A Comparative Study on Face Sketch Synthesis

Akram, Adeel; Wang, Nannan; Li, Jie; Gao, Xinbo

doi:10.1109/access.2018.2852709

Cited by 11 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For sketch-matching method, we adopt nullspace linear discriminant analysis (NLDA) [43] as the basic recognition technique. The comparison results for sketch-matching are shown in Table 5, therein referring to [14], who uses the same training protocols as our experiment. Meanwhile, Zhang et al…”

Section: Comparisons To Other Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Identity-aware CycleGAN for face photo-sketch synthesis and recognition

Fang

Deng

et al. 2020

Pattern Recognition

View full text Add to dashboard Cite

Face photo-sketch synthesis and recognition has many applications in digital entertainment and law enforcement. Recently, generative adversarial networks (GANs) based methods have significantly improved the quality of image synthesis, but they have not explicitly considered the purpose of recognition. In this paper, we first propose an Identity-Aware CycleGAN (IACycleGAN) model that applies a new perceptual loss to supervise the image generation network. It improves CycleGAN on photo-sketch synthesis by paying more attention to the synthesis of key facial regions, such as eyes and nose, which are important for identity recognition. Furthermore, we de-* Corresponding author.

show abstract

Section: Comparisons To Other Methodsmentioning

confidence: 99%

“…Existing FPSS approaches can be classified into 4 categories [2]: subspace learning, sparse representation, Bayesian inference and deep-learning-based methods, where the former three categories belong to data-driven method, and the last one belongs to model-driven method [14].…”

Section: Face Photo-sketch Synthesismentioning

confidence: 99%

Identity-aware CycleGAN for face photo-sketch synthesis and recognition

Fang

Deng

et al. 2020

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…This model was called random sampling and locality constraint (RSLCR). Akram et al [43] carried out a comparative study of all basic methodologies of the exemplar-based approach as well as two newer methods of sketch synthesis, called FCN [44] and GAN [45], which are based on the convolutional neural network and generative adversarial networks, respectively. The last two works may be included among the pioneer efforts of "learning-based" algorithms of sketch synthesis.…”

Section: Related Workmentioning

confidence: 99%

A Decision Support System for Face Sketch Synthesis Using Deep Learning and Artificial Intelligence

Azhar

Sharif

Raza

et al. 2021

Sensors

View full text Add to dashboard Cite

The recent development in the area of IoT technologies is likely to be implemented extensively in the next decade. There is a great increase in the crime rate, and the handling officers are responsible for dealing with a broad range of cyber and Internet issues during investigation. IoT technologies are helpful in the identification of suspects, and few technologies are available that use IoT and deep learning together for face sketch synthesis. Convolutional neural networks (CNNs) and other constructs of deep learning have become major tools in recent approaches. A new-found architecture of the neural network is anticipated in this work. It is called Spiral-Net, which is a modified version of U-Net fto perform face sketch synthesis (the phase is known as the compiler network C here). Spiral-Net performs in combination with a pre-trained Vgg-19 network called the feature extractor F. It first identifies the top n matches from viewed sketches to a given photo. F is again used to formulate a feature map based on the cosine distance of a candidate sketch formed by C from the top n matches. A customized CNN configuration (called the discriminator D) then computes loss functions based on differences between the candidate sketch and the feature. Values of these loss functions alternately update C and F. The ensemble of these nets is trained and tested on selected datasets, including CUFS, CUFSF, and a part of the IIT photo–sketch dataset. Results of this modified U-Net are acquired by the legacy NLDA (1998) scheme of face recognition and its newer version, OpenBR (2013), which demonstrate an improvement of 5% compared with the current state of the art in its relevant domain.

show abstract

“…After applying the irregular neighborhoods in temporal domain, work in [6] enables a more general framework for dynamic element textures, from which we draw inspiration to pursue benefits of data-driven approaches for synthesizing dynamic contents in 2D animation. Besides, there are other interesting data driven synthesis methods offering the state-of-the-art results, but most of them aim at specific applications, such as cloth wrinkles [27], crowds [28], faces cartooning [29], [30] and learning basketball dribbling skills [31]. Therefore, we draw our inspiration from all the above investigations to pursue similar benefits of data-driven approaches for synthesizing dynamic contents in 2D animation, which tends to be more general and user friendly.…”

Section: B Data-driven Animation Synthesismentioning

confidence: 99%

Efficient PatchMatch-Based Synthesis for Cartoon Animation

Hao

Chen

2019

IEEE Access

View full text Add to dashboard Cite

Automating the production of 2D hand-drawn animations is a significant and interesting component in computer graphics and vision. However, traditional methods in animation production pipeline always use physically or geometrically based models which are consuming due to complicated and massive computations, reducing their practicability. In this paper, we propose an efficient data-driven approach to create hand-drawn animations in an automatic manner. The key idea is to employ a correspondence match-based random search process to extract the geometry samples and the global motion pattern in an input animation sequence and then to generate a new output sequence through a coarse-to-fine sample-based synthesis algorithm. Our experiments demonstrate that our method achieves good results with high quality and performance, producing a range of artistic effects that previously required disparate and professional techniques. INDEX TERMS Animation, data-driven approach, exemplar-based approach, motion tracking and synthesis, PatchMatch, sample based synthesis.

show abstract

A Comparative Study on Face Sketch Synthesis

Cited by 11 publications

References 21 publications

Identity-aware CycleGAN for face photo-sketch synthesis and recognition

Identity-aware CycleGAN for face photo-sketch synthesis and recognition

A Decision Support System for Face Sketch Synthesis Using Deep Learning and Artificial Intelligence

Efficient PatchMatch-Based Synthesis for Cartoon Animation

Contact Info

Product

Resources

About