this article, we perform facial recognition using transfer learning in a Siamese network composed of 2 comparable CNNs. A pair of 2 face picture is fed into the Siamese network as input, after which the network learns the traits of this pair of pictures.Next the network is trained using the PRelu activation function to find the ideal learning algorithm and maximal values. Then, the face was identified and categorized. Library Multi-Spectral Face Data - set and Library 2D Faceprint Database were used to test the methodology, it enhances the accuracy of face recognition when compared to algorithms trained on datasets with a particular dataset and a specific spectrum’s recognition rate peaked up to 98 percent.

Face recognition is a biometric technology used to identify individuals based on facial feature information. Previous studies of face recognition used features including the eye, mouth and nose; however, there have been few studies on the effects of using other facial components, such as the eyebrows and chin, on recognition performance. We measured the recognition accuracy affected by these facial components, and compared the differences between computer-based and human-based facial recognition methods. This research is novel in the following four ways compared to previous works. First, we measured the effect of components such as the eyebrows and chin. And the accuracy of computer-based face recognition was compared to human-based face recognition according to facial components. Second, for computer-based recognition, facial components were automatically detected using the Adaboost algorithm and active appearance model (AAM), and user authentication was achieved with the face recognition algorithm based on principal component analysis (PCA). Third, we experimentally proved that the number of facial features (when including eyebrows, eye, nose, mouth, and chin) had a greater impact on the accuracy of human-based face recognition, but consistent inclusion of some feature such as chin area had more influence on the accuracy of computer-based face recognition because a computer uses the pixel values of facial images in classifying faces. Fourth, we experimentally proved that the eyebrow feature enhanced the accuracy of computer-based face recognition. However, the problem of occlusion by hair should be solved in order to use the eyebrow feature for face recognition.

With the rapid development of electronic computers and information technology, face recognition is widely used in fields such as enterprises, entertainment, information security, and daily life. However, the current face recognition technology is still relatively poor in distinguishing facial features, resulting in a low accuracy of face recognition, which cannot meet increasing application requirements. For this reason, it is necessary to develop more accurate face recognition technology. Residual neural network (ResNet) neural network is a deep residual learning convolutional neural network, which can be used to solve the degeneration problem (i.e., after adding more layers to the neural network, the performance drops rapidly) of deep-learning neural networks. We aim to study the specific principles, calculation methods, and characteristics of the ResNet neural network, analyze the complexity of the classroom environment, propose the use of ResNet network for face feature extraction, and use additive angular margin loss for deep face recognition (ArcFace) as the loss function of the ResNet network to improve the ResNet network. Because the ArcFace function has the advantages of high performance, easy programming, low complexity and high training efficiency. We use this scheme to conduct field tests of face recognition on many students in the classroom. The test results show that this scheme enhances the discrimination of facial features and improves the accuracy of face recognition. In the case of different numbers of people, facial defects, and strong light exposure, the system can still detect and recognize faces stably. In the case of facial defects, the recognition accuracy rate is still 63.3%, and the recognition accuracy rate is still more than 60% under the illumination of strong light, and the recognition accuracy rate under correct conditions is more than 70%.

Currently, facial recognition systems need to reveal a person’s face to perform recognition. However, some people currently wear masks to prevent respiratory infections. Therefore, this will affect the efficiency of some face recognition systems. Therefore, in this study, we propose a face recognition and body temperature measurement system, and propose an integrated system for masked face recognition, mask detection, and body temperature detection. The proposed system can be used to recognize unconcluded facial images, and we use methods capable of simulating occluded images. The resulting images are used to train the neural network. Experimental results show that the accuracy of naked face recognition reaches 99.79%, and the accuracy of masked face recognition reaches 99.4%. In addition, the mask detection accuracy rate reaches 99.6%. Therefore, the system can improve the accuracy of face recognition and provide efficient security inspection results.

A multi-resolution approach for spinal metastasis detection using deep Siamese neural networks

Advances in neural networks and deep learning have opened a new era in medical imaging technology, health care data analysis and clinical diagnosis. This paper focuses on the classification of MRI for diagnosis of early and progressive dementia using transfer learning architectures that employ Convolutional Neural Networks-CNNs, as a base model, and fully connected layers of Softmax functions or Support Vector Machines-SVMs. The diagnostic process is based on the analysis of the neurodegenerative changes in the brain using segmented images of brain asymmetry, which has been identified as a predictive imaging source of early dementia. Results from 300 independent simulation runs on a set of four binary and one multiclass MRI classification tasks illustrate that transfer learning of CNN-based models equipped with SVM output layer is capable to produce better performing models within a few training epochs compared to commonly used transfer learning architectures that combine CNN pretrained models with fully connected Softmax layers. However, experimental findings also confirm that longer training sessions appear to compensate for the shortcomings of the fully connected Softmax layers in the long term. Diagnosis of early dementia on unseen patients’ brain asymmetry MRI data reached an average accuracy of 90.25% with both transfer learning architectures, while progressive dementia was promptly diagnosed with an accuracy that reached 95.90% using a transfer learning architecture that has the SVM layer.KeywordsConvolutional neural networkSupport vector machinesBrain asymmetryNeurodegenerative diseasesTransfer learningDementia

Facial recognition has become an important technology in the domain of biometric authentication, thereby providing greater protection to access control and identity verification applications. This work presents a facial verification system that is new and based on a Siamese neural network. Its operation is based on having deep convolutional architectures that extract strong feature embeddings for facial images. The proposed system employs the Labeled Faces in the Wild (LFW) dataset for training negative samples and was further enhanced using custom-captured positive and anchor images taken from the webcam with extensive data augmentation to mimic real-life variations in illumination, pose, and occlusion. The architecture of the network consists of an embedding layer to extract 4096-dimensional feature vectors, an L1 distance layer that measures the similarity between pairs of images, and a classification layer to predict the verification outcomes using a binary cross-entropy loss function optimized through the Adam algorithm. Experimental results indicate high precision and recall, showing near-unity performance on benchmark tests and real-time verification scenarios. Those results further highlight the capability of Siamese networks for one-shot learning in biometric applications, minimizing their dependence on large labeled datasets. Future work will focus on the scalability to larger and more heterogeneous datasets and integration with multimodal biometric systems. Generally, this research presents a promising framework for secure, efficient, and robust facial verification for real-world applications.

This paper presents a face and posture recognition model using convolutional neural network for adapting different resolution images. The performance of face recognition has dramatically improved by applying deep learning. However, it is known that the accuracy of face recognition would be decreased according to the resolution of face image. This problem is not negligible for some applications such as the real-time face recognition by surveillance camera, since the camera cannot always capture a face in a suitable position and distance. In order to solve this problem, our model adapts the resolution of an input image by selecting a proper model according to the resolution. In the experiment, we confirm the relationships between the recognition accuracy of face and posture and the resolution of captured image.

Neural machine translation (NMT) for low-resource languages has drawn great attention in recent years. In this paper, we propose a joint back-translation and transfer learning method for low-resource languages. It is widely recognized that data augmentation methods and transfer learning methods are both straight forward and effective ways for low-resource problems. However, existing methods, which utilize one of these methods alone, limit the capacity of NMT models for low-resource problems. In order to make full use of the advantages of existing methods and further improve the translation performance of low-resource languages, we propose a new method to perfectly integrate the back-translation method with mainstream transfer learning architectures, which can not only initialize the NMT model by transferring parameters of the pretrained models, but also generate synthetic parallel data by translating large-scale monolingual data of the target side to boost the fluency of translations. We conduct experiments to explore the effectiveness of the joint method by incorporating back-translation into the parent-child and the hierarchical transfer learning architecture. In addition, different preprocessing and training methods are explored to get better performance. Experimental results on Uygur-Chinese and Turkish-English translation demonstrate the superiority of the proposed method over the baselines that use single methods.

Surface electromyogram (sEMG)-based human-computer interface (HCI) is an effective tool for detecting human movements. Because sEMG-based motion recognition usually requires prolonged data measurements from the user (target), transfer learning reusing pre-measured (source) data from other users and pre-trained classifiers can be applied to sEMG data to reduce the measurement time. However, little knowledge is available regarding the combination of transfer learning methods and classifiers in sEMG data applications. Thus, we investigated the classification accuracy of data- and parameter-space-based transfer learning with shallow or deep classifiers in cross-subject sEMG classification. The dataset contains eight classes of forearm motions recorded from 25 volunteer participants. We used a support vector machine (SVM) as a shallow classifier as well as a deep neural network architecture, referred to as an artificial neural network (ANN), as a deep classifier. In addition, we used style transfer mapping (STM) as a data-space-based transfer learning method and fine-tuning (FT) as a parameter-space-based transfer learning method. Consequently, the classification accuracy of the ANN was higher than that of the SVM, regardless of the combinational use of transfer learning. STM and FT significantly improved the classification accuracy compared with non-transfer cases regardless of the classifier (note that FT can only be used with the ANN). In particular, the combined use of FT and the ANN yielded the best accuracy. These findings suggest that parameter-space-based transfer learning and deep classifiers are suitable for cross-subject sEMG classification. The combined use of parameter-space-based transfer learning and deep classifiers can effectively reduce the data measurement time of sEMG-based HCI applications.

In recent years, deep learning has entailed great progresses, but this success is seen as a triumph of empiricism. Despite the efforts made in the understanding of the deep models, the gap between the theoretical interpretability and the empirical success of deep models is still large. At present, the interpretability analysis of deep learning is mostly done after the training process. In this work, a novel method is proposed to extract interpretable features during the training process. Particularly, a modified Siamese network is used to disentangle features using a specially designed loss function. After a feature extractor, a fully connected layer is used to divide the output of the Siamese network into four different parts from which the new loss function is designed. The feature extractor used in the Siamese network may be different types of CNN. It is found that the proposed method can effectively disentangle the features at the semantic level, and the disentangled features can be used to effectively improve the classification accuracy in occluded face recognition.

An empirical study of the impact of masks on face recognition

The face recognition (FR) process identifies or confirms a person with the help of images and videos. The traditional aging FR (AFR) method encounters numerous issues as a result of age-related biological transformation. An adaptive fully recurrent deep neural learning (AFRDNL) technique is presented in this research to improve FR accuracy (FRA) with minimal time complexity (TC). Feature extraction and classification are two processes included in the proposed technique. The AFRDNL technique gathers facial images from the database and trains the face images with three layers. To learn the facial features, three hidden layers are employed in the AFRDNL technique. Finally, the AFRDNL technique utilizes the Gaussian activation function for matching extracted testing features with earlier saved training features. This process is repeated until a minimal training error with a higher FRA is achieved. Experimental evaluation is carried out with three image datasets like Face and Gesture Recognition Research Network, MORPH and Cross-Age Labeled faces in the Wild (CALFW) datasets using different metrics, such as FRA, false-positive rate (FPR), TC and F1score. The experimental results confirm that the AFRDNL technique effectively increases the FRA and F1score and minimizes the FPR and TC more effectively than the state-of-the-art methods.