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, we introduce a new image dataset consisting of 315 images of documents printed in three different fonts, captured using 21 smartphones and shared over WhatsApp.Experiments conducted on this dataset demonstrate that, in all scenarios, the proposed system performs as well as or better than the state-of-the-art system based on handcrafted features and classification of letters extracted from document images. The new dataset and code of the proposed system will be made publicly available along with this letter's publication, presently they are submitted for review.

A novel deep learning-based modelling strategy from image of particles to mechanical properties for granular materials with CNN and BiLSTM

“…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.…”

Three‐dimensional quantitative analysis on granular particle shape using convolutional neural network

“…Therefore, RGB values are rescaled to the range (0, 1) by multiplying 1/255 factor before training model. 38…”

“…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 …”