Efficient source camera identification with diversity-enhanced patch selection and deep residual prediction

Yunxia Liu, Zeyu Zou, Yang Yang, Ngai Fong Bonnie Law, Anil Anthony Bharath

Research output: Journal article publicationJournal articleAcademic researchpeer-review

25 Citations (Scopus)


Source camera identification has long been a hot topic in the field of image forensics. Besides conventional feature engineering algorithms developed based on studying the traces left upon shooting, several deep-learning-based methods have also emerged recently. However, identification performance is susceptible to image content and is far from satisfactory for small image patches in real demanding applications. In this paper, an efficient patch-level source camera identification method is proposed based on a convolutional neural network. First, in order to obtain improved robustness with reduced training cost, representative patches are selected according to multiple criteria for enhanced diversity in training data. Second, a fine-grained multiscale deep residual prediction module is proposed to reduce the impact of scene content. Finally, a modified VGG network is proposed for source camera identification at brand, model, and instance levels. A more critical patch-level evaluation protocol is also proposed for fair performance comparison. Abundant experimental results show that the proposed method achieves better results as compared with the state-of-the-art algorithms.

Original languageEnglish
Article number4701
Pages (from-to)1-22
Number of pages22
Issue number14
Publication statusPublished - 2 Jul 2021


  • Convolutional neural network
  • Deep learning
  • Image forensics
  • Imaging sensors
  • Source camera identification

ASJC Scopus subject areas

  • Analytical Chemistry
  • Information Systems
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Instrumentation
  • Electrical and Electronic Engineering


Dive into the research topics of 'Efficient source camera identification with diversity-enhanced patch selection and deep residual prediction'. Together they form a unique fingerprint.

Cite this