muntakimrafi Goto Github PK

6-pack

"6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints" code repository

anti-forensics-using-gan

Median Filtered Image Restoration and Anti-Forensics Using Adversarial Networks

application-of-densenet-in-camera-model-identification-and-post-processing-detection

Camera model identification has earned paramount importance in the field of image forensics with an upsurge of digitally altered images which are constantly being shared through websites, media, and social applications. But, the task of identification becomes quite challenging if metadata are absent from the image and/or if the image has been post-processed. In this paper, we present a DenseNet pipeline to solve the problem of identifying the source camera-model of an image. Our approach is to extract patches of 256 x 256 from a labeled image dataset and apply augmentations, i.e., Empirical Mode Decomposition (EMD). We use this extended dataset to train a Neural Network with the DenseNet-201 architecture. We concatenate the output features for 3 different sizes (64x64, 128x128, 256x256) and pass them to a secondary network to make the final prediction. This strategy proves to be very robust for identifying the source camera model, even when the original image is post-processed. Our model has been trained and tested on the Forensic Camera-Model Identification Dataset provided for the IEEE Signal Processing (SP) Cup 2018. During testing we achieved an overall accuracy of 98.37%, which is the current state-of-the-art on this dataset using a single model. We used transfer learning and tested our model on the Dresden Database for Camera Model Identification, with an overall test accuracy of over 99% for 19 models. In addition, we demonstrate that the proposed pipeline is suit- able for other image-forensic classification tasks, such as, detecting the type of post-processing applied to an image with an accuracy of 96.66% - which indicates the generality of our approach.

awesome-datascience

:memo: An awesome Data Science repository to learn and apply for real world problems.

awesome-steganalysis-project

🍿️some awesome Steganalysis

caltech.ml

Machine learning course from Caltech

celloracle

This is the alpha version of the CellOracle package

chrombpnet-torch

This repository hosts a minimal version of a Python API for BPNet.

cisregmodels

Scripts for building computational models of gene regulation with tensorflow

cnn_finetune

Fine-tune CNN in Keras

coarse2fine-imacomp

compute-canada-hpc

Beginner tutorials and help for using Compute Canada's High Performance Computer. Learn to setup and run a Jupyter Notebook!

courses

fast.ai Courses

deep-learning-papers-reading-roadmap

Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!

deepmind-research

This repository contains implementations and illustrative code to accompany DeepMind publications

digital-image-forensics

Digital Image Forensics to indentify the source camera

effcossim

Efficient Pairwise Cosine Similarity Computation

enforemer_embeddings

Repository containing code to extract the embeddings of the Enformer model.

evolution

This repository contains the code for our manuscript - 'The evolution, evolvability, and engineering gene regulatory DNA'

forensicimages

Final project for DA

forensics-tool-hybrid-g-prnu-extractor

State of the Art Image/Video Forensics Tool : Hybrid-G-PRNU-Extractor based on the work of Muammar, to additionally extract green channel photo response noise uniformity (G-PRNU) with customization of different sizes and interpolation methods. Also additionally, Li's PRNU enhancement is implemented.

ganhacks

starter from "How to Train a GAN?" at NIPS2016

grav-theme-ceevee

Ceevee is a clean, modern, fully responsive site template for your resume and portfolio. With this template, you can easily introduce yourself and showcase your works to future clients and employers. Also, it is flexible and easy to customize so you even use this template as a creative, business or portfolio site for your company.

image-denoising-state-of-the-art

image-forensics-mfsec17

Automated Large Scale Image Forensics using Tika and Tensorflow

image-forgery-detection-cnn-vs-transfer-learning-comparison

The binary classification problem focused on first IEEE Image forensics challenge-phase 1, to predict the given image is pristine or manipulated/edited/fake. Comparing CNN & Transfer Learning models for the problem and boosting the performance by feature extraction

imageforensics

Learning Manipulation-Invariant Image Similarity for Detecting Re-Use of Images in Scientific Publications

improved_ccgan

Continuous Conditional Generative Adversarial Networks for Image Generation

insbcn

Code used in the paper "Learning from #Barcelona Instagram data what Locals and Tourists post about its Neighbourhoods" ECCV 2018 MULA Workshop

instagram-scraper

scrapes medias, likes, followers, tags and all metadata. Inspired by instagram-php-scraper,bot