Deep face recognition: A survey
TL;DR: A comprehensive review of the recent developments on deep face recognition can be found in this paper, covering broad topics on algorithm designs, databases, protocols, and application scenes, as well as the technical challenges and several promising directions.
About: This article is published in Neurocomputing.The article was published on 2021-03-14 and is currently open access. It has received 353 citations till now. The article focuses on the topics: Deep learning & Feature extraction.
Citations
More filters
Journal Article•
3,940 citations
15 Oct 2004
2,118 citations
TL;DR: This survey provides a comprehensive overview of a variety of object detection methods in a systematic manner, covering the one-stage and two-stage detectors, and lists the traditional and new applications.
Abstract: Object detection is one of the most important and challenging branches of computer vision, which has been widely applied in people's life, such as monitoring security, autonomous driving and so on, with the purpose of locating instances of semantic objects of a certain class. With the rapid development of deep learning algorithms for detection tasks, the performance of object detectors has been greatly improved. In order to understand the main development status of object detection pipeline thoroughly and deeply, in this survey, we analyze the methods of existing typical detection models and describe the benchmark datasets at first. Afterwards and primarily, we provide a comprehensive overview of a variety of object detection methods in a systematic manner, covering the one-stage and two-stage detectors. Moreover, we list the traditional and new applications. Some representative branches of object detection are analyzed as well. Finally, we discuss the architecture of exploiting these object detection methods to build an effective and efficient system and point out a set of development trends to better follow the state-of-the-art algorithms and further research.
749 citations
TL;DR: In this article, the authors provide a review of deep neural network concepts in background subtraction for novices and experts in order to analyze this success and to provide further directions.
278 citations
01 Jan 2006
TL;DR: It is concluded that the problem of age-progression on face recognition (FR) is not unique to the algorithm used in this work, and the efficacy of this algorithm is evaluated against the variables of gender and racial origin.
Abstract: This paper details MORPH a longitudinal face database developed for researchers investigating all facets of adult age-progression, e.g. face modeling, photo-realistic animation, face recognition, etc. This database contributes to several active research areas, most notably face recognition, by providing: the largest set of publicly available longitudinal images; longitudinal spans from a few months to over twenty years; and, the inclusion of key physical parameters that affect aging appearance. The direct contribution of this data corpus for face recognition is highlighted in the evaluation of a standard face recognition algorithm, which illustrates the impact that age-progression, has on recognition rates. Assessment of the efficacy of this algorithm is evaluated against the variables of gender and racial origin. This work further concludes that the problem of age-progression on face recognition (FR) is not unique to the algorithm used in this work.
139 citations
References
More filters
01 Oct 2014
TL;DR: An approach to building face datasets that starts with detecting faces in images returned from searches for public figures on the Internet, followed by discarding those not belonging to each queried person, and is releasing the FaceScrub dataset.
Abstract: Large face datasets are important for advancing face recognition research, but they are tedious to build, because a lot of work has to go into cleaning the huge amount of raw data. To facilitate this task, we describe an approach to building face datasets that starts with detecting faces in images returned from searches for public figures on the Internet, followed by discarding those not belonging to each queried person. We formulate the problem of identifying the faces to be removed as a quadratic programming problem, which exploits the observations that faces of the same person should look similar, have the same gender, and normally appear at most once per image. Our results show that this method can reliably clean a large dataset, leading to a considerable reduction in the work needed to build it. Finally, we are releasing the FaceScrub dataset that was created using this approach. It consists of 141,130 faces of 695 public figures and can be obtained from http://vintage.winklerbros.net/facescrub.html.
622 citations
07 Mar 2016
TL;DR: The aim of this data set is to isolate the factor of pose variation in terms of extreme poses like profile, where many features are occluded, along with other `in the wild' variations to suggest that there is a gap between human performance and automatic face recognition methods for large pose variations in unconstrained images.
Abstract: We have collected a new face data set that will facilitate research in the problem of frontal to profile face verification ‘in the wild’. The aim of this data set is to isolate the factor of pose variation in terms of extreme poses like profile, where many features are occluded, along with other ‘in the wild’ variations. We call this data set the Celebrities in Frontal-Profile (CFP) data set. We find that human performance on Frontal-Profile verification in this data set is only slightly worse (94.57% accuracy) than that on Frontal-Frontal verification (96.24% accuracy). However we evaluated many state-of-the-art algorithms, including Fisher Vector, Sub-SML and a Deep learning algorithm. We observe that all of them degrade more than 10% from Frontal-Frontal to Frontal-Profile verification. The Deep learning implementation, which performs comparable to humans on Frontal-Frontal, performs significantly worse (84.91% accuracy) on Frontal-Profile. This suggests that there is a gap between human performance and automatic face recognition methods for large pose variation in unconstrained images.
618 citations
TL;DR: Experimental results show that the proposed framework can utilize large-scale noisy data to learn a Light model that is efficient in computational costs and storage spaces and achieves state-of-the-art results on various face benchmarks without fine-tuning.
Abstract: The volume of convolutional neural network (CNN) models proposed for face recognition has been continuously growing larger to better fit the large amount of training data. When training data are obtained from the Internet, the labels are likely to be ambiguous and inaccurate. This paper presents a Light CNN framework to learn a compact embedding on the large-scale face data with massive noisy labels. First, we introduce a variation of maxout activation, called max-feature-map (MFM), into each convolutional layer of CNN. Different from maxout activation that uses many feature maps to linearly approximate an arbitrary convex activation function, MFM does so via a competitive relationship. MFM can not only separate noisy and informative signals but also play the role of feature selection between two feature maps. Second, three networks are carefully designed to obtain better performance, meanwhile, reducing the number of parameters and computational costs. Finally, a semantic bootstrapping method is proposed to make the prediction of the networks more consistent with noisy labels. Experimental results show that the proposed framework can utilize large-scale noisy data to learn a Light model that is efficient in computational costs and storage spaces. The learned single network with a 256-D representation achieves state-of-the-art results on various face benchmarks without fine-tuning.
617 citations
TL;DR: Experimental results on the AR and FERET databases show that ESRC has better generalization ability than SRC for undersampled face recognition under variable expressions, illuminations, disguises, and ages.
Abstract: Sparse Representation-Based Classification (SRC) is a face recognition breakthrough in recent years which has successfully addressed the recognition problem with sufficient training images of each gallery subject. In this paper, we extend SRC to applications where there are very few, or even a single, training images per subject. Assuming that the intraclass variations of one subject can be approximated by a sparse linear combination of those of other subjects, Extended Sparse Representation-Based Classifier (ESRC) applies an auxiliary intraclass variant dictionary to represent the possible variation between the training and testing images. The dictionary atoms typically represent intraclass sample differences computed from either the gallery faces themselves or the generic faces that are outside the gallery. Experimental results on the AR and FERET databases show that ESRC has better generalization ability than SRC for undersampled face recognition under variable expressions, illuminations, disguises, and ages. The superior results of ESRC suggest that if the dictionary is properly constructed, SRC algorithms can generalize well to the large-scale face recognition problem, even with a single training image per class.
577 citations
19 Oct 2017
TL;DR: In this article, the authors identify and study four issues related to normalization through mathematical analysis, and propose two strategies for training using normalized features, one modification of softmax loss, which optimizes cosine similarity instead of inner-product, and another reformulation of metric learning by introducing an agent vector for each class.
Abstract: Thanks to the recent developments of Convolutional Neural Networks, the performance of face verification methods has increased rapidly. In a typical face verification method, feature normalization is a critical step for boosting performance. This motivates us to introduce and study the effect of normalization during training. But we find this is non-trivial, despite normalization being differentiable. We identify and study four issues related to normalization through mathematical analysis, which yields understanding and helps with parameter settings. Based on this analysis we propose two strategies for training using normalized features. The first is a modification of softmax loss, which optimizes cosine similarity instead of inner-product. The second is a reformulation of metric learning by introducing an agent vector for each class. We show that both strategies, and small variants, consistently improve performance by between 0.2% to 0.4% on the LFW dataset based on two models. This is significant because the performance of the two models on LFW dataset is close to saturation at over 98%.
558 citations