Face image assessment learned with objective and relative face image qualities for improved face recognition

Kim, Hyung-Il; Lee, Seol‐Hoon; Ro, Yong Man

doi:10.1109/icip.2015.7351562

Cited by 41 publications

(18 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They use a ranking loss computed on multiple face images of an identity to train a network. Kim et al [15] take advantage of two factors, including visual quality and mismatch degree between training and testing images to predict face image quality. However, these methods can only work well with face images under controlled conditions.…”

Section: Learning-based Fiqamentioning

confidence: 99%

SDD-FIQA: Unsupervised Face Image Quality Assessment with Similarity Distribution Distance

Ou¹,

Chen²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

In recent years, Face Image Quality Assessment (FIQA) has become an indispensable part of the face recognition system to guarantee the stability and reliability of recognition performance in an unconstrained scenario. For this purpose, the FIQA method should consider both the intrinsic property and the recognizability of the face image. Most previous works aim to estimate the sample-wise embedding uncertainty or pair-wise similarity as the quality score, which only considers the information from partial intra-class. However, these methods ignore the valuable information from the inter-class, which is for estimating to the recognizability of face image. In this work, we argue that a high-quality face image should be similar to its intra-class samples and dissimilar to its inter-class samples. Thus, we propose a novel unsupervised FIQA method that incorporates Similarity Distribution Distance for Face Image Quality Assessment (SDD-FIQA). Our method generates quality pseudo-labels by calculating the Wasserstein Distance (WD) between the intra-class similarity distributions and inter-class similarity distributions. With these quality pseudo-labels, we are capable of training a regression network for quality prediction. Extensive experiments on benchmark datasets demonstrate that the proposed SDD-FIQA surpasses the state-of-the-arts by an impressive margin. Meanwhile, our method shows good generalization across different recognition systems.

show abstract

Section: Learning-based Fiqamentioning

confidence: 99%

SDD-FIQA: Unsupervised Face Image Quality Assessment with Similarity Distribution Distance

Ou¹,

Chen²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Sang et al [28] also evaluated symmetry through illumination and pose based on a Gabor filter and measured blur by a discrete cosine transform (DCT) and inverse DCT. In the literature [29], researchers have employed DCT to evaluate sharpness. Nasrollahi et al [30] utilized the least out-of-plane rotated (LOPR) faces method to evaluate posture.…”

Section: Related Workmentioning

confidence: 99%

Sharpness and Brightness Quality Assessment of Face Images for Recognition

Chen

Huang

et al. 2021

Scientific Programming

View full text Add to dashboard Cite

Face image quality has an important effect on recognition performance. Recognition-oriented face image quality assessment is particularly necessary for the screening or application of face images with various qualities. In this work, sharpness and brightness were mainly assessed by a classification model. We selected very high-quality images of each subject and established nine kinds of quality labels that are related to recognition performance by utilizing a combination of face recognition algorithms, the human vision system, and a traditional brightness calculation method. Experiments were conducted on a custom dataset and the CMU multi-PIE face database for training and testing and on Labeled Faces in the Wild for cross-validation. The experimental results show that the proposed method can effectively reduce the false nonmatch rate by removing the low-quality face images identified by the classification model and vice versa. This method is even effective for face recognition algorithms that are not involved in label creation and whose training data are nonhomologous to the training set of our quality assessment model. The results show that the proposed method can distinguish images of different qualities with reasonable accuracy and is consistent with subjective human evaluation. The quality labels established in this paper are closely related to the recognition performance and exhibit good generalization to other recognition algorithms. Our method can be used to reject low-quality images to improve the recognition rate and screen high-quality images for subsequent processing.

show abstract

“…In the recent literature, learning-based approaches start getting popular, e.g. [3,4,14,23,30,5,39,10,24,8,21,35]. See [8,35] for an excellent extended literature review.…”

Section: Related Workmentioning

confidence: 99%

Inducing Predictive Uncertainty Estimation for Face Recognition

Xie,

Byrne,

Zisserman

2020

Preprint

View full text Add to dashboard Cite

Knowing when an output can be trusted is critical for reliably using face recognition systems. While there has been enormous effort in recent research on improving face verification performance, understanding when a model's predictions should or should not be trusted has received far less attention. Our goal is to assign a confidence score for a face image that reflects its quality in terms of recognizable information. To this end, we propose a method for generating image quality training data automatically from 'mated-pairs' of face images, and use the generated data to train a lightweight Predictive Confidence Network, termed as PCNet, for estimating the confidence score of a face image. We systematically evaluate the usefulness of PCNet with its error versus reject performance, and demonstrate that it can be universally paired with and improve the robustness of any verification model. We describe three use cases on the public IJB-C face verification benchmark: (i) to improve 1:1 image-based verification error rates by rejecting low-quality face images; (ii) to improve quality score based fusion performance on the 1:1 set-based verification benchmark; and (iii) its use as a quality measure for selecting high quality (unblurred, good lighting, more frontal) faces from a collection, e.g. for automatic enrolment or display.

show abstract

Face image assessment learned with objective and relative face image qualities for improved face recognition

Cited by 41 publications

References 15 publications

SDD-FIQA: Unsupervised Face Image Quality Assessment with Similarity Distribution Distance

SDD-FIQA: Unsupervised Face Image Quality Assessment with Similarity Distribution Distance

Sharpness and Brightness Quality Assessment of Face Images for Recognition

Inducing Predictive Uncertainty Estimation for Face Recognition

Contact Info

Product

Resources

About