It has been recently shown that Generative Adversarial Networks (GANs) can produce synthetic images of exceptional visual fidelity. In this work, we propose the first GAN-based method for automatic ...face aging. Contrary to previous works employing GANs for altering of facial attributes, we make a particular emphasize on preserving the original person's identity in the aged version of his/her face. To this end, we introduce a novel approach for "Identity-Preserving" optimization of GAN's latent vectors. The objective evaluation of the resulting aged and rejuvenated face images by the state-of-the-art face recognition and age estimation solutions demonstrate the high potential of the proposed method.
•We build a novel network architecture of conditioned-attention normalization GAN (CAN-GAN) for age synthesis.•We design a new conditioned-attention normalization (CAN) to enhance the aging-relevant ...information by an attention map.•We extend a contribution-aware age classifier (CAAC) to improve the ability of discriminator.
This work aims to freely translate an input face to an aging face with robust identity preservation, satisfying aging effect and authentic visual appearance. Witnessing the success of GAN in image synthesis, researchers employ GAN to address the problem of face aging synthesis. However, most GAN-based methods hold that the aging changing of all facial regions is equal, which ignores the fact that different facial regions have distinct aging speeds and aging patterns. To this end, we propose a novel Conditioned-Attention Normalization GAN (CAN-GAN) for age synthesis by leveraging the aging difference between two age groups to capture facial aging regions with different attention factors. In particular, a new Conditioned-Attention Normalization (CAN) layer is designed to enhance the aging-relevant information of face, while smoothing the aging-irrelevant information of face by attention map. Since different facial attributes contribute to the discrimination of age groups with divers degrees, we further present a Contribution-Aware Age Classifier (CAAC) that finely measures the importance of face vector’s elements in terms of the age classification. Qualitative and quantitative experiments on several commonly-used datasets show the advance of CAN-GAN compared with the other competitive methods.
•This paper was written by scanning the literature extensively.•Face age synthesis is the determination of how a person looks in the future or in the past by reconstructing their facial ...image.•Determining the change in the human face over the years is a critical process for cross-age face recognition systems in forensic issues such as finding missing people and fugitive criminals.•With the implementation of deep learning methods, better quality and photo-realistic images began to be produced.•We group the studies in the literature under two categories: classical methods and deep learning methods.•We review both categories in the methods used, evaluation methods, and databases.
Face age synthesis is the determination of how a person looks in the future or the past by reconstructing their facial image. Determining the change in the human face over the years is a critical process for cross-age face recognition systems in forensic issues such as finding missing people and fugitive criminals. Therefore, it is a subject that has attracted attention in recent years. With the implementation of deep learning methods, better quality and photo-realistic images began to be produced. However, researchers continue to improve both aging accuracy and identity preservation requirements. We group the studies in the literature under two categories: classical methods and deep learning methods. We review both categories in the methods used, evaluation methods, and databases.
Learning Continuous Face Age Progression: A Pyramid of GANs Yang, Hongyu; Huang, Di; Wang, Yunhong ...
IEEE transactions on pattern analysis and machine intelligence,
2021-Feb.-1, 2021-Feb, 2021-2-1, 20210201, Letnik:
43, Številka:
2
Journal Article
Recenzirano
Odprti dostop
The two underlying requirements of face age progression, i.e., aging accuracy and identity permanence, are not well studied in the literature. This paper presents a novel generative adversarial ...network based approach to address the issues in a coupled manner. It separately models the constraints for the intrinsic subject-specific characteristics and the age-specific facial changes with respect to the elapsed time, ensuring that the generated faces present desired aging effects while keeping personalized properties stable. To render photo-realistic facial details, high-level age-specific features conveyed by the synthesized face are estimated by a pyramidal adversarial discriminator at multiple scales, which simulates the aging effects in a finer way. Further, an adversarial learning scheme is introduced to simultaneously train a single generator and multiple parallel discriminators, resulting in smooth continuous face aging sequences. The proposed method is applicable even in the presence of variations in pose, expression, makeup, etc., achieving remarkably vivid aging effects. Quantitative evaluations by a COTS face recognition system demonstrate that the target age distributions are accurately recovered, and 99.88 and 99.98 percent age progressed faces can be correctly verified at 0.001 percent FAR after age transformations of approximately 28 and 23 years elapsed time on the MORPH and CACD databases, respectively. Both visual and quantitative assessments show that the approach advances the state-of-the-art.
Face aging is to render a given face to predict its future appearance, which plays an important role in the information forensics and security field as the appearance of the face typically varies ...with age. Although impressive results have been achieved with conditional generative adversarial networks (cGANs), the existing cGANs-based methods typically use a single network to learn various aging effects between any two different age groups. However, they cannot simultaneously meet three essential requirements of face aging-including image quality, aging accuracy, and identity preservation-and usually generate aged faces with strong ghost artifacts when the age gap becomes large. Inspired by the fact that faces gradually age over time, this paper proposes a novel progressive face aging framework based on generative adversarial network (PFA-GAN) to mitigate these issues. Unlike the existing cGANs-based methods, the proposed framework contains several sub-networks to mimic the face aging process from young to old, each of which only learns some specific aging effects between two adjacent age groups. The proposed framework can be trained in an end-to-end manner to eliminate accumulative artifacts and blurriness. Moreover, this paper introduces an age estimation loss to take into account the age distribution for an improved aging accuracy, and proposes to use the Pearson correlation coefficient as an evaluation metric measuring the aging smoothness for face aging methods. Extensively experimental results demonstrate superior performance over existing (c)GANs-based methods, including the state-of-the-art one; e.g ., PFA-GAN reduces the aging estimation errors by 0.23 and 0.35 and increases the identity preservation rates by 0.49 and 0.63 on two benchmarked datasets compared to the second best method for the challenging face aging from 30− to 51+. The source code is available at https://github.com/Hzzone/PFA-GAN .
•We present a large-scale longitudinal Indian child dataset (ICD), to address face aging, cross-age face recognition, age estimation, and gender preservation in children.•ChildGAN, a new method for ...age-progression and rejuvenation, which can automatically generate visually realistic face photos, while attaining enhanced face-recognition, age-estimation, and gender-preservation rates, compared to state-of-the-art methods.•We also investigate the generalization of ChildGAN by presenting Multi-Racial Child Dataset (MRCD) containing 64,965 face images of four races (Asian, Black, White, and Indian).•An encoder and discriminator architecture, inspired by the self-attention GAN, which exhibits a better balance between the ability to model long-range dependencies and computational and statistical efficiency.•The model and the MRCD web crawled images are available at: https://github.com/praveenkumarchandaliya/ChildGAN_Tamp1.
Child-face aging and rejuvenation have amassed considerable active research interest, owing to their immense impact on a broad range of social and security applications, e.g., digital entertainment, fashion and wellness, and searching for long-lost children using childhood photos. All current face aging approaches based on generative adversarial networks (GANs) focus on adult images or long-term aging. We present a new large-scale longitudinal Indian child (ICD) benchmark dataset to facilitate face age progression and regression, cross-age face recognition, age estimation, gender prediction, and kinship face recognition to alleviate these issues. Furthermore, we propose an automatic child-face age progression and regression model, namely, ChildGAN, that generates visually realistic images for enhanced face-identification accuracy while preserving the identity. Consequently, we have trained state-of-the-art (SOTA) face aging models on ICD for comprehensive qualitative and quantitative evaluations. We also present a multi-racial experiments dataset named Multi-Racial Child Dataset (MRCD) containing 64,965 child face images. The images are selected from publicly available datasets and web crawling. Finally, we investigate the generalization of ChildGAN by experimenting with White, Black, Asian, and Indian races. The experimental results suggest that the proposed ChildGAN and SOTA models can aid in reconnecting young children, who were lost at a young age as victims of child trafficking or abduction, with their families. The model and the MRCD web crawled images are available at https://github.com/praveenkumarchandaliya/ChildGAN_Tamp1/.
Age Synthesis and Estimation via Faces: A Survey Yun Fu; Guodong Guo; Huang, T S
IEEE transactions on pattern analysis and machine intelligence,
11/2010, Letnik:
32, Številka:
11
Journal Article
Recenzirano
Human age, as an important personal trait, can be directly inferred by distinct patterns emerging from the facial appearance. Derived from rapid advances in computer graphics and machine vision, ...computer-based age synthesis and estimation via faces have become particularly prevalent topics recently because of their explosively emerging real-world applications, such as forensic art, electronic customer relationship management, security control and surveillance monitoring, biometrics, entertainment, and cosmetology. Age synthesis is defined to rerender a face image aesthetically with natural aging and rejuvenating effects on the individual face. Age estimation is defined to label a face image automatically with the exact age (year) or the age group (year range) of the individual face. Because of their particularity and complexity, both problems are attractive yet challenging to computer-based application system designers. Large efforts from both academia and industry have been devoted in the last a few decades. In this paper, we survey the complete state-of-the-art techniques in the face image-based age synthesis and estimation topics. Existing models, popular algorithms, system performances, technical difficulties, popular face aging databases, evaluation protocols, and promising future directions are also provided with systematic discussions.
Face aging tasks aim to simulate changes in the appearance of faces over time. However, due to the lack of data on different ages under the same identity, existing models are commonly trained using ...mapping between age groups. This makes it difficult for most existing aging methods to accurately capture the correspondence between individual identities and aging features, leading to generating faces that do not match the real aging appearance. In this paper, we re-annotate the CACD2000 dataset and propose a consensus-agent deep reinforcement learning method to solve the aforementioned problem. Specifically, we define two agents, the aging process agent and the aging personalization agent, and model the task of matching aging features as a Markov decision process. The aging process agent simulates the aging process of an individual, while the aging personalization agent calculates the difference between the aging appearance of an individual and the average aging appearance. The two agents iteratively adjust the matching degree between the target aging feature and the current identity through a form of synergistic cooperation. Extensive experimental results on four face aging datasets show that our model achieves convincing performance compared to the current state-of-the-art methods.
Face aging simulation has received rising investigations nowadays, whereas it still remains a challenge to generate convincing and natural age-progressed face images. In this paper, we present a ...novel approach to such an issue using hidden factor analysis joint sparse representation. In contrast to the majority of tasks in the literature that integrally handle the facial texture, the proposed aging approach separately models the person-specific facial properties that tend to be stable in a relatively long period and the age-specific clues that gradually change over time. It then transforms the age component to a target age group via sparse reconstruction, yielding aging effects, which is finally combined with the identity component to achieve the aged face. Experiments are carried out on three face aging databases, and the results achieved clearly demonstrate the effectiveness and robustness of the proposed method in rendering a face with aging effects. In addition, a series of evaluations prove its validity with respect to identity preservation and aging effect generation.
Face aging has received increasing attention from the computer vision community due to wide applications in the real world. Age accuracy and identity preserving are two important indicators for face ...aging. Previous works usually rely on an extra pre-trained module for identity preserving and multi-level discriminators for fine-grained features extraction. In this work, we propose a cycle-consistent loss based method for face aging with wavelet-based multi-level facial attributes extraction from both generator and discriminators. The proposed model consists of one generator with three-level encoders and three levels of discriminators with an age and a gender classifier on top of each discriminator. Experiment results on both MORPH and CACD show that the application of multi-level generator can improve the identity preserving effects in face aging and reduce the training time significantly by eliminating the rely of an identity preserving module. Our model can outperform most of the existing approaches include the state-of-the-art techniques on two benchmark aging databases in terms of both aging accuracy and identity verification confidence, demonstrating the effectiveness and superiority of our method.
•Wavelet-based multi-level generator was applied to face aging for the first time.•Time reduction for model training without a pretrained module for identity preserving.•Outperforms the state of the arts in both aging accuracy and identity preserving.•Our model can generate images with a continuous and smooth increase of age.