470 Hits in 5.1 sec

Separating Chinese Character from Noisy Background Using GAN

Bin Huang, Jiaqi Lin, Jinming Liu, Jie Chen, Jiemin Zhang, Yendo Hu, Erkang Chen, Jingwen Yan, Philippe Fournier-Viger
2021 Wireless Communications and Mobile Computing  
The experimental results showed that the proposed method effectively separates Chinese characters from noisy background.  ...  Separating printed or handwritten characters from a noisy background is valuable for many applications including test paper autoscoring.  ...  In the results, we show the visual effect of separating the handwritten part and the printed part, respectively, of four different common Chinese fonts.  ... 
doi:10.1155/2021/9922017 fatcat:gx4ofxf33rg2lgcun2bdlvmg3m

Counteracting Dark Web Text-Based CAPTCHA with Generative Adversarial Learning for Proactive Cyber Threat Intelligence [article]

Ning Zhang, Mohammadreza Ebrahimi, Weifeng Li, Hsinchun Chen
2022 arXiv   pre-print
This framework encompasses a novel generative method to recognize dark web text-based CAPTCHA with noisy background and variable character length.  ...  To eliminate the need for human involvement, the proposed framework utilizes Generative Adversarial Network (GAN) to counteract dark web background noise and leverages an enhanced character segmentation  ...  region and separate the characters from the background [36] .  ... 
arXiv:2201.02799v2 fatcat:nepnavt6onaf7ncinm2x6ar5ey

Unsupervised Typography Transfer [article]

Hanfei Sun, Yiming Luo, Ziang Lu
2018 arXiv   pre-print
Sometimes the pairing is time-costing, and sometimes there is no perfect pairing, such as the pairing between traditional Chinese and simplified Chinese characters.  ...  Some recent work on computer vision proposes a brand new approach: to treat every Chinese character as an independent and inseparable image, so the pre-processing and post-processing of each character  ...  performance is poor and there are still noisy pixels in the background.  ... 
arXiv:1802.02595v1 fatcat:jb2jmqm3gjchpk4325mlc6ws6u

SCFont: Structure-Guided Chinese Font Generation via Deep Stacked Networks

Yue Jiang, Zhouhui Lian, Yingmin Tang, Jianguo Xiao
To address those problems, this paper proposes a structure-guided Chinese font generation system, SCFont, by using deep stacked networks.  ...  The key idea is to integrate the domain knowledge of Chinese characters with deep generative networks to ensure that high-quality glyphs with correct structures can be synthesized.  ...  , even the most commonly used Chinese charset (i.e., GB2312) is composed of 6763 characters.  ... 
doi:10.1609/aaai.v33i01.33014015 fatcat:6zqips3w3retzejptdtubglew4

Stylized Adversarial AutoEncoder for Image Generation

Yiru Zhao, Bing Deng, Jianqiang Huang, Hongtao Lu, Xian-Sheng Hua
2017 Proceedings of the 2017 ACM on Multimedia Conference - MM '17  
content feature, both encoded from real images.  ...  The split of the latent vector enables us adjusting the content and the style of the generated image arbitrarily by choosing di erent exemplary images.  ...  from being noisy and incomprehensible [5, 10] .  ... 
doi:10.1145/3123266.3123450 dblp:conf/mm/ZhaoDHLH17 fatcat:hnmoizwspnbanis3p3ncfhcrq4

Research and implementation of license plate recognition based on android platform

Yueyue Sun, Xuechen Zhao, J. Joo
2020 MATEC Web of Conferences  
library is generated by using jtessboxeditor tool, which realizes offline recognition of license plate number.  ...  On the basis of fully understanding the principle of Tesseract OCR recognition, a large number of training pictures are generated by license plate number simulation generator, and license plate character  ...  The Chinese characters are not all Chinese characters, but only Beijing, Tianjin, Shanghai, Chongqing, Hebei, Henan, Yunnan, Liaoning, Hei, Xiang, Anhui, Shandong, Xin, Su, Zhejiang, Gan, Hubei, Gui, Gan  ... 
doi:10.1051/matecconf/202030903034 fatcat:q3koso5z2jazdo5dkodbhfotuu

Adversarial Generation of Handwritten Text Images Conditioned on Sequences [article]

Eloi Alonso, Bastien Moysset, Ronaldo Messina
2019 arXiv   pre-print
We use bidirectional LSTM recurrent layers to get an embedding of the word to be rendered, and we feed it to the generator network.  ...  Together, these extensions to GAN enable to control the textual content of the generated word images.  ...  Chinese characters from a printed font.  ... 
arXiv:1903.00277v1 fatcat:y6xjm5uxhreqjow4as7evvle4y

A Survey on Generative Adversarial Networks: Variants, Applications, and Training [article]

Abdul Jabbar, Xi Li, Bourahla Omar
2020 arXiv   pre-print
We survey, (I) the original GAN model and its modified classical versions, (II) detail analysis of various GAN applications in different domains, (III) detail study about the various GAN training obstacles  ...  Therefore, stable training is a crucial issue in different applications for the success of GAN.  ...  LSCGAN generates a new Chinese character font style by fusing the existing Chinese characters font styles.  ... 
arXiv:2006.05132v1 fatcat:gyjezuh5sfdilkp43ydsea5cwa

Research on License Plate Recognition Algorithms Based on Deep Learning in Complex Environment

Wang Weihong, Tu Jiaoyang
2020 IEEE Access  
License plate recognition systems are widely used in modern smart cities, such as toll payment systems, parking fee payment systems and residential access control.  ...  The traditional location recognition algorithm is easily affected by light, shadow, background complexity or other factors, resulting in the failure to meet the application of real scenes.  ...  Finally, seven recognizers recognize each segment, the first recognizer separately trained for the Chinese character, and the rest six recognizers share weights.  ... 
doi:10.1109/access.2020.2994287 fatcat:7l72osyti5c77n6dnpjztknsdq

One to Multiple Mapping Dual Learning: Learning Multiple Sources from One Mixed Signal [article]

Ting Liu, Wenwu Wang, Xiaofei Zhang, Zhenyin Gong, Yina Guo
2021 arXiv   pre-print
Single channel blind source separation (SCBSS) refers to separate multiple sources from a mixed signal collected by a single sensor.  ...  To address these problems, an algorithm is proposed in this paper to separate multiple sources from a mixture by designing a parallel dual generative adversarial Network (PDualGAN) that can build the relationship  ...  Due to the erosion of time, the loss of ancient Chinese characters often occurs in unearthed cultural relics and ancient books.  ... 
arXiv:2110.06568v3 fatcat:aynptmorm5hlndryrmhp67ig2y

Neural Storyboard Artist: Visualizing Stories with Coherent Image Sequences [article]

Shizhe Chen, Bei Liu, Jianlong Fu, Ruihua Song, Qin Jin, Pingping Lin, Xiaoyu Qi, Chunting Wang, Jin Zhou
2019 arXiv   pre-print
The creator then employs three rendering steps to increase the flexibility of retrieved images, which include erasing irrelevant regions, unifying styles of images and substituting consistent characters  ...  ACKNOWLEDGMENTS The authors would like to thank Qingcai Cui for cinematic image collection, Yahui Chen and Huayong Zhang for their efforts in 3D character substitution.  ...  Since the GraphMovie dataset is in Chinese, we translate the training set from English to Chinese via an automatic machine translation API 3 .  ... 
arXiv:1911.10460v1 fatcat:bj2zgw2rbvbjxjwz5em4w57hle

Vehicle Number Plate Detection and Recognition Techniques: A Review

Shahnaj Parvin, Liton Jude Rozario, Md. Ezharul Islam
2021 Advances in Science, Technology and Engineering Systems  
Hopefully, for future research, this review would be very useful.  ...  , what datasets have been focused on, what kinds of characters have been recognized and how much progress have been achieved.  ...  To separate license plates from related items, they also used a plate pre-identification algorithm.  ... 
doi:10.25046/aj060249 fatcat:dcuo3yztmvcctjdf6vlmrqzljq

Review of end-to-end speech synthesis technology based on deep learning [article]

Zhaoxi Mu, Xinyu Yang, Yizhuo Dong
2021 arXiv   pre-print
Moreover, this paper also summarizes the open-source speech corpus of English, Chinese and other languages that can be used for speech synthesis tasks, and introduces some commonly used subjective and  ...  It contains roughly 85 hours of emotion-neutral recordings spoken by 218 native Chinese mandarin speakers, as well as transcripts in Chinese character-level and pinyin-level.  ...  Meanwhile, Chinese characters are ideograms, which are not directly related to pronunciation. It is necessary to convert the original Chinese text into phonemes or pinyin as audio transcription.  ... 
arXiv:2104.09995v1 fatcat:q5lx74ycx5hobjox4ktl3amfta

A Robust Attentional Framework for License Plate Recognition in the Wild [article]

Linjiang Zhang, Peng Wang, Hui Li, Zhen Li, Chunhua Shen, Yanning Zhang
2020 arXiv   pre-print
The dataset can be available from:  ...  Moreover, we released a new license plate dataset, named "CLPD", with 1200 images from all 31 provinces in mainland China.  ...  The entry flow downsamples the spatial size from 160 × 48 to 40×6 and increases the feature channel from 3 to 256 using interleaved separable convolutions and max-poolings.  ... 
arXiv:2006.03919v2 fatcat:av4rltgmf5ernn2j4xmqexcruq

Paint4Poem: A Dataset for Artistic Visualization of Classical Chinese Poems [article]

Dan Li, Shuai Wang, Jie Zou, Chang Tian, Elisha Nieuwburg, Fengyuan Sun, Evangelos Kanoulas
2021 arXiv   pre-print
Thefirst part of Paint4Poem consists of 301 high-quality poem-painting pairs collected manually from an influential modern Chinese artistFeng Zikai.  ...  In this work we propose a new task: artistic visualization of classical Chinese poems, where the goal is to generatepaintings of a certain artistic style for classical Chinese poems.  ...  The average length of captions are only 6 characters. Painting style. All the paintings in Zikai-Caption are from Feng Zikai, thus they can provide useful signals to learn his painting style.  ... 
arXiv:2109.11682v2 fatcat:d6x4c3g6jnev5e2zxvx4pbvjpy
« Previous Showing results 1 — 15 out of 470 results