Human Face Images Research Articles

Sketch to Image Translation using Generative Adversarial Network

Using a Generative Adversarial Network (GAN) has proven its ability to successfully implement realistic images in image translation fields. It has its successful implementation in the sketch-to-image translation, too. Generative adversarial networks are widely used for the purpose of image translation. Most discriminators in generative adversarial networks use encoder or decoder blocks for image segmentation and classification tasks. U-net-based architecture is mostly used in the generator but rarely in the discriminator. If used in the discriminator, it is used for image resolution increment and segmentation tasks. In this research, a U-net-based discriminator is used for image translation tasks. U-net-based discriminator uses local and global differences between the real and fake images, which helps maintain global and local data representation. Resnet-9, used in the generator, uses skip connections, shortcuts, and concatenations, enabling information to flow from earlier to later layers. This helps preserve the original image features and solves the vanishing gradient problems in normal generators. The use of a strong discriminator and effective generator helps in the improvement system's performance. The available dataset was unpaired at the same time. Datasets from various sources were combined and formed a sketch-image pair. The input is a 512x256 human sketch and a corresponding real image pair. The image pair is split into sketch and image with dimensions 256x256. The system's output is the human face image of the corresponding sketch.

Sistem Buka-Tutup Sebuah Pintu Rumah Menggunakan Face Recognition Berbasis Mikrokontroler

Internet of Things technology is now widely used in all aspects of life including the application of smart homes. An automation technology is used to facilitate access at home, as well as access to the entrance of the house that uses facial image recognition (face detection). Human facial image recognition is one of the important technologies that continues to develop in the field of computer vision with its application in biometric recognition systems. One of them is by using the facial image recognition method, the Haar Cascade Classifier Algorithm. Therefore, a house door open-close system with facial recognition is designed using the ESP32-Cam module as a camera sensor. Face images were taken using the ESP32-Cam camera and processed using the ESP32 Microcontroller through the Arduino IDE program. Recognition results will be forwarded from the microcontroller to the PIR sensor, DC motor, buzzer, LED and website. The test result of this system is that if the detected face ID matches the data base, the PIR sensor will be active to detect the movement of objects in front of the entrance. When motion is detected, the buzzer as an alarm will be ON and the door will open and close automatically. If Face ID is not detected then the door will not open.

Artificial Intelligence-Generated Facial Images for Medical Education.

We evaluated the use of text-to-image models (Microsoft's Bing Image creator (powered by DALL·E) and Shutterstock's AI image generator) to generate realistic images of human faces and their associated pathology, which may be useful for medical education, given they may overcome issues of patient privacy and requirement for consent. These models have potential to augment rare medical image datasets for medical education, as well as provide greater inclusivity and representation of diverse populations.

CNN Based Efficient Facial Emotion Recognition System for Children

An efficient and robust technique for facial expression analysis for the different human face image input is carried out. During the analysis with every dataset, it is analysed through the Convolution Neural network (CNN) method. In order to analyse the facial data in terms of emotions, at this stage of research it is considered with the three different emotions such as Happy, Sad and Anger. For the analysis of facial data for the very rarely occurring disorder autism disorder in the age group around 10 years termed as children age group. As an initial step of analysis of autism disorder emotion expressed through face is a significant symptom hence in the present research is carried out using the freely available Kaggle database to achieve the better accuracy and stability in the obtained results by the proposed technique of methodology. To show the proposed technique is better than the existing algorithms, two different database are considered and cross correlation among the database in terms of its efficiency are considered.

Emotional Classification Based on Facial Expression Recognition Using Convolutional Neural Network Method

In recent years, the development of human-computer interaction technology has reached remarkable levels, particularly in the field of facial expression recognition. This technology utilizes human facial images to identify and classify emotional expressions such as happiness, sadness, fear, and more through computer image processing. Active research in facial expression recognition yields substantial benefits for individual and societal advancement, especially in the context of its application within Smart City environments. This study demonstrates that well- configured Convolutional Neural Network (CNN) models empowered by TensorFlow exhibit higher accuracy compared to models utilizing PyTorch. The TensorFlow model achieves the highest accuracy of 93% in recognizing emotional expressions, whereas the PyTorch model achieves 69% accuracy. The TensorFlow model also displays lower accuracy loss and shorter training times compared to the PyTorch model. In the context of calculating happiness indices within Smart City environments, the appropriate choice of technology significantly influences measurement accuracy and efficiency. Therefore, the TensorFlow platform, proven to deliver superior performance in this study, can be a strategic choice for integrating facial expression detection technology into happiness index measurements in such locations

A Dynamic Ensemble Selection of Deepfake Detectors Specialized for Individual Face Parts

The development of deepfake technology, based on deep learning, has made it easier to create images of fake human faces that are indistinguishable from the real thing. Many deepfake methods and programs are publicly available and can be used maliciously, for example, by creating fake social media accounts with images of non-existent human faces. To prevent the misuse of such fake images, several deepfake detection methods have been proposed as a countermeasure and have proven capable of detecting deepfakes with high accuracy when the target deepfake model has been identified. However, the existing approaches are not robust to partial editing and/or occlusion caused by masks, glasses, or manual editing, all of which can lead to an unacceptable drop in accuracy. In this paper, we propose a novel deepfake detection approach based on a dynamic configuration of an ensemble model that consists of deepfake detectors. These deepfake detectors are based on convolutional neural networks (CNNs) and are specialized to detect deepfakes by focusing on individual parts of the face. We demonstrate that a dynamic selection of face parts and an ensemble of selected CNN models is effective at realizing highly accurate deepfake detection even from partly edited and occluded images.

Emotion identification in human faces through ensemble of deep learning models

Investigation of human face images forms an important facet in affective analysis. The work, a DL-based ensemble is proposed for this purpose. Seven pre-trained models namely Facenet, Facenet2018, VGG16, Resnet-50, Senet-50, Arcface and Openface that have been developed for face verification have been exploited and customized for emotion identification. To each of these models, each all over interaction with softmax method to classification groups are augmented and entire network is then trained completely for emotion recognition. After training all the models individually, the probabilities for each of the class by each of the model are summed to derive at the final value. The class that holds the highest of this value is finalized as the predicted emotion. Thus, the proposed methodology involves image collection, image pre-processing comprising of contrast enhancement, face detection and extraction, face alignment, image augmentation facilitating rotation, shifting, flipping and zooming transformations and appropriate resizing and rescaling, feature extraction and classification through ensemble of customized afore-mentioned pre-trained convolutional neural networks, evaluation and evolving of best weights for emotion recognition from face images with enhanced accuracy. The proposed methodology is evaluated on the well-established FER-2013 dataset. The methodology achieves a validation accuracy of 74.67% and test accuracy of 76.23%. Further, similar images of another dataset (Face Expression Recogniton dataset) are included for training the models and the impact of extra training is assessed to see if there is improvement in performance. The experiments reveal marked improvement in face emotion identification performance reaching values of 94.98% for both validation and test set of FER-2013 dataset and 94.99% on validation set of Face Expression Recognition dataset.

Generation of High-Resolution Facial Expression Images Using a Super-Resolution Technique and Self-Supervised Guidance

The recent spread of smartphones and social networking services has increased the means of seeing images of human faces. Particularly, in the face image field, the generation of face images using facial expression transformation has already been realized using deep learning–based approaches. However, in the existing deep learning–based models, only low-resolution images can be generated due to limited computational resources. Consequently, the generated images are blurry or aliasing. To address this problem, we proposed a two-step method to enhance the resolution of the generated facial images by combining a super-resolution network following the generative model, which can be considered a serial model, in our previous work. We further proposed a parallel model that trains a generative adversarial network and a superresolution network through multitask learning. In this paper, we propose a new model that integrates self-supervised guidance encoders into the parallel model to further improve the accuracy of the generated results. Using the peak signalto- noise ratio as an evaluation index, image quality was improved by 0.25 dB for the male test data and 0.28 dB for the female test data compared with our previous multitaskbased parallel model.

Automatic Face Recognition System Using Deep Convolutional Mixer Architecture and AdaBoost Classifier

In recent years, advances in deep learning (DL) techniques for video analysis have developed to solve the problem of real-time processing. Automated face recognition in the runtime environment has become necessary in video surveillance systems for urban security. This is a difficult task due to face occlusion, which makes it hard to capture effective features. Existing work focuses on improving performance while ignoring issues like a small dataset, high computational complexity, and a lack of lightweight and efficient feature descriptors. In this paper, face recognition (FR) using a Convolutional mixer (AFR-Conv) algorithm is developed to handle face occlusion problems. A novel AFR-Conv architecture is designed by assigning priority-based weight to the different face patches along with residual connections and an AdaBoost classifier for automatically recognizing human faces. The AFR-Conv also leverages the strengths of pre-trained CNNs by extracting features using ResNet-50, Inception-v3, and DenseNet-161. The AdaBoost classifier combines these features’ weighted votes to predict labels for testing images. To develop this system, we use the data augmentation method to enhance the number of datasets using human face images. The AFR-Conv method is then used to extract robust features from images. Finally, to recognize human identity, an AdaBoost classifier is utilized. For the training and evaluation of the AFR-Conv model, a set of face images is collected from online data sources. The experimental results of the AFR-Conv approach are presented in terms of precision (PR), recall (RE), detection accuracy (DA), and F1-score metrics. Particularly, the proposed approach attains 95.5% PR, 97.6% RE, 97.5% DA, and 98.5% of F1-score on 8500 face images. The experimental results show that our proposed scheme outperforms advanced methods for face classification.

DeepPortraitDrawing: Generating human body images from freehand sketches

Various methods for generating realistic images of objects and human faces from freehand sketches have been explored. However, generating realistic human body images from sketches is still a challenging problem. It is, first because of the sensitivity to human shapes, second because of the complexity of human images caused by body shape and pose changes, and third because of the domain gap between realistic images and freehand sketches. In this work, we present DeepPortraitDrawing, a deep generative framework for converting roughly drawn sketches to realistic human body images. To encode complicated body shapes under various poses, we take a local-to-global approach. Locally, we employ semantic part auto-encoders to construct part-level shape spaces, which are useful for refining the geometry of an input pre-segmented hand-drawn sketch. Globally, we employ a cascaded spatial transformer network to refine the structure of body parts by adjusting their spatial locations and relative proportions. Finally, we use a style-based generator as the global synthesis network for the sketch-to-image translation task which is modulated by segmentation maps for semantic preservation. Extensive experiments have shown that given roughly sketched human portraits, our method produces more realistic images than the state-of-the-art sketch-to-image synthesis techniques.

People remember face pareidolia more than human face images during naturalistic encoding

People remember face pareidolia more than human face images during naturalistic encoding

MASK FACE INPAINTING BASED ON IMPROVED GENERATIVE ADVERSARIAL NETWORK

Face recognition technology has been widely used in all aspects of people's lives. However, the accuracy of face recognition is greatly reduced due to the obscuring of objects, such as masks and sunglasses. Wearing masks in public has been a crucial approach to preventing illness, especially since the Covid-19 outbreak. This poses challenges to applications such as face recognition. Therefore, the removal of masks via image inpainting has become a hot topic in the field of computer vision. Deep learning-based image inpainting techniques have taken observable results, but the restored images still have problems such as blurring and inconsistency. To address such problems, this paper proposes an improved inpainting model based on generative adversarial network: the model adds attention mechanisms to the sampling module based on pix2pix network; the residual module is improved by adding convolutional branches. The improved inpainting model can not only effectively restore faces obscured by face masks, but also realize the inpainting of randomly obscured images of human faces. To further validate the generality of the inpainting model, tests are conducted on the datasets of CelebA, Paris Street and Place2, and the experimental results show that both SSIM and PSNR have improved significantly.

Implementation of Face Recognition in People Monitoring Access In-and-Out of Crystal Dormitory Universitas Klabat

Crystal Dormitory is a dormitory in Universitas Klabat that accommodates some male students. This study aims for monitoring and minimize the entry of foreigners into the dormitory which affects the comfort and safety of boarding students. Using the prototyping model, the systems can observe the faces of students who live in the dormitory, as well as foreigners who enter the dormitory. The system performed face recognition to recognize a person’s face when the person’s face data has been stored in the dataset. The hardware in this system used a Raspberry Pi 3 which is integrated with a webcam and monitor to detect and recognize human facial images. With machine learning libraries namely TensorFlow, OpenCV, Dlib, and Haar Cascade, combine with Python programming, the system can detect and recognize human facial images. If the system detects an unfamiliar human face, then the image of that person's face will be sent via the Telegram application using the auto-send feature to notify about the unidentified person.

FEditNet: Few-Shot Editing of Latent Semantics in GAN Spaces

Generative Adversarial networks (GANs) have demonstrated their powerful capability of synthesizing high-resolution images, and great efforts have been made to interpret the semantics in the latent spaces of GANs. However, existing works still have the following limitations: (1) the majority of works rely on either pretrained attribute predictors or large-scale labeled datasets, which are difficult to collect in most cases, and (2) some other methods are only suitable for restricted cases, such as focusing on interpretation of human facial images using prior facial semantics. In this paper, we propose a GAN-based method called FEditNet, aiming to discover latent semantics using very few labeled data without any pretrained predictors or prior knowledge. Specifically, we reuse the knowledge from the pretrained GANs, and by doing so, avoid overfitting during the few-shot training of FEditNet. Moreover, our layer-wise objectives which take content consistency into account also ensure the disentanglement between attributes. Qualitative and quantitative results demonstrate that our method outperforms the state-of-the-art methods on various datasets. The code is available at https://github.com/THU-LYJ-Lab/FEditNet.

Deep learning-based models’ application to generating a cryptographic key from a face image

Generating cryptographic keys, such as passwords or pin codes, involves utilizing specialized algorithms that rely on complex mathematical transformations. These keys necessitate secure storage measures and complex distribution and processing mechanisms, which often incur substantial costs. However, an alternative approach emerges, proposing the generation of cryptographic keys based on the user's biometric data. Since one can generate keys "on the fly," there is no longer a requirement for key storage or distribution. These generated keys, derived from biometric information, can be effectively employed for biometric authentication, offering numerous advantages. Additionally, this alternative approach unlocks new possibilities for constructing information infrastructure. By utilizing biometric keys, the initiation of cryptographic algorithms like encryption and digital signatures becomes more streamlined and less burdensome in storing and processing procedures. This paper explores biometric key generation technologies, focusing on applying deep learning models. In particular, we employ convolutional neural networks to extract significant biometric features from human face images as the foundation for subsequent key generation processes. A comprehensive analysis involves extensive experimentation with various deep-learning models. We achieve remarkable results by optimizing the algorithm's parameters, with the False Reject Rate (FRR) and False Acceptance Rate (FAR) approximately equal and less than 10%. With code-based cryptographic extractors’ post-quantum level of security, we ensure the continued protection and integrity of sensitive information within the cryptographic framework.

Emotions recognition from human facial images based on fast learning network

Systems of facial emotion recognition have witnessed a high significance in the research field. The face emotions are based on human facial expressions which play a crucial role in silent communication. Machine learning algorithms have widely used in systems of human facial emotion detection from images. However, many systems suffer from low accuracy rate. In this paper, we present a system of facial emotion recognition by using images. In this proposed system, the samples of facial emotions have taken from Yale Face database. In addition, the histograms of oriented gradients (HOG) is used to extract features from the images. The extracted features will feed the fast learning network (FLN) algorithm for the classification part to identify the images of facial emotions with respect to their subjects. Many evaluation measurements have used to evaluate the performance of the proposed system. Based on the results of the experiment, the proposed system achieves 95.04% for the highest accuracy, 72.73% precision. Also, the results of the proposed system in terms of recall, f-measure, and G-main are all equal to 72.73%, respectively.

Automatic Synthesis of Realistic Human Faces from Text using GANs

Abstract: The field of image generation has witnessed significant advancements in recent years, particularly through the application of Generative Adversarial Networks (GANs). Many capable generative adversarial networks (GANs) models have emerged in recent times which help in synthesizing, generating real-like images and playing around with images using text. However, most existing tasks are limited to generating simple images such as flowers from captions.This project aims to create a deep learning based model and a system that tries to generate realistic human facial images from a given textual description. The project explores the utilization and applications of GANs, and uses a particular type like VQGAN. In this work, we extend this problem to the domain of face generation from fine-grained textual descriptions of the human face, e.g. “A person has curly hair, an oval face, and a mustache”. To expedite this process, the project uses VQGAN that is conditioned on the given text using a language conditioning model called CLIP (Contrastive Language-Image Pretraining). The model is trained on the CelebA image dataset. Overall, the project seeks to improve the speed and accuracy of mapping faces to text by leveraging advances in deep learning and image generation. We broaden this objective in our study to the less-explored area of face generation using precise textual descriptions of faces.

LCA-GAN: Low-Complexity Attention-Generative Adversarial Network for Age Estimation with Mask-Occluded Facial Images

Facial-image-based age estimation is being increasingly used in various fields. Examples include statistical marketing analysis based on age-specific product preferences, medical applications such as beauty products and telemedicine, and age-based suspect tracking in intelligent surveillance camera systems. Masks are increasingly worn for hygiene, personal privacy concerns, and fashion. In particular, the acquisition of mask-occluded facial images has become more frequent due to the COVID-19 pandemic. These images cause a loss of important features and information for age estimation, which reduces the accuracy of age estimation. Existing de-occlusion studies have investigated masquerade masks that do not completely occlude the eyes, nose, and mouth; however, no studies have investigated the de-occlusion of masks that completely occlude the nose and mouth and its use for age estimation, which is the goal of this study. Accordingly, this study proposes a novel low-complexity attention-generative adversarial network (LCA-GAN) for facial age estimation that combines an attention architecture and conditional generative adversarial network (conditional GAN) to de-occlude mask-occluded human facial images. The open databases MORPH and PAL were used to conduct experiments. According to the results, the mean absolution error (MAE) of age estimation with the de-occluded facial images reconstructed using the proposed LCA-GAN is 6.64 and 6.12 years, respectively. Thus, the proposed method yielded higher age estimation accuracy than when using occluded images or images reconstructed using the state-of-the-art method.

Circumscribed interests in autism: Can animals potentially re-engage social attention?

BackgroundCircumscribed interests (CI) in autism are highly fixated and repetitive interests, generally centering on non-social and idiosyncratic topics. The increased salience of CI objects often results in decreased social attention, thus interfering with social interactions. Behavioural, biomarker and neuroimaging research points to enhanced social functioning in autistic children in the presence of animals. For instance, neuroimaging studies report a greater activation of reward systems in the brain in response to animal stimuli whereas eye-tracking studies reveal a higher visual preference for animal faces in autistic individuals. This potentially greater social reward attached to animals, introduces the interesting and yet unexplored possibility that the presence of competing animal stimuli may reduce the disproportionately higher visual attention to CI objects. MethodWe examined this using a paired-preference eye-tracking paradigm where images of human and animal faces were paired with CI and non-CI objects. 31 children (ASD n = 16; TD n = 15) participated in the study (3391 observations). ResultsAutistic children showed a significantly greater visual attention to CI objects whereas typical controls showed a significantly greater visual attention to social images across pairings. Interestingly, pairing with a CI object significantly reduced the social attention elicited to human faces but not animal faces. Further, in pairings with CI objects, significantly greater sustained attention per visit was seen for animal faces when compared to human faces. ConclusionsThese results thus suggest that social attention deficits in ASD may not be uniform across human and animal stimuli. Animals may comprise a potentially important stimulus category modulating visual attention in ASD.

Face Recognition Systems

Abstract: Face recognition systems have become increasingly popular and important in recent years due to their various applications in security, surveillance, and human-computer interaction. These systems use algorithms to detect and recognize human faces in images or videos, and can be trained to identify individuals with high accuracy.