Web Identification Image Recognition Based on Deep Learning

Zhao, Yanling; Zhang, Xinchang; Mei, Xu; Sun, Zhanquan; Liu, Guangqi; Li, Shifeng

doi:10.1109/icisce.2016.164

Cited by 1 publication

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhao et al [7] communicates worries over the creation of information as loads of information is being produced each day. Huge data is a promising field that can procedure these gigantic measures of information to get gainful bits of knowledge from it.…”

Section: Literature Reviewmentioning

confidence: 99%

Fake colorized and morphed image detection using convolutional neural network

Pillai¹

2020

TIPCV

View full text Add to dashboard Cite

As the technology develops, utilization of the phony pictures is at highest, So, as per an overview most of the pictures stored on the server or in the cloud are being transformed or counterfeit. As a result, it is difficult to identify whether the images stored are real or not. So not many systems are existing today which are equipped to tell whether pictures are fake or not. Earlier Histogram based and feature extraction-based methods were used to identify fake images. The neural network is being the most advanced technology distinguishes the phony pictures by studying various features of the image and learning the procedure of faking an image. So as a minor advance towards this, proposed system uses features like dark channel, bright channel, RGB channel and alpha channel. Using Gaussian distribution, we can anlayze the edges of the images to identify phony images. Deep layer analysis is performed using convolutional neural system along with the fuzzy classification procedure to improve the likelihood of recognizing phony pictures. Through this research it is concluded that convolutional neural networks (CNN) based fake colorized image detection showcases a better result than histogram based and feature extraction based fake colorized image detection.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Fake colorized and morphed image detection using convolutional neural network

Pillai¹

2020

TIPCV

View full text Add to dashboard Cite

show abstract

Web Identification Image Recognition Based on Deep Learning

Cited by 1 publication

References 6 publications

Fake colorized and morphed image detection using convolutional neural network

Fake colorized and morphed image detection using convolutional neural network

Contact Info

Product

Resources

About