Cross aging face recognition ability will decrease to recognize someone's face after a certain time. Adding synthetics face images at a certain age generated from face aging architecture is one way ...to increase the performance of cross aging face recognition. A synthetics face image can create use the Generative Adversarial Network-based architecture. The current Generative Adversarial Network-based in face aging still needs high computation to create a model. Based on that reason we proposed a new optimal variant of Identity Preserving Conditional Generative Adversarial Network (IPCGAN), to generate a synthetic face image at certain age groups. In the proposed architecture, change made at the structure in the generator module, age classification module, and change the objective function to increasing the accuracy performance when generates a realistic synthetic face image in certain age groups and also speed up the training time. Modification in the age classifier at the proposed network forces our architecture to generate better synthetics face in certain age groups. Evaluation using Facenet, and Age prediction shows our method accuracy has 4.2% better results in k-NN classification, 3.6% better accuracy results in SVM classification, 8.6% better accuracy result in age verification, and 4.5% fewer accuracy results in age prediction.
Face aging is an active area of research in multimedia applications that involves modifying a person’s facial photo to resemble their appearance at a different age. While conditional Generative ...Adversarial Networks (cGANs) have made significant progress in this field, most current approaches still face challenges in generating convincing age progression while preserving the subject’s identity. These limitations arise due to three main factors: i) a scarcity of long-range sequential labelled faces of the same person in existing datasets, which are required for training; ii) a focus on texture changes such as wrinkles, which neglects structural variations that are important in aging and limit the effectiveness of these models for large age spans; and iii) the tendency to preserve personal identity by minimizing the differences between inputs and synthesized results, which can result in blurry artifacts and insufficient variations. In this paper, we propose a novel approach to address these limitations called Landmark-guided Dual-learning cGAN (LDcGAN), which includes a multi-attention mechanism. Our approach uses an external landmark attention to adjust variations in facial structure and a built-in attention to emphasize the most discriminative regions relevant to aging. The primal cGAN is conditioned with age vectors and converts input faces to target ages, while the dual cGAN inverts the process by feeding the synthesized results back to the original input age range. This enables LDcGAN to improve age consistency and minimize changes that affect personal identity and background. Our approach demonstrates appealing results in terms of image quality, personal identity, and age accuracy, as confirmed by both qualitative and quantitative experiments.
Modeling the aging process of human faces is important for cross-age face verification and recognition. In this paper, we propose a Recurrent Face Aging (RFA) framework which takes as input a single ...image and automatically outputs a series of aged faces. The hidden units in the RFA are connected autoregressively allowing the framework to age the person by referring to the previous aged faces. Due to the lack of labeled face data of the same person captured in a long range of ages, traditional face aging models split the ages into discrete groups and learn a one-step face transformation for each pair of adjacent age groups. Since human face aging is a smooth progression, it is more appropriate to age the face by going through smooth transitional states. In this way, the intermediate aged faces between the age groups can be generated. Towards this target, we employ a recurrent neural network whose recurrent module is a hierarchical triple-layer gated recurrent unit which functions as an autoencoder. The bottom layer of the module encodes the input to a latent representation, and the top layer decodes the representation to a corresponding aged face. The experimental results demonstrate the effectiveness of our framework.
Face aging is a task which referred to image synthesis, and the challenge comes from the training dataset, most existing face aging works require paired face images which is difficult to collect. ...Face images with various ages of the same person can be considered as unpaired images which come from different domains. The degree of aging effect can be influenced by age, gender, race and some other factors. In this paper, we are committed to studying the impact of gender on face aging problem, which involves the processing and modeling of face images.
It has been proved that Generative Adversarial Networks(GANs) is competitive in realistic image synthesis, and many works employed Cycle-Consistent Adversarial Networks(CycleGANs) have shown the high performance in unpaired image-to-image translation.
To overcome current difficulties and improve the performance of existing models on the face aging tasks, we proposed an innovative Gender-based training method using CycleGAN by pairwise training CycleGAN over several age groups which are grouped by age and gender. We build a constraint model based on gender discrimination to better simulate the expected aging effect of face images.
To evaluate our works using subjective method, we have set up a quantitative evaluation mechanism with participants involved in. Compared with other similar subjective evaluation methods, our method is more objective in the demonstration of experimental results. The experimental results show that our method has a more realistic and excellent performance compared to those using CycleGAN for face age synthesis directly.
•Explains the challenges in the existing face aging problem and proposes solutions.•A gender-constrained model is proposed that does not require paired data.•Put forward a persuasive experimental evaluation method.•Improved the performance of the current face aging model.
A Compositional and Dynamic Model for Face Aging JINLI SUO; ZHU, Song-Chun; SHIGUANG SHAN ...
IEEE transactions on pattern analysis and machine intelligence,
03/2010, Letnik:
32, Številka:
3
Journal Article
Recenzirano
Odprti dostop
In this paper, we present a compositional and dynamic model for face aging. The compositional model represents faces in each age group by a hierarchical And-or graph, in which And nodes decompose a ...face into parts to describe details (e.g., hair, wrinkles, etc.) crucial for age perception and Or nodes represent large diversity of faces by alternative selections. Then a face instance is a transverse of the And-or graph-parse graph. Face aging is modeled as a Markov process on the parse graph representation. We learn the parameters of the dynamic model from a large annotated face data set and the stochasticity of face aging is modeled in the dynamics explicitly. Based on this model, we propose a face aging simulation and prediction algorithm. Inversely, an automatic age estimation algorithm is also developed under this representation. We study two criteria to evaluate the aging results using human perception experiments: (1) the accuracy of simulation: whether the aged faces are perceived of the intended age group, and (2) preservation of identity: whether the aged faces are perceived as the same person. Quantitative statistical analysis validates the performance of our aging model and age estimation algorithm.
•A simple but effective method for face sketch aging via PCA is proposed.•The method skips the time consuming process of collecting sketch aging sequences.•The method utilizes the photo aging ...sequences to conduct face sketch aging problem.•Performance of the proposed method is promising.
Display omitted
Face sketch aging (FSA) simulation has many practical applications. Most of researchers devote themselves into face photo aging problem. There are few works about face sketch aging. In this manuscript, a simple but effective method for face sketch aging is proposed. We assume that the aging principle of face sketch and photo is the same in the proposed method. Face sketches to be aged are first projected into the space spanned by aging photos via principal component analysis (PCA). Then the obtained coefficients of face sketches are evolved according to the regular of coefficients of aging photos. Finally, aged face sketches can by generated from evolved coefficients with PCA. The proposed method escapes the process of collecting sketch aging sequences elegantly. Experimental results validate that the proposed method is effective and promising.
A Concatenational Graph Evolution Aging Model Suo, Jinli; Chen, Xilin; Shan, Shiguang ...
IEEE transactions on pattern analysis and machine intelligence,
11/2012, Letnik:
34, Številka:
11
Journal Article
Recenzirano
Modeling the long-term face aging process is of great importance for face recognition and animation, but there is a lack of sufficient long-term face aging sequences for model learning. To address ...this problem, we propose a CONcatenational GRaph Evolution (CONGRE) aging model, which adopts decomposition strategy in both spatial and temporal aspects to learn long-term aging patterns from partially dense aging databases. In spatial aspect, we build a graphical face representation, in which a human face is decomposed into mutually interrelated subregions under anatomical guidance. In temporal aspect, the long-term evolution of the above graphical representation is then modeled by connecting sequential short-term patterns following the Markov property of aging process under smoothness constraints between neighboring short-term patterns and consistency constraints among subregions. The proposed model also considers the diversity of face aging by proposing probabilistic concatenation strategy between short-term patterns and applying scholastic sampling in aging prediction. In experiments, the aging prediction results generated by the learned aging models are evaluated both subjectively and objectively to validate the proposed model.
Face aging with pixel-level alignment GAN Wu, Xing; Zhang, Yafei; Li, Qing ...
Applied intelligence (Dordrecht, Netherlands),
10/2022, Letnik:
52, Številka:
13
Journal Article
Recenzirano
Face aging is of great significance in cross-time identity verification problem. However, there is still a huge gap between the synthesized face image and the real face in terms of quality and ...consistency due to identity ambiguity and image distortion caused by existing face aging methods. To meet this challenge, we propose a face aging framework named as Pixel-level Alignment GAN, PAGAN, to synthesize faces of different age groups. Face images are featured by age, identity, and fine-grained pixel-value to ensure the quality, which is a typical multi-task learning problem. The proposed face aging framework with PAGAN is a combination of age estimation, identity preservation, and image de-noising. Extensive experiments demonstrate that the proposed method outperforms state-of-the-art methods not only in the accuracy of age classification but also in the image quality. With the proposed PAGAN, the face recognition accuracy with synthesized images has increased 0.21% and the image quality rating has increased around 5%, which proves the effectiveness and validity of proposed method.
•We propose a 3D model to simulate faces at younger age.•We propose a Generic Perception Based Mode to evaluate the results.•We show that proposed 3D model improves the verification performances.
...Face aging has been widely considered in many studies regarding all the potential applications. However, the de-aging known as the rejuvenation or backward modeling has recently received more attention. Previous studies mainly focused on rejuvenating faces from aged adults into young adults using two-dimensional (2D) models. In this work, we propose an extension of a previous 2D adult-child B-FAM into 3D model. This model allows a digital face appearance rejuvenation within a range of 75–3 years old. To evaluate the performances of the proposed approach, first, we proposed two performance evaluation modes, namely: Generic Perception Based and Biometric Verification Mode. Then, the performances have been evaluated over our own 3D database, called Face Time-Machine database constructed using 75 females and 70 males, leading to 500 textured surface meshes. Finally, results show that they are perceptually satisfying and system performance increases by using the faces obtained from our model.