Graph-based image completion using patch offsets and structure feature

2014 ◽  
Author(s):  
Weiwei Xue ◽  
Rong Zhang
Keyword(s):  
Image Completion ◽  
Structure Feature

An Answer Extraction Algorithm Based on Syntax Structure Feature Parsing and Classification

2009 ◽  
Vol 31 (4) ◽  
pp. 662-676 ◽  
Author(s):  
Bao-Shun HU ◽  
Da-Ling WANG ◽  
Ge YU ◽  
Ting MA
Keyword(s):  
Structure Feature ◽  
Answer Extraction ◽  
Extraction Algorithm

scholarly journals Structure-Feature based Graph Self-adaptive Pooling

2020 ◽  
Author(s):  
Liang Zhang ◽  
Xudong Wang ◽  
Hongsheng Li ◽  
Guangming Zhu ◽  
Peiyi Shen ◽  
...  
Keyword(s):  
Structure Feature ◽  
Feature Based ◽  
Self Adaptive

scholarly journals Chinese Character Image Completion Using a Generative Latent Variable Model

2021 ◽  
Vol 11 (2) ◽  
pp. 624
Author(s):  
In-su Jo ◽  
Dong-bin Choi ◽  
Young B. Park
Keyword(s):  
Latent Variable ◽  
Chinese Character ◽  
Image Inpainting ◽  
Latent Variable Model ◽  
Chinese Characters ◽  
Image Completion ◽  
Variable Model ◽  
Variational Autoencoder ◽  
Convolution Model ◽  
Detection Technologies

Chinese characters in ancient books have many corrupted characters, and there are cases in which objects are mixed in the process of extracting the characters into images. To use this incomplete image as accurate data, we use image completion technology, which removes unnecessary objects and restores corrupted images. In this paper, we propose a variational autoencoder with classification (VAE-C) model. This model is characterized by using classification areas and a class activation map (CAM). Through the classification area, the data distribution is disentangled, and then the node to be adjusted is tracked using CAM. Through the latent variable, with which the determined node value is reduced, an image from which unnecessary objects have been removed is created. The VAE-C model can be utilized not only to eliminate unnecessary objects but also to restore corrupted images. By comparing the performance of removing unnecessary objects with mask regions with convolutional neural networks (Mask R-CNN), one of the prevalent object detection technologies, and also comparing the image restoration performance with the partial convolution model (PConv) and the gated convolution model (GConv), which are image inpainting technologies, our model is proven to perform excellently in terms of removing objects and restoring corrupted areas.

Fragment-based image completion

2003 ◽  
Author(s):  
Iddo Drori ◽  
Daniel Cohen-Or ◽  
Hezy Yeshurun
Keyword(s):  
Image Completion

Multi-option image completion based on semantic matching image

Optik ◽  
2014 ◽  
Vol 125 (17) ◽  
pp. 4985-4989 ◽  
Author(s):  
Hao Wu ◽  
Zhenjiang Miao
Keyword(s):  
Semantic Matching ◽  
Image Completion

Electric Connecting Piece Cutting Blanking Punching Compound Die Design

2013 ◽  
Vol 706-708 ◽  
pp. 1327-1330
Author(s):  
Hong Yun Jiang
Keyword(s):  
Spare Parts ◽  
Die Design ◽  
Working Process ◽  
Structure Feature ◽  
Stamping Process

It analyses the electric meeting slice parts stamping process, introduces all kinds of process’s feature and points out using the piece cutting blanking punching compound to form one time with the features of these spare parts. At the same time, it introduces the mold’s structure feature and the working process, and introduces the design of punch, bump mode, incision of the punch.

Sign in / Sign up

Export Citation Format

Share Document