Classical and modern face recognition approaches: a complete review

Ali, Waqar; Tian, Wenhong; Din, Salah Ud; Iradukunda, Desire; Khan, Abdullah

doi:10.1007/s11042-020-09850-1

Cited by 93 publications

(35 citation statements)

References 266 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method incorporates the SAC block based on the attention mechanism to capture important features and weight them to enhance model performance. In addition, we used a modified loss function constructed by adding a large margin to reinforce high discriminatory power for face recognition applications [34]. The proposed method delivers a considerable performance improvement over the baseline models and uses a higher threshold for face verification when subjected to an increase in intraclass variance.…”

Section: Discussionmentioning

confidence: 99%

SqueezeFace: Integrative Face Recognition Methods with LiDAR Sensors

Gwak

Thoummala

et al. 2021

Journal of Sensors

View full text Add to dashboard Cite

In this paper, we propose a robust and reliable face recognition model that incorporates depth information such as data from point clouds and depth maps into RGB image data to avoid false facial verification caused by face spoofing attacks while increasing the model’s performance. The proposed model is driven by the spatially adaptive convolution (SAC) block of SqueezeSegv3; this is the attention block that enables the model to weight features according to their importance of spatial location. We also utilize large-margin loss instead of softmax loss as a supervision signal for the proposed method, to enforce high discriminatory power. In the experiment, the proposed model, which incorporates depth information, had 99.88% accuracy and an F 1 score of 93.45%, outperforming the baseline models, which used RGB data alone.

show abstract

Section: Discussionmentioning

confidence: 99%

SqueezeFace: Integrative Face Recognition Methods with LiDAR Sensors

Gwak

Thoummala

et al. 2021

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…As a result, the accuracy of face recognition algorithms has improved significantly using deep learning. Deep learning techniques in face recognition use convolutional neural network (CNN), which are proved to be more successful as they have large quantities of training data [ 1 ]. Deep learning methods can leverage extensive datasets of faces and learn rich and compact representations of faces, allowing modern models to first perform and later to outperform the face recognition capabilities of humans.…”

Section: Introductionmentioning

confidence: 99%

A Study of Deep Learning-Based Face Recognition Models for Sibling Identification

Goel

Mehmood

Ugail

2021

Sensors

View full text Add to dashboard Cite

Accurate identification of siblings through face recognition is a challenging task. This is predominantly because of the high degree of similarities among the faces of siblings. In this study, we investigate the use of state-of-the-art deep learning face recognition models to evaluate their capacity for discrimination between sibling faces using various similarity indices. The specific models examined for this purpose are FaceNet, VGGFace, VGG16, and VGG19. For each pair of images provided, the embeddings have been calculated using the chosen deep learning model. Five standard similarity measures, namely, cosine similarity, Euclidean distance, structured similarity, Manhattan distance, and Minkowski distance, are used to classify images looking for their identity on the threshold defined for each of the similarity measures. The accuracy, precision, and misclassification rate of each model are calculated using standard confusion matrices. Four different experimental datasets for full-frontal-face, eyes, nose, and forehead of sibling pairs are constructed using publicly available HQf subset of the SiblingDB database. The experimental results show that the accuracy of the chosen deep learning models to distinguish siblings based on the full-frontal-face and cropped face areas vary based on the face area compared. It is observed that VGGFace is best while comparing the full-frontal-face and eyes—the accuracy of classification being with more than 95% in this case. However, its accuracy degrades significantly when the noses are compared, while FaceNet provides the best result for classification based on the nose. Similarly, VGG16 and VGG19 are not the best models for classification using the eyes, but these models provide favorable results when foreheads are compared.

show abstract

“…Face recognition is one of the main applications of machine vision and plays a significant role in data security field. Currently, most of the face information still uses visible imaging systems to capture face images and relies on feature extraction algorithms [ 1 ]. The research on face recognition in a controlled environment has proved to be successful and achieved wide application.…”

Section: Introductionmentioning

confidence: 99%

“…The research on face recognition in a controlled environment has proved to be successful and achieved wide application. There are still major challenges for an uncontrolled environment, where the subjects are dynamic, and it is difficult to capture changes in the machine angle due to several reasons [ 1 ]. Face information is prone to being influenced and partially reduced in the dark environment.…”

Section: Introductionmentioning

confidence: 99%

A Novel Infrared and Visible Image Fusion Approach Based on Adversarial Neural Network

Chen

Wang

Liang

et al. 2021

Sensors

View full text Add to dashboard Cite

The presence of fake pictures affects the reliability of visible face images under specific circumstances. This paper presents a novel adversarial neural network designed named as the FTSGAN for infrared and visible image fusion and we utilize FTSGAN model to fuse the face image features of infrared and visible image to improve the effect of face recognition. In FTSGAN model design, the Frobenius norm (F), total variation norm (TV), and structural similarity index measure (SSIM) are employed. The F and TV are used to limit the gray level and the gradient of the image, while the SSIM is used to limit the image structure. The FTSGAN fuses infrared and visible face images that contains bio-information for heterogeneous face recognition tasks. Experiments based on the FTSGAN using hundreds of face images demonstrate its excellent performance. The principal component analysis (PCA) and linear discrimination analysis (LDA) are involved in face recognition. The face recognition performance after fusion improved by 1.9% compared to that before fusion, and the final face recognition rate was 94.4%. This proposed method has better quality, faster rate, and is more robust than the methods that only use visible images for face recognition.

show abstract

Classical and modern face recognition approaches: a complete review

Cited by 93 publications

References 266 publications

SqueezeFace: Integrative Face Recognition Methods with LiDAR Sensors

SqueezeFace: Integrative Face Recognition Methods with LiDAR Sensors

A Study of Deep Learning-Based Face Recognition Models for Sibling Identification

A Novel Infrared and Visible Image Fusion Approach Based on Adversarial Neural Network

Contact Info

Product

Resources

About