2019
DOI: 10.1016/j.image.2019.05.020
|View full text |Cite
|
Sign up to set email alerts
|

First steps toward CNN based source classification of document images shared over messaging app

Abstract: Knowledge of source smartphone corresponding to a document image can be helpful in a variety of applications including copyright infringement, ownership attribution, leak identification and usage restriction. In this letter, we investigate a convolutional neural network-based approach to solve source smartphone identification problem for printed text documents which have been captured by smartphone cameras and shared over messaging platform. In absence of any publicly available dataset addressing this problem,… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2020
2020
2022
2022

Publication Types

Select...
5

Relationship

0
5

Authors

Journals

citations
Cited by 7 publications
(3 citation statements)
references
References 34 publications
0
3
0
Order By: Relevance
“…If the original images are directly fed to the CNN-based model, the values in the feature map would be extremely large, which may result in difficulty in the convergence of a training process. Therefore, the RGB values are rescaled into the range (0, 1) by multiplying 1/255 factor in this study [47]. Regarding the database of stress-strain relationships, to eliminate the effect of scale difference of input parameters on the training process of BiLSTM, all datasets are normalized into the range of (-1, 1) using the Min-Max scaling method.…”
Section: Data Preprocessingmentioning
confidence: 99%
“…If the original images are directly fed to the CNN-based model, the values in the feature map would be extremely large, which may result in difficulty in the convergence of a training process. Therefore, the RGB values are rescaled into the range (0, 1) by multiplying 1/255 factor in this study [47]. Regarding the database of stress-strain relationships, to eliminate the effect of scale difference of input parameters on the training process of BiLSTM, all datasets are normalized into the range of (-1, 1) using the Min-Max scaling method.…”
Section: Data Preprocessingmentioning
confidence: 99%
“…Therefore, RGB values are rescaled to the range (0, 1) by multiplying 1/255 factor before training model. 38…”
Section: Data Pre-processingmentioning
confidence: 99%
“…Large RGB values are sensitive to the variation of weights and biases, leading to the difficulty in the convergence of the training process and stability of the model. Therefore, RGB values are rescaled to the range (0, 1) by multiplying 1/255 factor before training model 38 …”
Section: Modelling Process Using 3d‐cnnmentioning
confidence: 99%