Face Photo-Sketch Synthesis and Recognition

By Amit R.Sharma, Prakash.R.Devale Prakash.R.Devale. 2012

731 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9f87e3212ab1d89c5d46924c925d6bb1da02f92b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

DualGAN: Unsupervised Dual Learning for Image-to-Image Translation (2017, methodology): “To compare DualGAN with GAN and cGAN [4], four labeled datasets are used: PHOTO-SKETCH [22, 25], DAY-NIGHT [5], LABEL-FACADES [20], and AERIALMAPS, which was directly captured from Google Map [4].”
Sketch Me That Shoe (2016, methodology): “For specific domains such as face, large-scale datasets exist such as the CUHK Face Sketches [30].”
Few-shot Image Generation via Cross-domain Correspondence (2021, background): “We explore adaptation to the following target domains: (i) face caricatures, (ii) face sketches [31], (iii) face paintings by Amedeo Modigliani [36], (iv) FFHQ-babies, (v) FFHQ-sunglasses, (vi) landscape drawings, (vii) haunted houses, (viii) Van Gogh’s house paintings, (ix) wrecked/abandoned cars.”
Heterogeneous Face Recognition Using Kernel Prototype Similarities (2013, background): “The motivation behind heterogeneous face recognition is that circumstances exist in which only a particular modality of a face image is available for querying a large database of mug shots (visible band face images).”
Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition (2017, methodology): “methods were first used in face photo-sketch synthesis and recognition [25], with [26] transforming a face image from one modality to another based on facial analogies and [27] synthesizing a face photo from a pseudo-sketch by using multi-scale Markov random fields.”
A Comprehensive Survey to Face Hallucination (2013, methodology): “…al. (2005) FERET, AR (Martinez and Benavente 1998), Cohn Kanade (Kanade et al. 2000), PIE (Sim et al. 2002) BI(GP) VP N/A Wang and Tang (2009) CUFS (Wang and Tang 2009) BI(MRF) VP FR Liu et al. (2001) FERET, AR BI(MRF) VP N/A Gao et al. (2008b,c) (Gao et al. 2008b,c) BI(E-HMM) VP UIQI, FR Park and…”
Coupled information-theoretic encoding for face photo-sketch recognition (2011, methodology): “We test our method with the same conﬁguration of training and testing splits as [31, 14].”
The CASIA NIR-VIS 2.0 Face Database (2013, methodology): “To our knowledge, there are five existing heterogeneous face databases: CUHK Face Sketch Database (CUFS) [16], CUHK Face Sketch FERET Database (CUFSF) [21], MSU Forensic Sketch Database [4], CASIA HFB Database (HFB) [7], and Long Distance Heterogeneous Face Database (LDHF-DB) [12].”
Sparse Modeling for Image and Vision Processing (2014, methodology): “Wright et al. [2009] have indeed proposed a state-ofthe-art classifier for this task; as we will see, however, even though it was first evaluated on face datasets, the classifier is generic and can be applied to other modalities. More specifically, let us first consider a set of training signals fro”
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation (2020, methodology): “Dataset Construction There are several datasets such as the CUHK face sketch database [43, 47] that are commonly used for the task of sketch-to-image synthesis.”
Visual Domain Adaptation: A survey of recent advances (2015, background): “(d) [91], [102], [103]. from labeled data in a related domain when learning a classifier for unseen data.”
SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis (2018, background): “There is also the CUHK Face Sketches [57] containing 606 face sketches drawn by artists.”
Scribbler: Controlling Deep Image Synthesis with Sketch and Color (2016, methodology): “• CUHK Finally, we add the CUHK dataset, which contains 188 hand-drawn portrait sketches and their corresponding photos [47].”
Cali-Sketch: Stroke Calibration and Completion for High-Quality Face Image Generation from Poorly-Drawn Sketches (2019, methodology): “Figure 5 are illustration of well-drawn sketches from [53].”
Face Recognition Vendor Test (FRVT) Performance of Face Identification Algorithms NIST IR 8009 (2014, background): “” The data was collected to support research into synthesis and recognition of sketches [25, 28].”
Deep Learning Identity-Preserving Face Space (2013, methodology): “In the future work, we will extend the framework to deal with robust face recognition in other difficult conditions such as expression change and face sketch recognition [25, 30], and will combine FIP features with more classic face recognition approaches to further improve the performance [28, 29, ”