The goal of the competition on Kaggle platform was to build an algorithm that identifies which camera model captured a given image by using traces intrinsically left in the raw image.

The list of camera models for the challenge:

  • Sony NEX-7
  • Motorola Moto X
  • Motorola Nexus 6
  • Motorola DROID MAXX
  • LG Nexus 5x
  • Apple iPhone 6
  • Apple iPhone 4s
  • HTC One M7
  • Samsung Galaxy S4
  • Samsung Galaxy Note 3

The final result of participation: the 15th place out of 582 teams (top-3%, Kaggle silver megal).

Contents:

  1. Camera model identification with deep learning
  2. An approach to predicted class balancing

Competition posts

Title img
21 Feb 2018

An approach to predicted class balancing

An approach how to increase your position on a leaderpoard in a classification datascience competition by balancing predictions.

7 mins read
Title img
20 Feb 2018

Camera model identification with deep learning

Ideas and approach to the Kaggle IEEE's Signal Processing Society - Camera Model Identification challenge.

5 mins read