Face Sketch Synthesis From a Single Photo–Sketch Pair

Zhang, Shengchuan; Gao, Xinbo; Wang, Nannan; Li, Jie

doi:10.1109/tcsvt.2015.2511482

Cited by 28 publications

(6 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An experiment using a large set of surveillance cameras monitoring metro turnstiles was conducted in order to evaluate face capture and attribute-based person identification [45], [174]. Facial sketches were investigated as helpful data to be added to the short-term watchlists [193], [192]. Authentication and risk assessment are also mandatory mechanisms in the smart home [27], [39] and smart city [132].…”

Section: Frontiers In Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

Emerging Biometrics: Deep Inference and Other Computational Intelligence

Yanushkevich,

Eastwood,

Lai

et al. 2020

Preprint

View full text Add to dashboard Cite

This paper aims at identifying emerging computational intelligence trends for the design and modeling of complex biometric-enabled infrastructure and systems. Biometric-enabled systems are evolving towards deep learning and deep inference using the principles of adaptive computing, -the front tides of the modern computational intelligence domain. Therefore, we focus on intelligent inference engines widely deployed in biometrics. Computational intelligence applications that cover a wide spectrum of biometric tasks using physiological and behavioral traits are chosen for illustration. We highlight the technology gaps that must be addressed in future generations of biometric systems. The reported approaches and results primarily address the researchers who work towards developing the next generation of intelligent biometric-enabled systems.

show abstract

Section: Frontiers In Applicationsmentioning

confidence: 99%

“…Facial sketches: This is a particular case of synthetic facial images. Survey [175], as well as papers [193], [192], provide a necessary platform for facial sketch techniques. A synthesizer that explores the differences in visible face images and thermal images was proposed in [128].…”

Section: Affect Analyzers A)mentioning

confidence: 99%

Emerging Biometrics: Deep Inference and Other Computational Intelligence

Yanushkevich,

Eastwood,

Lai

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…For instance, Song et al [35] present the Bidirectional Transformation Network (BTN), which generates a whole face/sketch recursively by using a small number of facial patches. Zhang et al [50] propose to integrate a Sparse Representation-based Greedy Search (SRGS) and Bayesian Inference (BI) for face sketch synthesis. However, all of these works focus on the face-to-sketch-translation task, but they could not generate sketches conditioned on external facial attributes.…”

Section: Related Workmentioning

confidence: 99%

“…Face-to-sketch translation is quite challenging due to the fact that it is a non-linear process conditioned on the appearance of the input face. To address this problem, several methods have been proposed [35], [47], [50], [44], [15] for image-to-image translation problems which convert a photo to a sketch. However, these works focus only on the faceto-sketch-translation ignoring the possibility of using facial Fig.…”

Section: Introductionmentioning

confidence: 99%

Attribute-Guided Sketch Generation

Tang

Chen

Wang

et al. 2019

2019 14th IEEE International Conference on Automatic Face &Amp; Gesture Recognition (FG 2019)

View full text Add to dashboard Cite

Facial attributes are important since they provide a detailed description and determine the visual appearance of human faces. In this paper, we aim at converting a face image to a sketch while simultaneously generating facial attributes. To this end, we propose a novel Attribute-Guided Sketch Generative Adversarial Network (ASGAN) which is an endto-end framework and contains two pairs of generators and discriminators, one of which is used to generate faces with attributes while the other one is employed for image-to-sketch translation. The two generators form a W-shaped network (Wnet) and they are trained jointly with a weight-sharing constraint. Additionally, we also propose two novel discriminators, the residual one focusing on attribute generation and the triplex one helping to generate realistic looking sketches. To validate our model, we have created a new large dataset with 8,804 images, named the Attribute Face Photo & Sketch (AFPS) dataset which is the first dataset containing attributes associated to face sketch images. The experimental results demonstrate that the proposed network (i) generates more photo-realistic faces with sharper facial attributes than baselines and (ii) has good generalization capability on different generative tasks.

show abstract

“…Subsequently, they utilized support vector regression to learn the high frequency relationship between the photo and sketch patch pairs with the aim of compensating the missing details in the pre-synthesized sketch, assuming that the sparse codes in both modalities are same. Likewise, Zhang et al [24] presented a sparse representation method incorporated into Bayesian interference for face sketch synthesis. In the same context, Wang et al [25] proposed a Model-Driven (MD) face sketch synthesis method based on linear regression to learn the mapping between the photo and sketch modalities, intentionally for fast synthesis performance.…”

Section: Introductionmentioning

confidence: 99%

A Superpixel-Wise Approach for Face Sketch Synthesis

Radman

Suandi

2019

IEEE Access

View full text Add to dashboard Cite

Face sketch synthesis from an input photo has drawn great attention in law enforcement and digital entertainment applications. Currently, the input photo is simply divided into overlapped rectangular patches and transformed to a sketch through weighted average of corresponding sketch patches. However, the regular patches lead to defects in the structure of synthesized sketch. In addition, existing methods need to cross the whole training dataset in order to collect the corresponding sketch patches, which limits their usability with the big training datasets. In this paper, a superpixel-wise approach based on the Superpixel technique incorporated into the Locality-constraint Linear Coding (LLC), termed as SuperLLC, is proposed to enhance the facial structure of synthesized sketch and simultaneously maintain fixed computational complexity regardless of the training dataset size. First, the input photo is segmented into overlapped superpixels to find their corresponding sketch superpixels from the training dataset. The LLC is then imposed to regularize proper weights to reconstruct the target sketch from these sketch superpixels, with averaging the overlapped areas between adjacent superpixels. But before all these, for each input photo, a sub-training set is selected based on facial landmarks distance between the input photo and the training photos set. This insures a steady synthesis process. Both subjective and objective experiments on public face sketch databases are finally carried out to reveal the superior performance of the proposed SuperLLC method compared to state-of-the-art methods.

show abstract

Face Sketch Synthesis From a Single Photo–Sketch Pair

Cited by 28 publications

References 30 publications

Emerging Biometrics: Deep Inference and Other Computational Intelligence

Emerging Biometrics: Deep Inference and Other Computational Intelligence

Attribute-Guided Sketch Generation

A Superpixel-Wise Approach for Face Sketch Synthesis

Contact Info

Product

Resources

About