Bio

Bio


Christian Riess received his diploma degree in theoretical computer science in 2007 and his doctoral degree in pattern recognition in 2013, both from the University of Erlangen-Nuremberg, Germany. From 2007 to 2010, he was working on an industry project with Giesecke+Devrient on optical inspection of banknotes. In his PhD thesis, Christian proposed novel physics-based and statistical features to detect manipulations in digital photographs. During his PhD project, he collaborated with Joost van de Weijer's group at the Computer Vision Center in Barcelona, Spain, and the RECOD lab at the University of Campinas, Brazil.
As a postdoctoral researcher, Christian joined the Radiological Sciences Laboratory at Stanford University, where he is focusing on medical image processing. His research goal is to investigate the translation of phase-contrast X-ray to clinical applications, to obtain high-resolution, ultra low-dose radiographs of soft tissue. Christian has authored and coauthored four publications in high-profile image processing journals, and more than 20 peer-reviewed conference contributions on multimedia security, color imaging and pattern recognition.

Honors & Awards


  • 1st place with team de.tector, category "format-based attacks", 1st IEEE IFS-TC Image Forensics Challenge (2013)
  • 3rd place at the teaching evaluation for exercises, School of Engineering, University of Erlangen-Nuremberg (2013)
  • Young Researcher Award, 10th Workshop on Parallel Systems and Algorithms (2012)
  • 1st place, CiberMouse Contest at IEEE Real-Time Systems Symposium (2007)
  • 2nd place at the local competition, International Collegiate Programming Contest (2004)
  • 2nd place at the "Schulen im Wandel" competition, Melanchthon-Gymnasium Nuremberg (2001)
  • Melanchthon award for distinguished honorary services, Melanchthon-Gymnasium Nuremberg (1999)

Boards, Advisory Committees, Professional Organizations


  • Member, IEEE (2009 - Present)
  • Member, Gesellschaft fuer Informatik (2002 - Present)

Professional Education


  • Diplom, Universitat Erlangen Nurnberg (2007)
  • Doctor, Universitat Erlangen Nurnberg (2013)

Stanford Advisors


Research & Scholarship

Current Research and Scholarly Interests


When light waves traverse matter, the phase of the wave is subject to a subtle shift in the phase. Recently, it became possible to observe phase shifts with conventional X-ray tubes, promising unprecedented insights into the human body. However, it is up to now not yet clear how these findings can be effectively exploited in a clinical environment. Still, if a way is found to use phase-sensitive X-ray routinely for diagnosis, we have a completely new modality at hand that allows imaging small differences in soft tissue at ultra-high resolution at a dose that is comparable or even lower than traditional X-ray.

My particular research is on translating this exciting technology to clinical practice. As an image processing expert, my particular strength lies in visualizing and enhancing the data beyond the limitations of the hardware. As such, I am acting at the interface between the raw data generation from the phase-sensitive imaging system and the radiologists who visually interpret the data for early detection of cancer. One particularly interesting question is which information within the very cluttered raw data is actually the most relevant for successful diagnosis, and how to tailor image processing algorithms to optimally enhance these tell-tales.

Publications

Journal Articles


  • Multi-Illuminant Estimation With Conditional Random Fields IEEE TRANSACTIONS ON IMAGE PROCESSING Beigpour, S., Riess, C., van de Weijer, J., Angelopoulou, E. 2014; 23 (1): 83-96

    Abstract

    Most existing color constancy algorithms assume uniform illumination. However, in real-world scenes, this is not often the case. Thus, we propose a novel framework for estimating the colors of multiple illuminants and their spatial distribution in the scene. We formulate this problem as an energy minimization task within a conditional random field over a set of local illuminant estimates. In order to quantitatively evaluate the proposed method, we created a novel data set of two-dominant-illuminant images comprised of laboratory, indoor, and outdoor scenes. Unlike prior work, our database includes accurate pixel-wise ground truth illuminant information. The performance of our method is evaluated on multiple data sets. Experimental results show that our framework clearly outperforms single illuminant estimators as well as a recently proposed multi-illuminant estimation approach.

    View details for DOI 10.1109/TIP.2013.2286327

    View details for Web of Science ID 000329195500007

    View details for PubMedID 24144663

  • CONRAD-A software framework for cone-beam imaging in radiology MEDICAL PHYSICS Maier, A., Hofmann, H. G., Berger, M., Fischer, P., Schwemmer, C., Wu, H., Mueller, K., Hornegger, J., Choi, J., Riess, C., Keil, A., Fahrig, R. 2013; 40 (11)

    Abstract

    In the community of x-ray imaging, there is a multitude of tools and applications that are used in scientific practice. Many of these tools are proprietary and can only be used within a certain lab. Often the same algorithm is implemented multiple times by different groups in order to enable comparison. In an effort to tackle this problem, the authors created CONRAD, a software framework that provides many of the tools that are required to simulate basic processes in x-ray imaging and perform image reconstruction with consideration of nonlinear physical effects.CONRAD is a Java-based state-of-the-art software platform with extensive documentation. It is based on platform-independent technologies. Special libraries offer access to hardware acceleration such as OpenCL. There is an easy-to-use interface for parallel processing. The software package includes different simulation tools that are able to generate up to 4D projection and volume data and respective vector motion fields. Well known reconstruction algorithms such as FBP, DBP, and ART are included. All algorithms in the package are referenced to a scientific source.A total of 13 different phantoms and 30 processing steps have already been integrated into the platform at the time of writing. The platform comprises 74.000 nonblank lines of code out of which 19% are used for documentation. The software package is available for download at http://conrad.stanford.edu. To demonstrate the use of the package, the authors reconstructed images from two different scanners, a table top system and a clinical C-arm system. Runtimes were evaluated using the RabbitCT platform and demonstrate state-of-the-art runtimes with 2.5 s for the 256 problem size and 12.4 s for the 512 problem size.As a common software framework, CONRAD enables the medical physics community to share algorithms and develop new ideas. In particular this offers new opportunities for scientific collaboration and quantitative performance comparison between the methods of different groups.

    View details for DOI 10.1118/1.4824926

    View details for Web of Science ID 000326991800041

    View details for PubMedID 24320447

  • Exposing Digital Image Forgeries by Illumination Color Classification IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY de Carvalho, T. J., Riess, C., Angelopoulou, E., Pedrini, H., Rocha, A. d. 2013; 8 (7): 1182-1194
  • An Evaluation of Popular Copy-Move Forgery Detection Approaches IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY Christlein, V., Riess, C., Jordan, J., Riess, C., Angelopoulou, E. 2012; 7 (6): 1841-1854

Stanford Medicine Resources: