scholarly journals A Joint Training Model for Face Sketch Synthesis

2019 ◽  
Vol 9 (9) ◽  
pp. 1731 ◽  
Author(s):  
Weiguo Wan ◽  
Hyo Jong Lee
Keyword(s):  
Sampling Strategy ◽  
Training Model ◽  
Objective Evaluation ◽  
Synthesis Methods ◽  
Locality Constraint ◽  
Joint Training ◽  
Sketch Synthesis ◽  
Face Sketch Synthesis ◽  
Public Datasets ◽  
High Pass

The exemplar-based method is most frequently used in face sketch synthesis because of its efficiency in representing the nonlinear mapping between face photos and sketches. However, the sketches synthesized by existing exemplar-based methods suffer from block artifacts and blur effects. In addition, most exemplar-based methods ignore the training sketches in the weight representation process. To improve synthesis performance, a novel joint training model is proposed in this paper, taking sketches into consideration. First, we construct the joint training photo and sketch by concatenating the original photo and its sketch with a high-pass filtered image of their corresponding sketch. Then, an offline random sampling strategy is adopted for each test photo patch to select the joint training photo and sketch patches in the neighboring region. Finally, a novel locality constraint is designed to calculate the reconstruction weight, allowing the synthesized sketches to have more detailed information. Extensive experimental results on public datasets show the superiority of the proposed joint training model, both from subjective perceptual and the FaceNet-based face recognition objective evaluation, compared to existing state-of-the-art sketch synthesis methods.

scholarly journals Fast Preprocessing for Robust Face Sketch Synthesis

2017 ◽  
Author(s):  
Yibing Song ◽  
Jiawei Zhang ◽  
Linchao Bao ◽  
Qingxiong Yang
Keyword(s):  
State Of The Art ◽  
Computational Cost ◽  
Intensity Difference ◽  
Synthesis Methods ◽  
Local Contrast ◽  
Challenging Problem ◽  
Pixel Intensity ◽  
Lighting Conditions ◽  
Sketch Synthesis ◽  
Face Sketch Synthesis

Exemplar-based face sketch synthesis methods usually meet the challenging problem that input photos are captured in different lighting conditions from training photos. The critical step causing the failure is the search of similar patch candidates for an input photo patch. Conventional illumination invariant patch distances are adopted rather than directly relying on pixel intensity difference, but they will fail when local contrast within a patch changes. In this paper, we propose a fast preprocessing method named Bidirectional Luminance Remapping (BLR), which interactively adjust the lighting of training and input photos. Our method can be directly integrated into state-of-the-art exemplar-based methods to improve their robustness with ignorable computational cost

Face sketch synthesis: a survey

2021 ◽  
Author(s):  
Hongbo Bi ◽  
Ziqi Liu ◽  
Lina Yang ◽  
Kang Wang ◽  
Ning Li
Keyword(s):  
Sketch Synthesis ◽  
Face Sketch Synthesis

scholarly journals Generative adversarial learning for detail-preserving face sketch synthesis

2021 ◽  
Vol 438 ◽  
pp. 107-121
Author(s):  
Weiguo Wan ◽  
Yong Yang ◽  
Hyo Jong Lee
Keyword(s):  
Adversarial Learning ◽  
Sketch Synthesis ◽  
Face Sketch Synthesis

scholarly journals JOINT TRAINING MODEL FOR ENHANCING COMPETENCY OF APPARATUS IN PROVINCE GOVERNMENT OF MITRA PRAJA UTAMA

2018 ◽  
Vol 2 (2) ◽  
pp. 104-117
Author(s):  
Hari Soesanto
Keyword(s):  
Local Government ◽  
Local Governments ◽  
Regional Cooperation ◽  
Training Model ◽  
Regional Government ◽  
Civil State ◽  
Central Java ◽  
State Apparatus ◽  
Joint Training ◽  
Training Institutions

ABSTRAK Penelitian atau kajian mengenai pelatihan bagi para aparatur sipil negara sudah banyak dilakukan, namun penelitian yang fokus pada pelatihan bagi aparatur yang bertugas pada pemerintah daerah Mitra Praja Utama masih sangat langka. Kajian ini menyajikan skema atau model alternatif peningkatan kompetensi aparatur sipil negara untuk meningkatkan kerjasama antar daerah melalui pelatihan bersama. Ruang lingkup pemerintah daerah yang menjadi kajian adalah pemerintah daerah yang tergabung dalam forum Mitra Praja Utama (MPU). MPU merupakan forum kerjasama dan koordinasi antar pemerintah daerah di Indonesia yang terdiri dari  10 Provinsi yaitu Provinsi Jawa Barat, Provinsi DKI Jakarta, Provinsi Jawa Tengah, Provinsi Daerah Istimewa Yogyakarta, Provinsi Jawa Timur, Provinsi Bali, Provinsi Lampung, Provinsi Nusa Tenggara Barat, Provinsi Banten dan Provinsi Nusa Tengggara Timur. Model pelatihan bersama yang disajikan pada kajian ini merupakan suatu alternatif metode yang dapat dipertimbangkan oleh lembaga diklat pemerintah, khususnya pada lembaga diklat pemerintah yang tergabung dalam Mitra Praja Utama dalam rangka peningkatan kerjasama antar daerah untuk berbagai urusan pemerintahan daerah terutama dari aspek kompetensi aparatur.   Kata kunci: pelatihan, mitra praja utama, kompetensi, aparatur sipil negara     ABSTRACT Research or studies on training for the state civil apparatus have been carried out a lot, but research that focuses on training for officers serving in the Mitra Praja Utama regional government is still very rare. This study presents an alternative model for enhancing the competence of civil state apparatus to increase cooperation among regions through joint training. The scope of local government to be studied is the local government who are members of the forum Mitra Praja Utama (MPU). MPU is a forum of cooperation and coordination among local governments in Indonesia consisting of 10 Provinces of West Java Province, DKI Jakarta Province, Central Java Province, Special Province of Yogyakarta, East Java Province, Bali Province, Lampung Province, West Nusa Tenggara Province, Banten Province and East Nusa Tenggara Province. The joint training model presented in this study is an alternative method that can be ascertained by special government training institutions in government training institutions incorporated in Mitra Praja Utama in order to increase inter-regional cooperation for various local government affairs.   Keywords: training, mitra praja utama, competence, civil state apparatus  

scholarly journals Dense U-net Based on Patch-Based Learning for Retinal Vessel Segmentation

Entropy ◽  
2019 ◽  
Vol 21 (2) ◽  
pp. 168 ◽  
Author(s):  
Chang Wang ◽  
Zongya Zhao ◽  
Qiongqiong Ren ◽  
Yongtao Xu ◽  
Yi Yu
Keyword(s):  
Data Augmentation ◽  
Learning Strategy ◽  
Retinal Vessel ◽  
Semantic Segmentation ◽  
Training Model ◽  
Vessel Segmentation ◽  
Evaluation Metrics ◽  
Segmentation Result ◽  
Retinal Vessel Segmentation ◽  
Public Datasets

Various retinal vessel segmentation methods based on convolutional neural networks were proposed recently, and Dense U-net as a new semantic segmentation network was successfully applied to scene segmentation. Retinal vessel is tiny, and the features of retinal vessel can be learned effectively by the patch-based learning strategy. In this study, we proposed a new retinal vessel segmentation framework based on Dense U-net and the patch-based learning strategy. In the process of training, training patches were obtained by random extraction strategy, Dense U-net was adopted as a training network, and random transformation was used as a data augmentation strategy. In the process of testing, test images were divided into image patches, test patches were predicted by training model, and the segmentation result can be reconstructed by overlapping-patches sequential reconstruction strategy. This proposed method was applied to public datasets DRIVE and STARE, and retinal vessel segmentation was performed. Sensitivity (Se), specificity (Sp), accuracy (Acc), and area under each curve (AUC) were adopted as evaluation metrics to verify the effectiveness of proposed method. Compared with state-of-the-art methods including the unsupervised, supervised, and convolutional neural network (CNN) methods, the result demonstrated that our approach is competitive in these evaluation metrics. This method can obtain a better segmentation result than specialists, and has clinical application value.

Sign in / Sign up

Export Citation Format

Share Document